NAGAOKA Takashi
Department of Computational Systems Biology | Associate Professor |
■Researcher basic information
ORCID ID
J-Global ID
Research Keyword
- メラノーマ ハイパースペクトラルイメージング 表在性腫瘍 無侵襲計測 生体情報・計測 眼底 応用分光学 医療機器開発 内視鏡 検査・診断システム 医用・生体画像
Research Field
■Career
Career
- 2023/04 - Today Kindai UniversityFaculty of Biology-Oriented Science and Technology Department of Computational Systems BiologyAssociate Professor
- 2015/04 - 2023/03 Kindai UniversityFaculty of Biology-Oriented Science and Technology, Department of Computational Systems Biology講師
- 2009/04 - 2015/03 Waseda UniversityFaculty of Science and Engineering次席研究員
- 2006/04 - 2009/03 県立静岡がんセンター研究所任期付研究員
- 2003/04 - 2006/03 Waseda UniversitySchool of Science and Engineering助手
Educational Background
■Research activity information
Award
- 2024/02 SPIE Honorable Mention Poster Award
Unsupervised lung lesion detection on FDG-PET/CT images by deep image transformation-based 2.5-dimensional local anomaly detection.受賞者: A Segawa;M Nemoto;H Kaida;Y Kimura;T Nagaoka;K Mikami;T Yamada;K Hanaoka;T Tsuchiya;K Kitajima;K Ishii - 2022/06 日本生体医工学会 臨床工学技士研究発表 奨励賞
深層画像生成技術を用いたFDG-PET/CT像異常検知による病変強調受賞者: 瀬川新;根本充貴;甲斐田勇人;山口明乃;木村裕一;永岡隆;山田誉大;北島一宏;石井一成 - 2019/06 日本生体医工学会 Young Investigator's Award
深層畳み込みオートエンコーダーを用いた健常データの教師無し学習による病変認識特徴量の汎用的自動生成 japan_society受賞者: 牛房和之;根本充貴;木村裕一;永岡隆;山田誉大;林直人 - 2017/09 日本生体医工学会 生体医工学シンポジウム2017ベストレビューワーアワード
受賞者: 永岡 隆 - 2017/07 公益社団法人日本青年会議所 超生産性向上大賞 文部科学大臣賞
超ライフの創出 ~ゆりかごのデータから墓場のデータまで~受賞者: 近畿大学生物理工学部生命情報工学科 - 2017/07 公益社団法人日本青年会議所 超生産性向上大賞 内閣総理大臣賞
超ライフの創出 ~ゆりかごのデータから墓場のデータまで~受賞者: 近畿大学生物理工学部生命情報工学科 - 2015/09 日本生体医工学会 生体医工学シンポジウム2015ベストレビューワーアワード
受賞者: 永岡 隆 - 2009/12 公益社団法人 計測自動制御学会 SI2009 優秀講演賞
受賞者: 永岡 隆 - 2009/02 公益社団法人 計測自動制御学会 計測自動制御学会学術奨励賞 研究奨励賞
受賞者: 永岡 隆 - 2003/08 一般社団法人電気学会 電気学会C部門研究会優秀論文発表賞
受賞者: 永岡 隆
Paper
- Arata Segawa; Mitsutaka Nemoto; Hayato Kaida; Yuichi Kimura; Takashi Nagaoka; Katsuhiro Mikami; Takahiro Yamada; Kohei Hanaoka; Tatsuya Tsuchitani; Kazuhiro Kitajima; Kazunari IshiiMedical Imaging 2024: Imaging Informatics for Healthcare, Research, and Applications SPIE 2024/04
- Mitsutaka Nemoto; Kazuyuki Ushifusa; Yuichi Kimura; Takashi Nagaoka; Takahiro Yamada; Takeharu YoshikawaApplied Sciences MDPI AG 13 (14) 8330 - 8330 2023/07There are growing expectations for AI computer-aided diagnosis: computer-aided diagnosis (CAD) systems can be used to improve the accuracy of diagnostic imaging. However, it is not easy to collect large amounts of disease medical image data with lesion area annotations for the supervised learning of CAD systems. This study proposes an unsupervised local image feature extraction method running without such disease medical image datasets. Local image features are one of the key determinants of system performance. The proposed method requires only a normal image dataset that does not include lesions and can be collected easier than a disease dataset. The unsupervised features are extracted by applying multiple convolutional autoencoders to analyze various 2.5-dimensional images. The proposed method is evaluated by two kinds of problems: the detection of cerebral aneurysms in head MRA images and the detection of lung nodules in chest CT images. In both cases, the performance is high, showing an AUC of more than 0.96. These results show that the proposed method can automatically learn features that are useful for lesion recognition from lesion-free normal data, regardless of the type of image or lesion.
- Mitsutaka Nemoto; Atsuko Tanaka; Hayato Kaida; Yuichi Kimura; Takashi Nagaoka; Takahiro Yamada; Kohei Hanaoka; Kazuhiro Kitajima; Tatsuya Tsuchitani; Kazunari IshiiPhysics in medicine and biology 67 (19) 2022/09 [Refereed]
We propose a method to detect primary and metastatic lesions with Fluorine-18 fluorodeoxyglucose (FDG) accumulation in the lung field, neck, mediastinum, and bony regions on the FDG-PET/CT images. To search for systemic lesions, various anatomical structures must be considered. The proposed method is addressed by using an extraction process for anatomical regions and a uniform lesion detection approach. The uniform approach does not utilize processes that reflect any region-specific anatomical aspects but has a machine-learnable framework. Therefore, it can work as a lesion detection process for a specific anatomical region if it machine-learns the specific region data. In this study, three lesion detection processes for the whole-body bone region, lung field, or neck-mediastinum region are obtained. These detection processes include lesion candidate detection and false positive (FP) candidate elimination. The lesion candidate detection is based on a voxel anomaly detection with a one-class support vector machine. The FP candidate elimination is performed using an AdaBoost classifier ensemble. The image features used by the ensemble are selected sequentially during training and are optimal for candidate classification. Three-fold cross-validation was used to detect performance with the 54 diseased FDG-PET/CT images. The mean sensitivity for detecting primary and metastatic lesions at 3 FPs per case was 0.89 with a 0.10 standard deviation (SD) in the bone region, 0.80 with a 0.10 SD in the lung field, and 0.87 with a 0.10 SD in the neck region. The average areas under the ROC curve were 0.887 with a 0.125 SD for detecting bone metastases, 0.900 with a 0.063 SD for detecting pulmonary lesions, and 0.927 with a 0.035 SD for detecting the neck-mediastinum lesions. These detection performances indicate that the proposed method could be applied clinically. These results also show that the uniform approach has high versatility for providing various lesion detection processes. - Mika Yamamuro; Yoshiyuki Asai; Naomi Hashimoto; Nao Yasuda; Hiroto Kimura; Takahiro Yamada; Mitsutaka Nemoto; Yuichi Kimura; Hisashi Handa; Hisashi Yoshida; Koji Abe; Masahiro Tada; Hitoshi Habe; Takashi Nagaoka; Seiun Nin; Kazunari Ishii; Yongbum Lee16th International Workshop on Breast Imaging (IWBI2022) SPIE 2022/07 [Refereed]
- Mika Yamamuro; Yoshiyuki Asai; Naomi Hashimoto; Nao Yasuda; Hiorto Kimura; Takahiro Yamada; Mitsutaka Nemoto; Yuichi Kimura; Hisashi Handa; Hisashi Yoshida; Koji Abe; Masahiro Tada; Hitoshi Habe; Takashi Nagaoka; Seiun Nin; Kazunari Ishii; Yohan KondoBiomedical Physics & Engineering Express IOP Publishing 8 (4) 045016 - 045016 2022/06 [Refereed]
Abstract This study investigates the equivalence or compatibility between U-Net and visual segmentations of fibroglandular tissue regions by mammography experts for calculating the breast density and mean glandular dose (MGD). A total of 703 mediolateral oblique-view mammograms were used for segmentation. Two region types were set as the ground truth (determined visually): (1) one type included only the region where fibroglandular tissue was identifiable (called the ‘dense region’); (2) the other type included the region where the fibroglandular tissue may have existed in the past, provided that apparent adipose-only parts, such as the retromammary space, are excluded (the ‘diffuse region’). U-Net was trained to segment the fibroglandular tissue region with an adaptive moment estimation optimiser, five-fold cross-validated with 400 training and 100 validation mammograms, and tested with 203 mammograms. The breast density and MGD were calculated using the van Engeland and Dance formulas, respectively, and compared between U-Net and the ground truth with the Dice similarity coefficient and Bland–Altman analysis. Dice similarity coefficients between U-Net and the ground truth were 0.895 and 0.939 for the dense and diffuse regions, respectively. In the Bland–Altman analysis, no proportional or fixed errors were discovered in either the dense or diffuse region for breast density, whereas a slight proportional error was discovered in both regions for the MGD (the slopes of the regression lines were −0.0299 and −0.0443 for the dense and diffuse regions, respectively). Consequently, the U-Net and ground truth were deemed equivalent (interchangeable) for breast density and compatible (interchangeable following four simple arithmetic operations) for MGD. U-Net-based segmentation of the fibroglandular tissue region was satisfactory for both regions, providing reliable segmentation for breast density and MGD calculations. U-Net will be useful in developing a reliable individualised screening-mammography programme, instead of relying on the visual judgement of mammography experts. - Takashi Nagaoka; Takenori Kozuka; Takahiro Yamada; Hitoshi Habe; Mitsutaka Nemoto; Masahiro Tada; Koji Abe; Hisashi Handa; Hisashi Yoshida; Kazunari Ishii; Yuichi KimuraAdvanced Biomedical Engineering Japanese Society for Medical and Biological Engineering 11 76 - 86 2022/03 [Refereed]
- Takashi NagaokaCardiovascular Engineering and Technology Springer Science and Business Media LLC 1869-408X 2021/05
- II-21 Clinical performance of a novel hyperspectral imaging device for cutaneous melanoma and pigmented skin lesions in Caucasian skin.Gustav Boelsgaard; Christensen Takashi Nagaoka; Yoshio Kiyohara; Iva Johansson Christian Ingvar; Atsushi Nakamura; Takayuki Sota; Kari NielsenSkin Res Technol. 27 803 - 809 2021/03 [Refereed]
- Ginji Hirano; Mitsutaka Nemoto; Yuichi Kimura; Yoshio Kiyohara; Hiroshi Koga; Naoya Yamazaki; Gustav Christensen; Christian Ingvar; Kari Nielsen; Atsushi Nakamura; Takayuki Sota; Takashi NagaokaSkin Research and Technology Wiley 26 (6) 891 - 897 0909-752X 2020/11
- Takashi NagaokaAdvanced Biomedical Engineering Japanese Society for Medical and Biological Engineering 9 (0) 225 - 232 2020/08 [Refereed]
- Yuichi Kimura; Aya Watanabe; Takahiro Yamada; Shogo Watanabe; Takashi Nagaoka; Mitsutaka Nemoto; Koichi Miyazaki; Kohei Hanaoka; Hayato Kaida; Kazunari IshiiAnnals of Nuclear Medicine Springer 34 (7) 512 - 515 1864-6433 2020/07Objective: An artificial intelligence (AI)-based algorithm typically requires a considerable amount of training data however, few training images are available for dementia with Lewy bodies and frontotemporal lobar degeneration. Therefore, this study aims to present the potential of cycle-consistent generative adversarial networks (CycleGAN) to obtain enough number of training images for AI-based computer-aided diagnosis (CAD) algorithms for diagnosing dementia. Methods: We trained CycleGAN using 43 amyloid-negative and 45 positive images in slice-by-slice. Results: The CycleGAN can be used to synthesize reasonable amyloid-positive images, and the continuity of slices was preserved. Discussion: Our results show that CycleGAN has the potential to generate a sufficient number of training images for CAD of dementia.
- Yuichi Kimura; Aya Watanabe; Takahiro Yamada; Shogo Watanabe; Takashi Nagaoka; Mitsutaka Nemoto; Koichi Miyazaki; Kohei Hanaoka; Hayato Kaida; Kazunari IshiiAnnals of nuclear medicine 0 (0) 0 - 0 2020/07 [Refereed]
OBJECTIVE: An artificial intelligence (AI)-based algorithm typically requires a considerable amount of training data; however, few training images are available for dementia with Lewy bodies and frontotemporal lobar degeneration. Therefore, this study aims to present the potential of cycle-consistent generative adversarial networks (CycleGAN) to obtain enough number of training images for AI-based computer-aided diagnosis (CAD) algorithms for diagnosing dementia. METHODS: We trained CycleGAN using 43 amyloid-negative and 45 positive images in slice-by-slice. RESULTS: The CycleGAN can be used to synthesize reasonable amyloid-positive images, and the continuity of slices was preserved. DISCUSSION: Our results show that CycleGAN has the potential to generate a sufficient number of training images for CAD of dementia. - II-17 Performance Improvement of Automated Melanoma Diagnosis System by Data AugumentationKana Kato; Mitsutaka Nemoto; Yuichi Kimura; Yoshio Kiyohara; Hiroshi Koga; Naoya Yamazaki; Gustav Christensen; Christian Ingvar; Kari Nielsen; Atsushi Nakamura; Takayuki Sota; Takashi NagaokaAdvanced Biomedical Engineering 9 62 - 70 2020/03 [Refereed]
- Takahiro Yamada; Shogo Watanabe; Takashi Nagaoka; Mitsutaka Nemoto; Kohei Hanaoka; Hayato Kaida; Kazunari Ishii; Yuichi KimuraAnnals of nuclear medicine 34 (2) 102 - 107 2020/02 [Refereed]
OBJECTIVE: This study aims to develop an algorithm named AutoRef to delineate a reference region for quantitative PET amyloid imaging. METHODS: AutoRef sets the reference region automatically using a distinguishing feature in the kinetics of reference region. This is reflected in the shapes of the tissue time activity curve. A statistical shape recognition algorithm of the gaussian mixture model is applied with considering spatial and temporal information on a reference region. We evaluate the BPND with manually set reference region and AutoRef using 86 cases (43 positive cases, 10 equivocal cases, and 33 negative cases) of dynamically scanned 11C-Pittsburgh Compound-B. RESULTS: From the Bland-Altman plot, the difference between two BPND is 0.099 ± 0.21 as standard deviation, and no significant systematic error is observed between the BPND with AutoRef and with manual definition of a reference region. Although a proportional error is detected, it is smaller than the 95% limits of agreement. Therefore, the proportional error is negligibly small. CONCLUSIONS: AutoRef presents the same performance as the manual definition of the reference region. Further, since AutoRef is more algorithmic than the ordinary manual definition of the reference region, there are few operator-oriented uncertainties in AutoRef. We thus conclude that AutoRef can be applied as an automatic delineating algorithm for the reference region in amyloid imaging. - Nagaoka T; Kimura YSkin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging (ISSI) 25 (3) 318 - 324 0909-752X 2019/01 [Refereed]
- Tsuyoshi Oguma; Takashi Nagaoka; Muneshige Kurahashi; Naofumi Kobayashi; Shinji Yamamori; Chizuko Tsuji; Hiroto Takiguchi; Kyoko Niimi; Hiromi Tomomatsu; Katsuyoshi Tomomatsu; Naoki Hayama; Takuya Aoki; Tetsuya Urano; Kazushige Magatani; Sunao Takeda; Tadashi Abe; Koichiro AsanoPLOS ONE PUBLIC LIBRARY SCIENCE 12 (4) e0174802 1932-6203 2017/04 [Refereed]
Background Exhaled volatile organic compounds (VOC) are being considered as biomarkers for various lungs diseases, including cancer. However, the accurate measurement of extremely low concentrations of VOC in expired air is technically challenging. We evaluated the clinical contribution of exhaled VOC measured with a new, double cold-trap method in the diagnosis of lung cancer. Methods Breath samples were collected from 116 patients with histologically confirmed lung cancer and 37 healthy volunteers (controls) after inspiration of purified air, synthesized through a cold-trap system. The exhaled VOC, trapped in the same system, were heat extracted. We analyzed 14 VOC with gas chromatography. Results The concentrations of exhaled cyclohexane and xylene were significantly higher in patients with lung cancer than in controls (p = 0.002 and 0.0001, respectively), increased significantly with the progression of the clinical stage of cancer (both p < 0.001), and decreased significantly after successful treatment of 6 patients with small cell lung cancer (p = 0.06 and 0.03, respectively). Conclusion Measurements of exhaled VOCs by a double cold-trap method may help diagnose lung cancer and monitor its progression and regression. - III-14 生物理工学部における工学系教育へのアクティブラーニング導入の取り組みの一例永岡 隆近畿大学生物理工学部紀要 40 25 - 32 2017/03 [Refereed]
- Takuya Aoki; Takashi Nagaoka; Naofumi Kobayashi; Muneshige Kurahashi; Chizuko Tsuji; Hiroto Takiguchi; Katsuyoshi Tomomatsu; Tsuyoshi Oguma; Naoki Kobayashi; Kazushige Magatani; Sunao Takeda; Koichiro Asano; Tadashi AbeTOXICOLOGICAL SCIENCES OXFORD UNIV PRESS 156 (2) 362 - 374 1096-6080 2016/12 [Refereed]
Various volatile organic compounds (VOCs) are known to be toxic. Although exhaled VOC patterns change in obstructive sleep apnea (OSA) patients, individual VOC profiles are not fully determined. The primary outcome was VOC characterizations; secondary outcomes included their relationships with sleep and clinical parameters in OSA patients. We prospectively examined 32 OSA patients with an apnea-hypopnea index (AHI) >= 15 by full polysomnography, and 33 age-and sex-matched controls without obvious OSA symptoms. Nine severe OSA patients were examined before and after continuous positive airway pressure (CPAP) treatment. By applying amethod which eliminates environmental VOC influences, exhaled VOCs were identified by gas chromatography (GC)-mass spectrometry, and their concentrations were determined by GC. Exhaled aromatic hydrocarbon concentrations (toluene, ethylbenzene, p-xylene, and phenylacetic acid) in the severe OSA groups (AHI >= 30) and exhaled saturated hydrocarbon concentrations (hexane, heptane, octane, nonane, and decane) in themost severe OSA group (AHI >= 60) were higher than those in the control group. Exhaled isoprene concentrations were increased in all OSA groups (AHI >= 15); acetone concentration was increased in the most severe OSA group. Ethylbenzene, p-xylene, phenylacetic acid, and nonane concentrations were increased according to OSA severity, and correlated with AHI, arousal index, and duration of percutaneous oxygen saturation (SpO(2)) <= 90%. Multiple regression analyses revealed these 4 VOC levels were associated with the duration of SpO(2) <= 90%. Isoprene and acetone decreased after CPAP treatment. OSA increased some toxic VOCs, and some correlated with OSA severity. CPAP treatment possibly ameliorates these productions. - NAGAOKA TakashiAdvanced Biomedical Engineering 5 111 - 117 2016/07 [Refereed]
- Atsushi Nakamura; Hidekazu Okuda; Takashi Nagaoka; Norimitsu Akiba; Kenji Kurosawa; Kenro Kuroki; Fumihiko Ichikawa; Akira Torao; Takayuki SotaFORENSIC SCIENCE INTERNATIONAL ELSEVIER IRELAND LTD 254 100 - 105 0379-0738 2015/07 [Refereed]
Untreated latent fingerprints are known to exhibit fluorescence under UV laser excitation. Previously, the hyperspectral imager (HSI) has been primarily evaluated in terms of its potential to enhance the sensitivity of latent fingerprint detection following treatment by conventional chemical methods in the forensic science field. In this study however, the potential usability of the HSI for the visualization and detection of untreated latent fingerprints by measuring their inherent fluorescence under continuous wave (CW) visible laser excitation was examined. Its potential to undertake spectral separation of overlapped fingerprints was also evaluated. The excitation wavelength dependence of fluorescent images was examined using an untreated palm print on a steel based wall, and it was found that green laser excitation is superior to blue and yellow lasers' excitation for the production of high contrast fluorescence images. In addition, a spectral separation method for overlapped fingerprints/palm prints on a plaster wall was proposed using new images converted by the division and subtraction of two single wavelength images constructed based on measured hyperspectral data (HSD). In practical tests, the relative isolation of two overlapped fingerprints/palm prints was successful in twelve out of seventeen cases. Only one fingerprint/palm print was extracted for an additional three cases. These results revealed that the feasibility of overlapped fingerprint/palm print spectral separation depends on the difference in the temporal degeneration of each fluorescence spectrum. The present results demonstrate that a combination of a portable HSI and CW green laser has considerable potential for the identification and detection of untreated latent fingerprints/palm prints on the walls under study, while the use of HSD makes it practically possible for doubly overlapped fingerprints/palm prints to be separated spectrally. (C) 2015 Elsevier Ireland Ltd. All rights reserved. - Nagaoka Takashi; Kanou Saki; Kobayashi Naofumi; Kurahashi Muneshige; Oguma Tsuyoshi; Tsuji Chizuko; Aoki Takuya; Urano Tetsuya; Magatani Kazushige; Asano Koichiro; Abe Tadashi; Takeda SunaoADVANCED BIOMEDICAL ENGINEERING Japanese Society for Medical and Biological Engineering 4 112 - 118 2187-5219 2015/06 [Refereed]
Volatile organic compounds (VOCs) are organic chemical substances that volatilize easily in ambient air at normal temperature and pressure. VOCs in human expired gas have been reported to be useful in the diagnosis of various diseases, but measurement of VOCs in human expired gas is technically difficult because the concentrations in expired gas are extremely low and almost the same as the concentrations in ambient air. Accurate VOC measurement usually requires a large system, and no VOC measuring systems suitable for clinical practice are available. We developed a compact, simple, double cold trap system that can measure the concentrations of VOCs originating in humans. Our system detects a limited number of VOCs with very high sensitivity at concentrations as low as 0.05 ppb. We evaluated the reproducibility of our system and measured VOCs in ambient air, purified air, and human expired gas from smokers, non-smokers, and patients. Errors of ±10% seem unavoidable in our system. Our verification experiment using human expired gas strongly suggests that the reproducibility and detection sensitivity of our system allow the detection of most VOCs in human expired gas. - T. Nagaoka; A. Nakamura; T. Yamazaki; Y. Nakata; K. Endo; T. Sakaguchi; N. Kawata; T. Sota2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE 218 - 221 1557-170X 2014/08 [Refereed]
Hyperspectral imaging system for diagnosing digestive diseases was newly developed in order to obtain information on pathology beyond morphology of lesions. In order to guide light reflected from a lesion, a baby fiber, which can be inserted in a forceps channel of the electronic endoscope, was also developed. The performance of the system was evaluated by animal experiment. Obtained hyperspectral data were found to have sufficient quality endurable to practical use. Harmful phenomena to a living body were not observed within the experiment. It was considered from the animal experiment that the present system could be practically used for humans. - T. Nagaoka; Y. Kiyohara; H. Koga; A. Nakamura; T. Saida; T. SotaSKIN RESEARCH AND TECHNOLOGY WILEY-BLACKWELL 21 (3) 278 - 283 0909-752X 2014/08 [Refereed]
BackgroundThe morphology of pigmented skin lesions (PSLs) is predominantly a result of varying concentrations and distributions of pigmented molecules such as melanin and hemoglobin. Based on these differences and the fact that their information is contained in cutaneous spectra, a hyperspectral imager (HSI) for pigmented melanoma and a single discrimination index derived from the resultant hyperspectral data are proposed. ObjectiveTo develop and evaluate a new discrimination index for melanomas, compared to the previous index. MethodsA HSI, which is convenient for both patients and clinicians, was newly developed and used in a clinical trial conducted in 2 centers with 80 patients with primary lesions and 17 volunteers between March 2011 and December 2013. There were 24 melanomas and 110 other PSLs. A previously proposed discrimination index was used without modifications. A new index, which emphasized the essential features of melanoma, was proposed, and its performance was examined. For each index, a threshold value was set to minimize the average value of the false positive and false negative fractions. The performances of both indices were compared. ResultsThe sensitivity and specificity of the old index were 75% and 97%, respectively, while those of the new index were 96% and 87%. ConclusionThe new index had a higher sensitivity and adequate specificity, indicating that it is more useful than the old index. - S. Kanou; T. Nagaoka; N. Kobayashi; M. Kurahashi; S. Takeda; T. Aoki; T. Tsuji; T. Urano; T. Abe; K. MagataniProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 3837 - 3840 1557-170X 2013/07 [Refereed]
A new concept expired gas measurement system used double cold-trap method was developed. The system could detect selectively volatile organic compound (VOC) derived from the human body. The gas chromatography (GC) profiles of healthy volunteer's expired gas collected by our system were analyzed. As a result, 60 VOCs were detected from the healthy volunteer's expired gas. We examined 14 VOCs among them further, which could be converted to the concentration from the GC profiles. The concentration of almost VOCs decreased when the subjects inspired purified air compared with the atmosphere. On the other hand, isoprene was almost the same. It was strongly suggested that these VOCs were derived from the human body because the concentration of these VOCs in the atmosphere were nearly zero. Expired gas of two sleep apnea syndrome (SAS) patients were analyzed as preliminary study. As a result of the study, the concentration of some VOCs contained in the expired gas of the SAS patients showed higher value than a healthy controls. © 2013 IEEE. - Yasuyuki Yamauchi; Hiroyuki Kemma; Hiroshi Goto; Atsushi Nakamura; Takashi Nagaoka; Takayuki SotaJAPANESE JOURNAL OF OPHTHALMOLOGY SPRINGER JAPAN KK 56 (6) 577 - 583 0021-5155 2012/10 [Refereed]
To determine the objective and quantitative hyperspectral parameters for distinguishing between age-related macular degeneration (AMD) and a normal macula. Near-infrared hyperspectral images were taken of 71 eyes of 62 AMD patients with exudative AMD and 21 eyes of 12 control subjects without AMD. The spatial information included a 480 x 321-pixel image in a 50A degrees field located at the ocular fundus and a 720-950-nm-per-pixel reflectance spectrum. Macular vectors were determined as the average spectrum for each macula, and reference vectors were used as average macular vectors for healthy volunteers. Variations in vector length and angle were calculated based on comparison with the reference vector. The AMD differentiation index was a parameter that minimized the plot overlap between AMD patients and controls. Statistically significant differences between the AMD patients and controls were noted. Receiver-operating characteristic curve analysis revealed an area under the curve of 0.888. The appropriate threshold values were attained for the proposed discrimination index, including 68 % sensitivity, 95 % specificity and 74 % accuracy. This study presents a simplified diagnostic index for the determination of age-related macular degeneration based on near-infrared spectra. - T. Nagaoka; A. Nakamura; Y. Kiyohara; T. Sota2012 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) IEEE 3728 - 3731 1557-170X 2012/08 [Refereed]
Early detection and proper excision of the primary lesions of melanoma are crucial for reducing melanoma-related deaths. In order to support the early detection of melanoma, melanoma screening systems have been extensively studied and developed. Recently we have proposed a melanoma discrimination index derived from hyperspectral data (HSD) in the visible-near infrared wavelength region. The index represents variegation in spectra over a lesion and works well in discriminating melanoma from other pigmented lesions. However the previous hyperspectral imager did not have an enough allowance for measurement of lesions. To overcome the problem with it, we have developed a hyperspectral imager attached to imaging fiberscope. This equipment has been able to accumulate HSD in a view field of phi 40 mm within about 10 seconds, from which the above-mentioned melanoma discrimination index has been calculated. Performance of the system has been studied in nine cases of melanoma and 18 cases of non-melanoma, obtained from patients and volunteers, all of whom were Japanese. The index has achieved a sensitivity of 100 % and a specificity of 94.4 %. - Takashi Nagaoka; Atsushi Nakamura; Haruka Okutani; Yoshio Kiyohara; Hiroshi Koga; Toshiaki Saida; Takayuki SotaSKIN RESEARCH AND TECHNOLOGY WILEY-BLACKWELL 19 (1) E290 - E296 0909-752X 2012/06 [Refereed]
Background/purpose: Early detection and proper excision of the primary lesions of melanoma are crucial for reducing melanoma-related deaths. To support the early detection of melanoma, automated melanoma-screening systems have been extensively studied and developed. In this article, a previously reported hyperspectral imager and melanoma discrimination index are applied to the discrimination of acral lentiginous melanoma (ALM) from acral nevus (AN), and their diagnostic performance is reported. Methods: The index expresses the disordered nature of each lesion including variegation in color based on variation in spectral information obtained from each lesion. Performance of the index has been studied in thirteen cases of ALM and seven cases of AN, obtained from patients and volunteers, all of whom were Japanese. Results: The index discriminated ALM from AN with a sensitivity of 92% and a specificity of 86%. The area under the receiver operating characteristic curve was 0.97. Conclusion: The performance of the proposed objective melanoma discrimination index at a molecular pigmentary level approached that of clinical experts, using the three-step algorithm as the gold standard. - Takashi Nagaoka; Atsushi Nakamura; Haruka Okutani; Yoshio Kiyohara; Takayuki SotaSKIN RESEARCH AND TECHNOLOGY WILEY-BLACKWELL 18 (3) 301 - 310 0909-752X 2011/08 [Refereed]
Background Early detection and proper excision of the primary lesions of malignant melanoma (MM) are crucial for reducing melanoma-related deaths. To support the early detection of melanoma, automated melanoma screening systems have been extensively studied and developed. In this article, we present a hyperspectral melanoma screening system and propose a possible melanoma discrimination index derived from the characteristics of the pigment molecules in the skin, both of which have been derived from hyperspectral data (HSD). Methods The index expresses the disordered nature of each lesion including variegation in color based on variation in spectral information obtained from each lesion. Performance of the index in discriminating melanomas from other pigmented skin lesions has been studied in five cases of melanoma (41 HSD sets), one case of Spitz nevus (13 HSD sets), 10 cases of seborrheic keratosis (78 HSD sets), three cases of basal cell carcinoma (16 HSD sets), and nine cases of melanocytic nevus (21 HSD sets), obtained from patients and volunteers, all of whom were Japanese. Results Performance of the index, which reflects the disordered nature of a lesion, discriminates melanomas with a sensitivity of 90%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.93, on resubstitution. Conclusion An objective melanoma discrimination index at a molecular pigmentary level, derived from HSD, has been proposed, and its performance evaluated. This index was highly successful in discriminating MM from non-melanoma, although the statistical population was small. - OKUTANI Haruka; NAKAMURA Atsushi; NAGAOKA Takashi; KIYOHARA Yoshio; SOTA TakayukiSkin Cancer The Japanese Skin Cancer Society 26 (1) 94 - 97 0915-3535 2011/01 [Refereed]
The ABCD-rule of dermoscopy has increased diagnostic accuracy ; however, some training is required in using it efficiently, and the diagnosis based on morphology is to a large extent subjective as with any clinical diagnosis. Morphology mainly comes from spatial variegation in skin pigmentation, i.e. spatial change in pigment molecular species and their concentration. Optical spectra reflected from the skin carry information about it. An essential feature of melanoma is the variety in morphology of the lesion, which is equivalent to change in spectrum from portion to portion within the lesion. The hyperspectral imaging technique enables one to measure hyperspectral data (HSD) within a short period, which consist of both spatial and spectral information. In this paper, we propose a single melanoma discrimination index derived from HSD using the entropy concept, and demonstrate its usefulness.[Skin Cancer (Japan) 2011 ; 26 : 94-97] - NAGAOKA Takashi; NAKAMURA Atsushi; AIZAWA Katsuo; OHTSUBO Shinya; KIYOHARA Yoshio; SOTA TakayukiSkin Cancer The Japanese Skin Cancer Society 25 (1) 81 - 84 0915-3535 2010/01 [Refereed]
The morphology of pigmented skin lesions (PSLs) comes from differences in distribution and in concentration of melanin and hemoglobin pigment molecules. Those differences may be analyzed qualitatively and quantitatively using diffuse reflectance spectra in the visible to near infrared wavelength region. We have expressed differences in concentration distribution of both pigment molecules numerically with the use of diffuse reflectance spectra varying from site to site. Performance of the parameter has been studied on fifteen cases of PSLs : six cases of melanoma, five cases of seborrheic keratosis, and four cases of nevus. It has been demonstrated that the parameter can discriminate melanoma from others with a sensitivity of 85% and a specificity of 91%. It has also been suggested that the parameter reflects both boundary irregularity and variation in colors of PSLs.[Skin Cancer (Japan) 2010 ; 25 : 81-84] - Takashi Nagaoka; Atsushi Nakamura; Katsuo Aizawa; Shinya Ohtsubo; Toru Mochizuki; Yoshio Kiyohara; Takayuki Sota2008 30TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-8 IEEE 2008 1234 - + 1557-170X 2008/08 [Refereed]
Using multi spectral imaging technology, which enable us to simultaneously obtain spatial and wavelength information, we have newly developed blood vessel viewer. Our device is composed of the light source, the lens or the endoscope, the optical device, CCD camera, and PC. As an evaluation of our device, we measured the skin diffuse reflectance spectrum of the human hand. The blood vessel observed by our device was corresponding to an anatomy finding. However, even if Principal Component Analysis was used, the reflection of horny was not able to be removed completely. - Nagaoka T; Eikje NS; Nakamura A; Aizawa K; Kiyohara Y; Ichikawa F; Yamazaki T; Doi M; Nakamura K; Otsubo S; Sota TConference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference 2007 3357 - 3361 1557-170X 2007/08 [Refereed]
- Hironori Suzaki; Naoki Kobayashi; Takashi Nagaoka; Kiyotaka Iwasaki; Mitsuo Umezu; Sunao Takeda; Tatsuo Togawa2006 International Conference of the IEEE Engineering in Medicine and Biology Society IEEE 1 799 - 802 0589-1019 2006/08 [Refereed]
Total hemoglobin (tHb), carboxyhemoglobin (COHb), and methemoglobin (MetHb) are usually measured with a CO-oximeter. Noninvasive and continuous measurement of these blood components is expected to decrease the pain of a patient. Therefore, we developed an instrument to measure oxygen saturation (SpO 2), tHb, COHb, and MetHb non-invasively. Multiwavelength LED (600, 625, 660, 760, 800, 940, and 1300 nm) and a combined detector (Si, InGaAs) were built into the instrument (Seven wavelengths transparent pulse spectrophotometer). We used the Waseda mock circulatory system, which can simulate blood circulation in tissues and generate a pulse wave mechanically, to estimate the instrument's performance. Furthermore we proposed new calculation formula including DC components of optical density (this method). Under conditions without any change of other components, the mean error ± standard deviation between this method and the CO-oximetry were SaO 2=0.0±1.4%, tHb=0.0±0.0 g/dl, COHb=0.0±2.0%, and MetHb=0.0±0.3%. When the concentration of other components was changed, this method showed mean errors and standard deviations of SaO 2=0.2±1.6%, tHb=0.0±0.4 g/dl, COHb=0.5±4.1%, and MetHb=0.0±0.3%. © 2006 IEEE. - H. Suzaki; S. Takeda; N. Kobayashi; H. Kubota; T. Aomi; T. Nagaoka; K. Iwasaki; M. Umezu; A. Uchiyama2005 IEEE Engineering in Medicine and Biology 27th Annual Conference IEEE 2005/09 [Refereed]
- T Nagaoka; A Uchiyama2005 3rd IEEE/EMBS Special Topic Conference on Microtechnology in Medicine and Biology IEEE 130 - 131 2005/05 [Refereed]
Medical capsule devices such as video capsule endoscopes are finding increasing use in clinical applications. At present, technologies capable of measuring capsule position and detecting a bleeding in the digestive tract at the same time have not yet been established. The present study aims to develop a small wireless position and bleeding detection sensor. The sensor position are measured by using the phenomenon of mutual induction and Newton's law. Electromotive forces induced in the sensor are modulated to FM signals using an astable multivibrator, and the signals are passed directly through living tissue at low current and then demodulated by detectors on the surface of the body. A prototype sensor was developed and evaluated in vitro. The sensor was capable of accurately measuring capsule position up to 500 (mm) from the primary coils with an accuracy of 5 (mm), and detecting 0.5 cc blood in 500 cc physiological saline. - NAGAOKA Takashi; ICHIKAWA Daisuke; UCHIYAMA AkihikoTransactions of the Japanese Society for Medical and Biological Engineering : BME Japanese Society for Medical and Biological Engineering 42 (4) 300 - 306 1347-443X 2004/08 [Refereed]
In recent years, the number of patients complaining of abnormal bowel movements has increased, and the incidence of abnormal bowel movements in the Japanese population over the age of 15 years old has been estimated to have increased to approximately 20%. Clarification of the intestinal peristalsis of the digestive tract is important for elucidating the pathology of digestive disorders. Existing assessment systems have problems with quantification and reproducibility. With this background, the present study was conducted to develop a system for analyzing intestinal peristalsis using three-dimensional (3D) position sensors. By creating 3D position sensors out of permanent magnets, we were able to directly measure the movements of intestinal contents and assess the state of intestinal peristalsis using strain gauges attached to the intestinal wall. The results of in vitro experiments showed that the maximum measurement error was 6.5mm within 250mm of the sensor. A preliminary animal study was conducted using wired position sensors. Radiographic findings showed that the sensors detected the movement of the intestinal contents, and the movement detected by the sensors correlated with the output of the strain gauges attached to the intestinal wall. - M. Nakai; T. Nagaoka; I. Yoshizawa; A. Fujita; S. Takeda; K. Yanasima; A. UchiyamaAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings 26 III 2055 - 2058 0589-1019 2004/08 [Refereed]
A tonometer is used to measure ocular pressure either by shooting a short blast of compressed air onto the cornea or by applying pressure directly to the cornea. At present, the tonometer is the primary instrument available for measuring ocular pressure. However, measuring ocular pressure by such means can either frighten or injure the patient. We propose an improved method of measuring ocular pressure in which the tonometer is applied over the patient's closed eyelid for several seconds. The sensor part of the newly developed tonometer contains a bimorph type transducer and weighs only 28.7 (g). When the sensor is placed on the eyelid and the transducer is vibrated by altering the applied voltage, the current flowing through the transducer changes in relation to the ocular pressure. Ocular pressure can thus be determined based on the current flowing through the system. During measurement, patients are generally unaware of the vibrations of the sensor and report no pain. - T. Nagaoka; A. UchiyamaAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings 26 III 2137 - 2140 0589-1019 2004/08 [Refereed]
Medical capsule devices such as video capsule endoscopes are finding increasing use in clinical applications. At present, technologies capable of measuring capsule position in the digestive tract have not yet been established. The present study aims to develop a small wireless position sensor capable of measuring capsule position based on the phenomenon of mutual induction. Currents into primary coils are adjusted to maintain electromotive force induced in secondary coils at a constant level. Electromotive forces induced in the secondary coils are modulated to FM signals using an astable multivibrator, and the signals are passed directly through living tissue at low current and then demodulated by detectors on the surface of the body. A prototype wireless sensor was developed and evaluated in vitro. The sensor was capable of accurately measuring capsule position up to 500 (mm) from the primary coils with an accuracy of 5 (mm). Miniaturization of the sensor is necessary for commercialization. - Takashi Nagaoka; Akihiko UchiyamaIEEJ Transactions on Electronics, Information and Systems The Institute of Electrical Engineers of Japan 124 (7) 1352 - 1358 1348-8155 2004/07 [Refereed]
We developed wireless 3-D position sensor. Although we reported a wired position sensor, in order that the wire might affect movement of the sensor, we develop a wireless position sensor newly. For inspection of position measurement algorithm, we first developed a trial product of wireless capsule type sensor without regard to size. The position of the sensor was detected by using mutual induction. In order to maintain the electromotive force induced at secondary coils in the sensor constant, the current flowing into the primary coil was regulated using feedback control. The position of the sensor was measured stably using the feedback control, even when the sensor was relatively far from the primary coil. Induced electromotive forces are modulated to FM signals by using astable multivibrator and the FM signal is flowed into a living body directly with low current, and demodulated from electrode on body surface. The position of the sensor was determined from the current flowing into the primary coil. As a re ult of accuracy evaluation of the sensor in vitro, the error was 2.17±0.99 mm (Ave±S.D.) in a range of up to 1 m from the magnetic field generator. This sensor is applicable to medical capsule devices, such as capsule endoscope. © 2004, The Institute of Electrical Engineers of Japan. All rights reserved. - Nagaoka T; Uchiyama AJournal of Magnetics Society of Japan 公益社団法人日本磁気学会 28;2 (2) 97 - 101 1880-4004 2004/04 [Refereed]
This paper proposes a new sensing method that can measure three-dimensional position inside a living body, using a magnetic field. This method is applicable to medical capsule devices, such as the capsule endoscope. The mutual induction phenomenon is used for position measurement. In order to hold constant the induced electromotive force that occurs in the secondary coil, we apply feedback control to the alternating current flowing into the primary coil. This method enables stable measurement of sensor position, even if the sensor exists relatively far from the primary coils. The position of the sensor is measured by calculating six formulas using Newton's method. The relationship between the induced electromotive force and the theoretical value of the magnetic field is determined in advance. Sensor in vitro accuracy was verified. For distances of less than 300 mm from the sensor to the magnetic field generator, the distance error was less than 7 mm. Although a wireless sensor would be ideal, the present sensor is connected to the computer through a thin cable. Development of wireless sensor should be the next research subject. - T Nagaoka; A UchiyamaIEEE EMBS APBME 2003 IEEE 266 - 267 2003/10 [Refereed]
Video capsule endoscopes are partly applied to clinical use. However, measurement technologies of capsule position in the digestive tract are not established yet. Therefore, the purpose or this study is to develop three-dimensional position sensor which can measure capsule position in the digestive tract. Three coils are arranged perpendicular in the capsule. The sensor generates electromotive force induced by magnetic field generator placed outside of a living body. By measuring induced electromotive force, we can calculate the distance between the sensor and the magnetic field generator. Although wireless is an ideal method for position measurements of capsule endoseope, this sensor is connected to computer through a thin cable because of electric power requirement. - NAGAOKA Takashi; TAKEDA Sunao; UCHIYAMA AkihikoTransactions of the Japanese Society for Medical and Biological Engineering : BME Japanese Society for Medical and Biological Engineering 41 (4) 239 - 249 1347-443X 2003/08 [Refereed]
We developed a three-dimensional position sensor that can measure the position of a capsule in the digestive tract. For the purpose of inspecting a new position measurement algorithm, we first developed a prototype wired capsule-type sensor that is capable of being swallowed. Our ultimate goal will be to develop a wireless sensor. The current sensor is applicable for medical capsule devices, such as capsule endoscope. The position of the sensor was detected using mutual induction. In order to maintain the electromotive force induced at secondary coils in the sensor constant, the current flowing into the primary coil was regulated using feedback control. The position of the sensor was measured stably using the feedback control, even when the sensor was relatively far from the primary coil. The position of the sensor was determined from the current flowing into the primary coil. As a result of evaluating the accuracy of the wired sensor in vitro, the error was 2.90 ± 2.10 mm (Ave.± S. D.) in a range of up to 1m from the magnetic field generator. Moreover, using a new position compensation algorithm, we were able to remove distortion caused by the magnetic field. - Hideo Kawakami; Nobuhiko Sugano; Takashi Nagaoka; Keisuke Hagio; Kazuo Yonenobu; Hideki Yoshikawa; Takahiro Ochi; Asaki Hattori; Naoki SuzukiMedical Image Computing and Computer-Assisted Intervention - MICCAI 2002, 5th International Conference, Tokyo, Japan, September 25-28, 2002, Proceedings, Part II Springer 261 - 267 2002/09 [Refereed]
MISC
- 坪子 侑佑; 木村 雄亮; 長嶋 耕平; 桑名 健太; 土井根 礼音; 前田 祐佳; 黒田 嘉宏; 永岡 隆; 荒船 龍彦 生体医工学 60- (4-5) 126 -129 2022/09
- 桑名 健太; 木村 雄亮; 佐藤 裕一; 坪子 侑佑; 土井根 礼音; 前田 祐佳; 黒田 嘉宏; 永岡 隆; 西川 拓也; 朔 啓太; 荒船 龍彦 生体医工学 59- (6) 185 -187 2021/12
- 辛川 領; 前田 祐佳; 西川 拓也; 木阪 智彦; 坪子 侑佑; 木村 雄亮; 朔 啓太; 塩澤 成弘; 永岡 隆; 黒田 嘉宏; 荒船 龍彦 生体医工学 59- (4-5) 127 -130 2021/09
- H Yamaguchi; M Nemoto; H Kaida; Y Kimura; T Nagaoka; T Yamada; K Hanaoka; K Kitajima; T Tsuchitani; K. Ishii International Journal of Computer Assisted Radiology and Surgery 16- (S1) 110 -111 2021/06 [Refereed]
- 木阪 智彦; 坪子 侑佑; 木村 雄亮; 朔 啓太; 辛川 領; 塩澤 成弘; 永岡 隆; 黒田 嘉宏; 荒船 龍彦 生体医工学 58- (4-5) 188 -191 2020/09
- 荒船,龍彦; 黒田,嘉宏; 永岡,隆; 西川,拓也; 前田,祐佳; 桑名,健太 Transactions of Japanese Society for Medical and Biological Engineering 56- (4) 168 -170 2018
- 動態に基づいたアミロイドイメージング雑音除去アルゴリズムの性能評価山田 誉大; 木村 裕一; 藤井 康介; 渡辺 翔吾; 永岡 隆; 花岡 宏平; 細川 知紗; 石井 一成; 村上 卓道 核医学 54- (Suppl.) S210 -S210 2017/09
- 黒田 嘉宏; 永岡 隆; 塩澤 成弘; 福満 雅史; 荒船 龍彦 Transactions of Japanese Society for Medical and Biological Engineering 55- (4) 366 -366 2017
- 黒田 嘉宏; 荒船 龍彦; 永岡 隆; 大須賀 美恵子 生体医工学 = Transactions of Japanese Society for Medical and Biological Engineering : 日本エム・イー学会誌 54- (4) 194 -196 2016/08
- NAGAOKA TAKASHI 中谷電子計測技術振興財団年報 (24) 92 -103 2010/08
- NAGAOKA TAKASHI; MOCHIZUKI TOORU; SOTA TAKAYUKI; NAKAMURA ATSUSHI 村田学術振興財団年報 (21) 370 -378 2007/12
- NAGAOKA TAKASHI; UCHIYAMA AKIHIKO; TAKEDA SUNAO マツダ財団研究報告書(科学技術振興関係) 19- 39 -42 2007/06
- NAGAOKA TAKASHI; UCHIYAMA AKIHIKO 立石科学技術振興財団助成研究成果集 (15) 52 -55 2006/09
- NAGAOKA TAKASHI 医科学応用研究財団研究報告 23- 72 -77 2006/02
Books and other publications
Lectures, oral presentations, etc.
- (033) IP Improving diagnostic performance of an automated melanoma diagnostic system using fast style transfer data augmentation [Not invited]Takashi Nagaoka; Mitsutaka Nemoto; Yuichi Kimura9th European Medical and Biological Engineering Conference 2024/06
- (099) DO 溶骨性転移を考慮したU-Net 2.5次元処理によるFDG-PET/CT像上骨領域抽出 [Not invited]佐原 詢之佑; 根本 充貴; 甲斐田 勇人; 木村 裕一; 永岡 隆; 三上 勝大; 山田 誉大; 花岡 宏平; 槌谷 達也; 北島 一宏; 石井 一成第63回日本生体医工学会大会 2024/05
- (098) DO 透析中の生体情報を用いた異常検知システムの開発 [Not invited]永岡 隆; 一色 啓二; 根本 充貴; 木村 裕一; 古薗 勉; 瀧 宏文; 政金 生人第63回日本生体医工学会大会 2024/05
- (097) DO 深層学習識別器の効果的な事前学習のためのフラクタル画像を用いたデータ拡張 [Not invited]吉岡雄健; 舩津朋和; 永岡 隆; 小塚健倫; 根本充貴; 山田誉大; 木村裕一; 石井一成; 波部 斉情報処理学会第86回全国大会 2024/03
- (032) IP Unsupervised Lung Lesion Detection on FDG-PET/CT Images by Deep Image Transformation-Based 2.5-Dimensional Local Anomaly Detection [Not invited]A. Segawa; M. Nemoto; H. Kaida and; Y. Kimura; T. Nagaoka; M. Katsuhiro; Y. Takahiro and; H. Kohei; T. Tatsuya; K. Kazuhiro; I. KazunariSPIE Medical Imaging 2023 2024/02
- (066) DP 生成系AIを用いた読影医によるアノテーション不要なFDG-PET/CT像の肺病変強調手法大谷 和暉; 根本 充貴; 甲斐田 勇人; 瀬川 新; 木村 裕一; 永岡 隆; 三上 勝大; 山田 誉大; 花岡 宏平; 槌谷 達也; 北島 一宏; 石井 一成第63回日本核医学会学術総会 2023/11
- (065) DP AIで生成したアミロイド画像におけるスライス間の連続性の評価渡邉 綾; 山田 誉大; 永岡 隆; 根本 充貴; 渡部 浩司; 茨木 正信; 松原 佳亮; 花岡 宏平; 甲斐田 勇人; 石井 一成; 木村 裕一第63回日本核医学会学術総会 2023/11
- (064) DP 教師無し深層画像生成を用いた FDG-PET/CT 像上の肺病変検出 [Not invited]瀬川新; 根本充貴; 甲斐田勇人; 木村裕一; 永岡隆; 三上勝大; 山田誉大; 花岡宏平; 北島一宏; 槌谷達也; 石井一成生体医工学シンポジウム2023 2023/09
- (063) DP スタイル変換による加増がメラノーマ自動診断システムの性能に与える影響 [Not invited]飛塚丈輝; 正木達也; 北畠直人; 花崎和寿; 張維倫; 永岡隆生体医工学シンポジウム2023 2023/09
- (062) DP 自動機械学習を用いたメラノーマ診断システムのパラメータ調整による性能向上 [Not invited]正木達也; 北畠直人; 飛塚丈輝; 花崎和寿; 張 維倫; 永岡 隆生体医工学シンポジウム2023 2023/09
- (061) DP ハイパースペクトルデータからのメラノーマ抽出と自動診断への応用 [Not invited]北畠直人; 飛塚丈輝; 花崎和寿; 正木達也; 張 維倫; 永岡 隆生体医工学シンポジウム2023 2023/09
- (060) DP 縁を付与したメラノーマ画像を用いた深層学習による病変抽出 [Not invited]花崎和寿; 北畠直人; 飛塚丈輝; 正木達也; 張維倫; 永岡隆生体医工学シンポジウム2023 2023/09
- (059) DP 肺マスク層を有する 3D-CNN を用いた COVID-19 診断システムの開発 [Not invited]張 維倫; 北畠 直人; 飛塚 丈輝; 正木 達也; 花崎 和寿; 永岡 隆生体医工学シンポジウム2023 2023/09
- (058) DP Contrastive learning と 2.5 次元画像解析による診断支援システム画像特徴量の生成に関する検討 [Not invited]細田和史; 根本充貴; 木村裕一; 永岡隆; 三上勝大; 吉川健啓生体医工学シンポジウム2023 2023/09
- (031) IP Improving performance of melanoma automated diagnosis system with style transfer [Not invited]Takeki Tobitsuka; Naoto Kitabata; Tatsuya Masaki; Kazutoshi Hanazaki; Wei Lun Chang; Nagaoka Takashi45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2023) 2023/07
- (030) IP Segmentation of pigmented skin lesions considering features of dermoscopic images [Not invited]Kazutoshi Hanazaki; Naoto Kitabata; Takeki Tobitsuka; Tatsuya Masaki; Wei Lun Chang; Takashi Nagaoka45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2023) 2023/07
- (096) DO 生成系 AI を用いた読影医によるアノテーション不要な FDG-PET/CT 像の肺病変強調手法 [Not invited]大谷 和暉; 根本 充貴; 甲斐田 勇人; 瀬川 新; 木村 裕一; 永岡 隆; 三上 勝大; 山田 誉大; 花岡 宏平; 槌谷 達也; 北島 一宏; 石井 一成第5回日本核医学会近畿支部会 2023/07
- (095) DO アミロイド PET 撮像判断のための生成系 AI による FDG 画像からのアミロイド画像合成の検討 [Not invited]本田 実沙; 山田 誉大; 永岡 隆; 三上 勝大; 根本 充貴; 花岡 宏平; 甲斐田 勇人; 石井 一成; 木村 裕一第5回日本核医学会近畿支部会 2023/07
- (094b) DO 診断情報を後ろ向き利用した胸部CT画像上肺結節領域の自動推定~医師によるアノテーションの負荷が少ない胸部画像診断AI開発に向けた一検討~ [Not invited]村中 皓紀; 根本 充貴; 木村 裕一; 永岡 隆; 三上 勝大; 吉川 健啓一般社団法人和歌山県臨床工学技士会第 28 回学術集会 2023/06
- (094a) DO U-netを用いた全身CT像上骨領域抽出~FDG-PET/CT像上多種がん骨転移検出AIに向けた検討~ [Not invited]佐原 詢之佑; 根本 充貴; 甲斐田 勇人; 木村 裕一; 永岡 隆; 三上 勝大; 山田 誉大; 花岡 宏平; 槌谷 達也; 北島 一宏; 石井 一成一般社団法人和歌山県臨床工学技士会第 28 回学術集会 2023/06
- (057) DP 3D-CNN と肺マスク画像を用いた COVID-19 診断システムの開発 [Not invited]張 維倫; 飛塚 丈輝; 正木 達也; 北畠 直人; 花崎 和寿; 永岡 隆第62回日本生体医工学会大会 2023/05
- (056) DP AutoML を用いたメラノーマ診断システムのデータ加増による性能向上 [Not invited]正木 達也; 北畠 直人; 飛塚 丈輝; 花崎 和寿; 張 維倫; 永岡 隆第62回日本生体医工学会大会 2023/05
- (055) DP ハイパースペクトラルデータと 3D u-net を用いたメラノーマ病変部抽出 [Not invited]北畠 直人; 飛塚 丈輝; 正木 達也; 花崎 和寿; 張 維倫; 永岡 隆第62回日本生体医工学会大会 2023/05
- (054) DP スタイル変換における加増パターンの違いに対するメラノーマ自動診断システムの性能変化 [Not invited]飛塚 丈輝; 正木 達也; 北畠 直人; 花崎 和寿; 張 維倫; 永岡 隆第62回日本生体医工学会大会 2023/05
- (053) DP 深層学習を用いたメラノーマの病変部抽出 [Not invited]花崎 和寿; 北畠 直人; 飛塚 丈輝; 正木 達也; 張 維倫; 永岡 隆第62回日本生体医工学会大会 2023/05
- (094) DO Pix2Pix 画像スタイル変換を用いた教師無し異常検知による FDG-PET/CT 像上肺病変強調 [Not invited]大谷 和暉; 根本 充貴; 甲斐田 勇人; 瀬川 新; 中前 由香子; 村中 皓紀; 吉田 昂平; 木村 裕一; 永岡 隆; 三上 勝大; 山田 誉大; 花岡 宏平; 槌谷 達也; 北島 一宏; 石井 一成第62回日本生体医工学会大会 2023/05
- (093) DO U-Net を用いた CT 像上肝臓および腎臓領域の同時抽出~腹部 PET/CT 像上病変検出に向けた検討~ [Not invited]吉田 昂平; 根本 充貴; 甲斐田 勇人; 瀬川 新; 中前 有香子; 村中 晧紀; 大谷 和暉; 木村 裕一; 永岡 隆; 山田 誉大; 花岡 宏平; 槌谷 達也; 北島 一宏; 石井 一成第62回日本生体医工学会大会 2023/05
- (092) DO AI 診断システム開発用病変ラベル作成負荷低減に向けた弱教師とマルチウィンドウ CT 像解析による肺結節領域推定 [Not invited]村中 皓紀; 根本 充貴; 木村 裕一; 永岡 隆; 細田 和史; 中前 有香子; 大谷 和暉; 吉田 昂平; 吉川 健啓第62回日本生体医工学会大会 2023/05
- (057b) DP U-Netを用いたCT像上肝臓および腎臓領域の同時抽出~腹部PET/CT像上病変検出に向けた検討~吉田昂平; 根本充貴; 甲斐田勇人; 瀬川新; 中前有香子; 村中皓紀; 大谷和暉; 木村裕一; 永岡隆; 山田誉大; 花岡宏平; 槌谷達也; 北島一宏; 石井一成第62回日本生体医工学会大会 2023/05
- (057a) DP Pix2Pix画像スタイル変換を用いた教師無し異常検知による FDG-PET/CT像上肺病変強調大谷和暉; 根本充貴; 甲斐田勇人; 瀬川新; 中前有香子; 村中皓紀; 吉田昂平; 木村裕一; 永岡隆; 山田誉大; 花岡宏平; 槌谷達也; 北島一宏; 石井一成第62回日本生体医工学会大会 2023/05
- (091)DO 3D-CNNを用いたCOVID-19診断システムの開発 [Not invited]張 維倫; 飛塚丈輝; 正木達也; 北畠直人; 花崎和寿; 永岡 隆メディカルイメージング連合フォーラム 2023/03
- (090)DO Auto MLを用いたメラノーマ診断システムの性能向上 [Not invited]正木達也; 北畠直人; 飛塚丈輝; 花崎和寿; 張 維倫; 永岡 隆メディカルイメージング連合フォーラム 2023/03
- (089)DO スタイル変換によるメラノーマ自動診断システムの性能向上 [Not invited]飛塚丈輝; 正木達也; 北畠直人; 花崎和寿; 張 維倫; 永岡 隆メディカルイメージング連合フォーラム 2023/03
- (088)DO ハイパースペクトラルデータとDeeplabv3+を用いたメラノーマ病変部抽出 [Not invited]北畠直人; 飛塚丈輝; 正木達也; 花崎和寿; 張 維倫; 永岡 隆メディカルイメージング連合フォーラム 2023/03
- (087)DO ダーモスコピーの縁を考慮に入れたメラノーマの病変抽出 [Not invited]花崎和寿; 北畠直人; 飛塚丈輝; 正木達也; 張 維倫; 永岡 隆メディカルイメージング連合フォーラム 2023/03
- (086)DO pix2pixを用いたメラノーマの病変領域抽出 [Not invited]永岡 隆; 根本充貴; 三上勝大; 篠原寿広; 木村裕一メディカルイメージング連合フォーラム 2023/03
- (085b) DO フラクタルデータベースを用いた胸部CT画像の肺炎識別器の事前学習 [Not invited]吉岡雄健; 舩津朋和; 永岡隆; 小塚健倫; 根本充貴; 山田誉大; 木村裕一; 石井一成; 波部斉情報処理学会第85回全国大会 2023/03
- (029d) IP Pre-training of Pneumonia Classifier for Chest CT images using Fractal DatabaseYuken Yoshioka; Daichi Ikefuji; Tomokazu Funatsu; Takashi Nagaoka; Takenori Kozuka; Mitsutaka Nemoto; Takahiro Yamada; Yuichi Kimura; Kazunari Ishii; Hitoshi HabeThe 29th International Workshop on Frontiers of Computer Vision (IW-FCV2023) Online Proceeding 2023/02
- (029c) IP Detection of Bone Metastasis on FDG-PET/CT Images using Multi-step Anomaly Voxel Detection and Local Patch analysis with Unsupervised Deep Features and Image TexturesYamaguchi H; Nemoto M; Kaida H; Kimura Y; Nagaoka T; Yamada T; Hanaoka K; Kitajima K; Tsuchitani T; Ishii K13th World Federation of Nuclear Medicine and Biology 2022/09
- (029b) IP Study for detecting pulmonary nodules on FDG-PET/CT images with training small datasetSegawa A; Nemoto M; Kaida H; Kimura Y; Nagaoka T; Yamaguchi H; Nakamae Y; Yamada T; Hanaoka K; Kitajima K; Tsuchitani T; Ishii K13th World Federation of Nuclear Medicine and Biology 2022/09
- (029a) IP Evaluation on Applicability of Generative Adversarial Network to Synthesize Training Images for AI-Based Computer Aided Diagnostic Algorithm to DementiaWatanabe A; Yamada T; Nagaoka T; Nemoto M; Watabe H; Ibaraki M; Matsubara K; Hanaoka K; Ishii K; Kimura Y13th World Federation of Nuclear Medicine and Biology 2022/09
- (029)IP Robustness of a U-net model for different image processing types in segmentation of the mammary gland regionMika Yamamuro; Yoshiyuki Asai; Naomi Hashimoto; Nao Yasuda; Hiroto Kimura; Takahiro Yamada; Mitsutaka Nemoto; Yuichi Kimura; Hisashi Handa; Hisashi Yoshida; Koji Abe; Masahiro Tada; Hitoshi Habe; Takashi Nagaoka; Seiun Nin; Kazunari Ishii; Yongbum Lee16th International Workshop on Breast Imaging (IWBI2022) 2022/07 SPIE
- (049)DP スタイル変換を用いた加増によるメラノーマ自動診断システムの性能向上 [Not invited]飛塚丈輝; 正木達也; 花崎和寿; 北畠直人; 永岡 隆第61回日本生体医工学会大会 2022/06
- (048)DP 深層学習を用いたメラノーマ診断システムのデータ加増による性能向上 [Not invited]正木達也; 飛塚丈輝; 花崎和寿; 北畠直人; 永岡 隆第61回日本生体医工学会大会 2022/06
- (047)DP 線形判別分析を用いたメラノーマの領域抽出とその診断性能への影響 [Not invited]北畠直人; 正木達也; 飛塚丈輝; 花崎和寿; 永岡 隆第61回日本生体医工学会大会 2022/06
- (046)DP メラノーマの病変部抽出花崎和寿; 飛塚丈輝; 正木達也; 北畠直人; 永岡 隆第61回日本生体医工学会大会 2022/06
- (050)DP 深層画像生成技術を用いたFDG-PET/CT像異常検知による病変強調瀬川新; 根本充貴; 甲斐田勇人; 甲斐田勇人; 山口明乃; 木村裕一; 永岡隆; 山田誉大; 北島一宏; 石井一成; 石井一成日本生体医工学会大会プログラム・抄録集(Web) 2022/06
- (051)DP CT画像テクスチャと患者情報のAI解析による体外衝撃波結石破砕術の結果予測中前有香子; 根本充貴; 木村裕一; 木村裕一; 永岡隆; 永岡隆; 出口龍良; 山下真平; 柑本康夫; 原勲日本生体医工学会大会プログラム・抄録集(Web) 2022/06
- (052)DP 画素異常検知と深層教師なし特徴抽出によるFDG-PET/CT像上がん骨転移検出山口明乃; 根本充貴; 甲斐田勇人; 甲斐田勇人; 木村裕一; 永岡隆; 山田誉大; 花岡宏平; 北島一宏; 槌谷達也; 石井一成; 石井一成日本生体医工学会大会プログラム・抄録集(Web) 2022/06
- (085a) 学習時の注目領域重視度の動的調整による画像分類精度の改善 [Not invited]舩津朋和; 波部 斉; 永岡 隆; 小塚健倫; 根本充貴; 山田誉大; 吉田 久; 木村裕一; 石井一成情報処理学会第84回全国大会 2022/03
- (084)DO 2種類の異常検知を用いたFDG-PET/CT像上のがん骨転移病変自動検出山口明乃; 根本充貴; 甲斐田勇人; 甲斐田勇人; 木村裕一; 永岡隆; 山田誉大; 花岡宏平; 北島一宏; 槌谷達也; 石井一成; 石井一成核医学(Web) 2021/11
- (085)DO 敵対的生成ネットワークで合成したPET画像における定量性の検討渡邉綾; 木村裕一; 山田誉大; 渡辺翔吾; 永岡隆; 根本充貴; 宮崎晃一; 花岡宏平; 甲斐田勇人; 甲斐田勇人; 石井一成; 石井一成核医学(Web) 2021/11
- (028)IP [CAR-PO-23] 001 Can radiological technologists create training data for automatically segmenting the mammary gland region in non-dense breasts? [Not invited]M. Yamamuro; Y. Asai; N. Hashimoto; N. Yasuda; Y. Ozaki; S. Nin; K. Ishii; T. Yamada; M. Nemoto; Y. Kimura; H. Handa; H. Yoshida; K. Abe; M. Tada; H. Habe; T. Nagaoka; Y. LeeCARS2021 2021/06
- (027)IP [CAD-PO-61] 033 Detection of bone metastases on FDG-PET/CT images by using two-step anomaly detection [Not invited]H. Yamaguchi; M. Nemoto; H. Kaida; Y. Kimura; T. Nagaoka; T. Yamada; K. Hanaoka; K. Kitajima; T. Tsuchitani; K. IshiiCARS2021 2021/06
- (083)DO O1-5-3-5 CT 画像によるCOVID-19 性肺炎診断支援システムKindAI-COVID の開発 [Not invited]永岡 隆; 小塚 健倫; 根本 充貴; 波部 斉; 山田 誉大; 吉田 久; 木村 裕一; 石井 一成第60回日本生体医工学会大会 2021/06
- (082)DO O1-5-4-4 2 種類のAI 異常検知カスケードを用いたFDG-PET/CT 像上がん骨転移検出 [Not invited]山口 明乃; 根本 充貴; 甲斐田 勇人; 木村 裕一; 永岡 隆; 山田 誉大; 花岡宏平; 北島 一宏; 槌谷 達也; 石井 一成第60回日本生体医工学会大会 2021/06
- (081)DO O1-5-3-3 CT 画像上のテクスチャ解析によるESWL 治療可能な尿路結石の自動認識 [Not invited]中前 有香子; 根本 充貴; 木村 裕一; 永岡 隆; 山田 誉大; 出口 龍良; 山下真平; 柑本 康夫; 原 勲第60回日本生体医工学会大会 2021/06
- (080)DO O1-5-2-4 認知症診断AI アルゴリズム学習のためのCycleGAN で合成したPET 画像の定量的検証 [Not invited]渡邉 綾; 山田 誉大; 渡辺 翔吾; 永岡 隆; 根本 充貴; 宮崎 晃一; 花岡 宏平; 甲斐田 勇人; 石井 一成; 木村 裕一第60回日本生体医工学会大会 2021/06
- (079)DO 深層学習によるメラノーマの自動診断 ~ HSDの主成分分析による次元縮約 ~ [Not invited]金澤祐斗; 永岡 隆; 木村裕一; 根本充貴メディカルイメージング連合フォーラム 2021/03
- (26b) IP How to select training data to segment mammary gland region using a deep-learning approach for reliable individualized screening mammography [Not invited]Mika Yamamuro; Yoshiyuki Asai; Naomi Hashimoto; Nao Yasuda; Takahiro Yamada; Mitsutaka Nemoto; Yuichi Kimura; Hisashi Handa; Hisashi Yoshida; Koji Abe; Masahiro Tada; Hitoshi Habe; Takashi Nagaoka; Yoshiaki Ozaki; Seiun Nin; Kazunari Ishii; Yongbum LeeMedical Imaging 2021: Computer-Aided Diagnosis 2021/02 SPIE
- (078)DO One-class SVMを用いた異常検知によるPET/CT上の骨転移病変自動検出 [Not invited]田中 敦子; 根本 充貴; 甲斐田 勇人; 木村 裕一; 永岡 隆; 牛房 和之; 山田 誉大; 花岡 宏平; 北島 一宏; 槌谷 達也; 石井 一成第60回日本核医学学術総会 2020/11
- (077)DO 認知症自動診断AIアルゴリズム学習のための深層学習により加増したアミロイド画像の検証渡邉 綾; 木村 裕一; 山田 誉大; 渡辺 翔吾; 永岡 隆; 根本 充貴; 宮崎 晃一; 花岡 宏平; 甲斐田 勇人; 石井 一成第60回日本核医学学術総会 2020/11
- (076)DO 深層学習を用いたメラノーマの自動診断システムの開発 ~ 病変部位強調画像の採用 ~ [Not invited]平野銀次; 根本充貴; 木村裕一; 永岡 隆電子情報通信学会医用画像研究会 2020/11
- One-class SVMによる画素悪性度の集中性を用いたFDG-PET/CT上の病変自動検出田中 敦子; 根本 充貴; 甲斐田 勇人; 木村 裕一; 永岡 隆; 牛房 和之; 山田 誉大; 花岡 宏平; 北島 一宏; 槌谷 達也; 石井 一成日本医用画像工学会大会予稿集 2020/09 日本医用画像工学会
- (045)DP P2-11少数症例を用いた教師無し深層学習による病変検出画像特徴量の汎用的生成-胸部 CT を用いた実験的検証- [Not invited]牛房和之; 根本充貴; 木村裕一; 永岡隆; 山田誉大; 田中敦子; 林直人第39回日本医用画像工学会大会, 山形(オンライン開催) 2020/09
- (044)DP P1-17One-class SVM による画素悪性度の集中性を用いた FDG-PET/CT 上の病変自動検出 [Not invited]田中 敦子; 根本 充貴; 甲斐田 勇人; 木村 裕一; 永岡 隆; 牛房 和之; 山田 誉大; 花岡 宏平; 北島 一宏; 槌谷 達也; 石井 一成第39回日本医用画像工学会大会, 山形(オンライン開催) 2020/09
- (26a)IP Automatic detection of cervical and thoracic lesions on FDG-PET/CT by organ specific one-class SVMs [Not invited]A. Tanaka; M. Nemoto; H. Kaida; Y. Kimura; T. Nagaoka; T. Yamada; K. Ushifusa; K. Hanaoka; K. Kitajima; T. Tsuchitani; K. IshiiInternational Journal of Computer Assisted Radiology and Surgery 2020/06 Springer Science and Business Media LLC
- (043)DP PO-1-033主成分分析を用いたHSDの次元縮約 [Not invited]金澤 祐斗; 永岡 隆第59回日本生体医工学会大会, 岡山(オンライン開催) 2020/05
- (042)DP PO-1-032ハイパースペクトラルデータを用いたメラノーマの自動診断支援システムの開発 [Not invited]平野 銀次; 根本 充貴; 木村 裕一; 永岡 隆第59回日本生体医工学会大会, 岡山(オンライン開催) 2020/05
- (041)DP PO-1-031メラノーマ診断に適した画像特徴量の追加検討 [Not invited]田村 侑大; 根本 充貴; 木村 裕一; 永岡 隆第59回日本生体医工学会大会, 岡山(オンライン開催) 2020/05
- (039)DP メラノーマ自動診断支援システムの開発における単一波長画像作成方法の検討 [Not invited]加藤日菜; 永岡 隆メディカルイメージング連合フォーラム2019 2020/01
- (075)DO 正常データセットの教師なし学習に基づく病変検出支援システム画像特徴量の汎用的生成に関する検討 ~ 少規模なデータセットを用いた特徴量生成の実験的検証 ~ [Not invited]牛房和之; 根本充貴; 木村裕一; 永岡 隆; 山田誉大; 田中敦子; 林 直人メディカルイメージング連合フォーラム2019 2020/01
- (074)DO One-class SVMを用いた病変強調によるFDG-PET/CT上の頸胸部病変の自動検出 [Not invited]田中敦子; 根本充貴; 甲斐田勇人; 木村裕一; 永岡 隆; 山田誉大; 牛房和之; 花岡宏平; 北島一宏; 槌谷達也メディカルイメージング連合フォーラム2019 2020/01
- (040)DP メラノーマ診断に適した画像特徴量の検討 [Not invited]田村侑大; 永岡 隆メディカルイメージング連合フォーラム2019 2020/01
- (038)DP 認知症自動診断AIアルゴリズム学習のための深層学習によるアミロイド画像の加増手法の検討渡邉 綾; 山田 誉大; 永岡 隆; 根本 充貴; 花岡 宏平; 甲斐田 勇人; 石井 一成; 木村 裕一第59回日本核医学会学術総会 2019/11
- (035)DP Automatic Diagnosis of Melanoma Using Hyperspectral Data and GoogLeNetGinji Hirano; Mitsutaka Nemoto; Yuichi Kimura; Yoshio Kiyohara; Hiroshi Koga; Naoya Yamazaki; Gustav Christensen; Atsushi Nakamura; Takayuki Sota; Takashi Nagaoka生体医工学シンポジウム2019 2019/09
- (036)DP Performance Improvement of Automated Melanoma Diagnosis System by Data AugmentationKana Kato; Mitsutaka Nemoto; Yuichi Kimura; Yoshio Kiyohara; Hiroshi Koga; Naoya Yamazaki; Gustav Christensen; Atsushi Nakamura; Takayuki Sota; Takashi Nagaoka生体医工学シンポジウム2019 2019/09
- (037)DP Weighting Function for Kinetics-Based Noise Reduction in PET Amyloid ImagingTakahiro Yamada; Shogo Watanabe; Takashi Nagaoka; Mitsutaka Nemoto; Kohei Hanaoka; Hayato Kaida; Kazunari Ishii; Yuichi Kimura生体医工学シンポジウム2019 2019/09
- (034)DP 病変検出支援アルゴリズムにおける局所画像特徴量の汎用的な自動生成 -健常データのみの学習による特徴量生成の検討- [Not invited]牛房 和之; 根本 充貴; 木村 裕一; 永岡 隆; 山田誉大; 林 直人第38回日本医用画像工学会大会 2019/07
- (073)DO ハイパースペクトラルデータを用いたメラノーマの自動診断支援システムの開発 ~ 深層学習の導入 ~ [Not invited]平野銀次; 永岡 隆電子情報通信学会医用画像研究会 2019/07
- (026)IP Automated Diagnosis of Melanoma using Three Wavelengths [Not invited]Yudai Tamura; Takashi Nagaoka41st International Engineering in Medicine and Biology Conference 2019/07
- (025)IP Automated Melanoma Diagnosis using Transfer Learning [Not invited]Kana Kato; Takashi Nagaoka41st International Engineering in Medicine and Biology Conference 2019/07
- (024)IP Automatic Diagnosis of Melanoma using Machine Learning [Not invited]Hirano Ginji; Nagaoka Takashi41st International Engineering in Medicine and Biology Conference 2019/07
- (023)IP AI-Based Melanoma Diagnosis Support System Using a Hyperspectral Imaging Technique [Not invited]Takashi Nagaoka41st International Engineering in Medicine and Biology Conference 2019/07
- (022)IP Custering-based data reduction algorithm with simplified reference tissue modelto generate parametric images in amyloid imagingT.Yamada; Y. Kimura; M. Sakata; T. Nagaoka; M. Nemoto; K. Hanaoka; H. Kaida; K. Ishii2019/07
- (032)DP FDG‐PET/CTの統計的異常検知処理による転移を考慮した頸胸部病変の自動検出 [Not invited]田中敦子; 根本充貴; 甲斐田勇人; 木村裕一; 永岡隆; 山田誉大; 花岡宏平; 石井一成日本生体医工学会大会プログラム・抄録集(Web) 2019/06
- (033)DP 深層畳み込みオートエンコーダを用いた健常データの教師なし学習による病変認識特徴量の汎用的自動生成 [Not invited]牛房和之; 根本充貴; 木村裕一; 永岡隆; 山田誉大; 林直人日本生体医工学会大会プログラム・抄録集(Web) 2019/06
- (072)DO 皮膚のスペクトル解析とその応用 [Not invited]永岡隆日本生体医工学会大会プログラム・抄録集(Web) 2019/06
- (071)DO メラノーマ診断支援装置ハイパースペクトル・イメージャー(HSI)の性能 白人色素性病変の診断能力 [Not invited]永岡 隆; グスタフクリステンセン; クリスチャンインバー; 清原 祥夫; 中村 厚; 宗田 孝之日本皮膚悪性腫瘍学会学術大会プログラム・抄録集 2019/05
- (031)DP HSDを用いたメラノーマの自動診断支援システムの開発 ~ Adaptive boostingによる鑑別 ~ [Not invited]平野銀次; 永岡 隆メディカルイメージング連合フォーラム 2019/01
- (070)DO 空間分解能を温存したノイズ低減アルゴリズムを用いたアミロイドイメージング動態撮像の短時間化 [Not invited]山田 誉大; 木村 裕一; 北西 巧; 永岡 隆; 根本 充貴; 花岡 宏平; 甲斐田 勇人; 石井 一成第8回核医学画像解析研究会, 秋田 2018/12
- (069)DO SRTM法を用いたアミロイドイメージングに対する空間分解能を損なわないノイズ低減アルゴリズムの検討 [Not invited]山田 誉大; 木村 裕一; 根本 充貴; 坂田 宗之; 永岡 隆; 花岡 宏平; 甲斐田 勇人; 石井 一成核医学 2018/11
- (067)DO メラノーマ診断支援装置ハイパースペクトル・イメージャ(HSI)の性能 [Not invited]中村 厚; 清原 祥夫; 古賀 弘志; 高橋 聡; 永岡 隆; 山崎 直也; 斎田 俊明; 宗田 孝之日本皮膚悪性腫瘍学会学術大会プログラム・抄録集 2018/07
- (068)DO ハイパースペクトルデータ(HSD)に基づく悪性黒色腫の腫瘍境界部の観察 [Not invited]清原 祥夫; 野口 遼介; 中村 厚; 永岡 隆; 吉川 周佐; 大塚 正樹; 杉原 悟; 宗田 孝之日本皮膚悪性腫瘍学会学術大会プログラム・抄録集 2018/07
- (021)IP Automatic diagnosis of melanoma using machine learning [Not invited]G. Hirano; T. NagaokaWorld Congress on Medical Physics and Biomedical Engineering 2018/06
- 山田誉大; 木村裕一; 藤井康介; 渡辺翔吾; 永岡隆; 根本充貴; 花岡宏平; 甲斐田勇人; 石井一成; 石井一成日本生体医工学会大会プログラム・抄録集(Web) 2018/06
- (020)IP Noise Reduction Algorithm for Amyloid Imaging to Preserve the Contrast Between Gray and White Matters Using Simplified Reference Tissue ModelT Yamada; Y Kimura; K Fujii; S Watanabe; T Nagaoka; M Nemoto; K Hanaoka; C Hosokawa; K IshiiWorld Congress of the World Federation of Nuclear Medicine and Biology 2018/04
- (029)DP HSDを用いたメラノーマの自動診断支援システムの開発 ~ 機械学習による鑑別 ~ [Not invited]竹村香音; 平野銀次; 永岡 隆メディカルイメージング連合フォーラム 2018/03
- (019)IP Noise Reduction Algorithm for Amyloid Image Preserving Image Resolution. - Quantitative Evaluation Using Clinical Images - [Not invited]T.Yamada; Y.Kimura; K.Fuji; S.Watanabe; T.Nagaoka; M.Nemoto; K.Hanaoka; H.Kaida; C.Hosokawa; K.IshiiHuman Amyloid Imaging Conference 2018/01
- (066)DO 動態に基づいたアミロイドイメージング雑音除去アルゴリズムの性能評価 [Not invited]山田 誉大; 木村 裕一; 藤井 康介; 渡辺 翔吾; 永岡 隆; 花岡 宏平; 細川 知紗; 石井 一成; 村上 卓道第57回日本核医学会学術総会 2017/10
- (028)DP ハイパースペクトラルイメージャーを用いた化粧品の定量評価に関する基礎研究 [Not invited]永岡隆; 麻生祐未; 横山真由; 河本敬子Aesthetic Dermatology 2017/07
- (065)DO PETアミロイドイメージングによる参照領域自動設定アルゴリズムの開発 - 時間情報及びクラスタ数の再検討 - [Not invited]山田 誉大; 木村 裕一; 永岡 隆; 花岡 宏平; 細川 知紗; 石井 一成第56回日本生体医工学会大会 2017/05
- (064)DO サマースクールの目指すもの [Not invited]永岡 隆第56回日本生体医工学会大会 2017/05
- Yamada Takahiro; Kimura Yuichi; Nagaoka Takashi; Hanaoka Kohei; Hosokawa Chisa; Ishii KazunariTransactions of Japanese Society for Medical and Biological Engineering 2017 Japanese Society for Medical and Biological Engineering
In Alzheimer's disease (AD) amyloid-β (Aβ) depositions disturbs neurons irreversibly, and early treatment before occurrence of dementia is important for AD treatments. This study aims at proposing an automated delineation algorithm for reference regions (AutoRef) for Aβ accumulation quantification. This presentation focuses on merits of a limited temporal information and the increased number clusters. As a result, for 86 clinical data (43 cases of AD, 33 cases of normal and 10 cases of equivocal deposition of Aβ), AutoRef succeeded in delineating the reference region for all the data. There was no significant difference (p < 0.05) between AutoRef and manually delineated reference region by a physician. The standard deviation of the difference between them was smaller than the discrimination threshold of AD used in actual clinical practice. In conclusions, the effectiveness of this study was suggested.
- (018)IP Algorithm for reference region delineation for amyloid imaging using pattern recognition scheme and kinetics of administered Aβ probe ― considering the number of clusters ― [Not invited]T. Yamada; Y. Kimura; T. Nagaoka; C. Hosokawa; T. Murakami; K. IshiiHuman Amyloid Imaging Conference 2017/01
- (017)IP Investigation of Potential Usability of Machine Learning to Diagnosis of Parkinson Disease Using SPECT DaTSCAN [Not invited]S. Watanabe; T. Nagaoka; Y. KimuraInternational Forum on Medical Imaging in Asia (IFMIA2017) 2017/01
- (016)IP Performance Evaluation of Kinetics-Based Denoising Algorithm for PET Amyloid Imaging [Not invited]K. Fuji; T. Yamada; T. Nagaoka; Y. KimuraInternational Forum on Medical Imaging in Asia (IFMIA2017) 2017/01
- (026)DP 化粧品のもちの定量評価―ファンデーションの時間変化― [Not invited]藤本茜; 永岡隆電子情報通信学会技術研究報告 2017/01
- (025)DP メラノーマの診断支援システムの開発―病変部の面積が及ぼす影響― [Not invited]平野銀次; 永岡隆電子情報通信学会技術研究報告 2017/01
- (027)DP 化粧品の主観評価とスペクトルの相関 [Not invited]舩倉美咲; 永岡隆電子情報通信学会技術研究報告 2017/01
- (024)DP 陽電子断層画像・アミロイドイメージングによるアルツハイマー病早期診断のためのデータ処理法 [Not invited]木村 裕一; 山田 誉大; 永岡 隆第17回計測自動制御学会 システムインテグレーション部門講演会(SI2016) 2016/12
- (023)DP 臨床データを用いたPETアミロイドイメージングにおける 参照領域自動設定法の性能評価 [Not invited]山田 誉大; 木村 裕一; 永岡 隆; 岡田 志麻; 細川 知紗; 石井 一成生体医工学シンポジウム2016 2016/09
- (022)DP PETアミロイドメージングにおけるトレーサの動態に基づいたノイズ除去アルゴリズムの可用性検討 [Not invited]藤井康介; 木村裕一; 山田誉大; 坂田宗之; 永岡 隆; 細川知紗; 石井一成生体医工学シンポジウム2016 2016/09
- (015)IP Hyperspectroscopic Evaluation correlated to the Subjective Evaluation for Cosmetics [Not invited]NAGAOKA Takashi38th Annual International Conference of the IEEE EMBS 2016/08
- (003)IO Deliniation Algorithm on Reference Region for Amyloid Imaging Using a Time History of Radioactivity [Not invited]Y. Kimura; T. Yamada; C. Hosokawa; S. Okada; T. Nagaoka; K. IshiiSNMMI 20016 Annual Meeting, San Diego, USA 2016/06
- (062)DO メラノーマ診断支援装置ハイパースペクトル・イメージャーの性能~掌蹠の色素性病変~:第五報 [Not invited]朴木達也; 高橋聡; 古賀弘志; 清原祥夫; 片桐孝太; 中村厚; 永岡隆; 山崎直也; 斎田俊明; 宗田孝之日本皮膚悪性腫瘍学会学術大会プログラム・抄録集 2016/05
- (063)DO メラノーマ診断支援装置ハイパースペクトル・イメージャーの性能~腫瘍厚の推定~:第六報 [Not invited]清原祥夫; 永岡隆; 中村厚; 古賀弘志; 斎田俊明; 宗田孝之日本皮膚悪性腫瘍学会学術大会プログラム・抄録集 2016/05
- (021)DP 肺癌患者における呼気ガス中揮発性有機化合物測定の有用性の検討 [Not invited]小熊剛; 永岡隆; 小林尚史; 倉橋宗重; 滝口寛人; 友松克允; 友松裕美; 新美京子; 端山直樹; 青木琢也; 浦野哲哉; 阿部直; 浅野浩一郎日本呼吸器学会誌 2016/04
- (061)DO Application of hyperspectral imaging in medicine [Not invited]永岡 隆生体医用画像研究会第3回若手発表会 2016/03
- Yamada Takahiro; Kimura Yuichi; Nagaoka Takashi; Okada Shima; Hosokawa Chisa; Ishii KazunariTransactions of Japanese Society for Medical and Biological Engineering 2016 Japanese Society for Medical and Biological Engineering
A deposit of amyloid β (Aβ) to the central nervous system causes Alzheimer's disease (AD). A periodical evaluation on Aβ, a year, can therefor detect the beginning of AD, and it realizes an effective medical treatment for AD. For quantitative measurement of Aβ deposit is available using PET, and it requires to delineate the cerebellum gray matter as a reference region, when no Aβ deposit occurs physiologically and it has complicated shape. This study aim at proposing automated delineation algorithm based on a kinetics of administered PET tracer for Aβ imaging. The validation using a clinical data presented no significant difference (p < 0.05) between the amount of Aβ deposit using an ordinary manual delineation and the automated method. We can conclude that the algorithm is clinically useful.
- 山田誉大; 木村裕一; 永岡隆; 岡田志麻; 細川知紗; 石井一成電子情報通信学会技術研究報告 2016/01
- (002)D講演 ハイパースペクトラルイメージャーを用いたメラノーマ診断支援システムの開発 [Invited]永岡 隆レーザー学会学術講演会第36回年次大会 2016/01
- 山田誉大; 木村裕一; 永岡隆; 岡田志麻; 細川知紗; 石井一成電子情報通信学会技術研究報告 2015/11
- (059)DO アミロイドイメージングにおける組織放射能時間曲線に対するパターン認識による参照領域設定アルゴリズム [Not invited]木村裕一; 山田誉大; 永岡 隆; 細川知紗; 石井一成; 村上卓道第55回日本核医学会学術総会 2015/11
- (020)DP PETアミロイドイメージングにおける参照領域自動設定アルゴリズムの開発 [Not invited]山田 誉大; 木村 裕一; 永岡 隆; 岡田 志麻; 細川 知紗; 石井 一成日本生体医工学会シンポジウム2015 2015/09
- (014)IP Fiber-type hyperspectral melanoma screening system [Not invited]Nagaoka T; Nakamura A; Kiyohara Y; Sota T37th annual international conference of the IEEE Engineering in Medicine and Biology Society 2015/08
- (001)D講演 宇宙からの目で皮膚を診る [Invited]永岡 隆第7回バイオメクフォーラム21, 大阪大学 2015/07
- (057)DO メラノーマ診断支援装置ハイパースペクトラル・イメージャーの性能:第四報 [Not invited]片桐孝太; 永岡 隆; 中村 厚; Gustav Christensen; Christian Ingvar; 古賀弘志; 清原祥夫; 斎田俊明; 宗田孝之第31回日本皮膚悪性腫瘍学会学術大会 2015/07
- (056)DO ハイパースペクトルイメージャを用いたメラノーマの自動診断−第5報− [Not invited]永岡 隆; 中村 厚; 清原祥夫; 宗田孝之第15回計測自動制御学会 システムインテグレーション部門講演会(SI2014) 2014/12
- (018)DP 経日に伴う潜在指紋成分の蛍光強度の増減 [Not invited]HIBINO KAZUTO; NAKAMURA ATSUSHI; NAGAOKA TAKASHI; TAKEUCHI SHIGEKI; SHIMODA OSAMU; TAKATSU MASAHISA; AKIBA NORIMITSU; KUROSAWA KENJI; KUROKI KENRO; SOTA TAKAYUKI日本法科学技術学会誌 2014/10
- (019)DP 近赤外カメラによる潜在指掌紋の顕在化~冷媒HFC152aによる前処理の効果~ [Not invited]NAKATSUKASA TAKUYA; SHIMODA OSAMU; SAWADA YUJI; KIMURA KOJI; KAMITA TOMOKAZU; MIURA YOSHIMASA; OGUSHI MASANORI; SAKATA MASAMICHI; TAKATSU MASAHISA; TAKEUCHI SHIGEKI; HIBINO KAZUTO; AKIBA NORIMITSU; KUROSAWA KENJI; KUROKI KENRO; NAKAMURA ATSUSHI; NAGAOKA TAKASHI; SOTA TAKAYUKI日本法科学技術学会誌 2014/10
- (013)IP Possible spectral separation of overlapped fingerprints [Not invited]Takashi Nagaoka; Atsushi Nakamura; Hidekazu Okuda; Norimitsu Akiba; Kenro Kuroki; Kenji Kurosawa; Fumihiko Ichikawa; Akira Torao; Takayuki Sota22nd International Symposium on the Forensic Sciences of the Australian and New Zealand Forensic Science Society 2014/09
- (054)DO ヒト呼気に含まれる揮発性有機化合物測定システムを用いた日内変動の測定 [Not invited]KANO SAKI; NAGAOKA TAKASHI; KOBAYASHI NAOFUMI; KURAHASHI MUNESHIGE; TAKEDA SUNAO; AOKI TAKUYA; TSUJI CHIZUKO; URANO TETSUYA; ABE TADASHI; MAGATANI KAZUSHIGE日本生体医工学会大会プログラム・論文集(CD-ROM) 2014/06
- (055)DO メラノーマ診断支援装置ハイパースペクトラル・イメージャーの性能:第三報 [Not invited]AOKI TOSHIYUKI; AKIYAMA SAORI; NAGAOKA TAKASHI; NAKAMURA ATSUSHI; KOGA HIROSHI; KIYOHARA YOSHIO; SAIDA TOSHIAKI; SOTA TAKAYUKI日本皮膚悪性腫瘍学会学術大会プログラム・抄録集 2014/06
- 3A1-E04 Basic research towards development of an expiration gas analysis system(Medical Robotics and Mechatronics (1))PANYASIRI Pongsakorn; KANO Saki; NAGAOKA Takashi; KOBAYASHI Naofumi; KURAHASHI Muneshige; TAKEDA Sunao; AOKI Takuya; TSUJI Tizuko; Urano Tetsuya; ABE Tadashi; MAGATANI Kazushigeロボティクス・メカトロニクス講演会講演概要集 2014/05 The Japan Society of Mechanical Engineers
In the purpose of pathological state by exhalation, we have developed an expiration gas analysis system. Also now there are various problems when subjects use the equipment for collecting breath gas. So we have developed the new equipment for collecting breath gas that using a pressure sensor to improve the ability to collect the sample. And because we want to know the difference between breathing resistance of the new equipment for collecting breath gas and currently equipment for collecting breath gas. So we have a subject to use the equipment of both. And we examined the breathing resistance at that time. - (012)IP Sleep-Apnea-Related Volatile Organic Compounds Are Elevated In Severe Obstructive Sleep Apnea Patients [Not invited]T. Aoki; T. Nagaoka; N. Kobayashi; M. Kurahashi; S. Yamamori; C. Tsuji; J. Tanaka; M. Sato; Y. Horio; H. Takiguchi; H. Tomomatsu; K. Tomomatsu; K. Niimi; N. Hayama; T. Oguma; T. Urano; K. Magatani; S. Takeda; K. Asano; T. AbeAMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE 2014/05 AMER THORACIC SOC
- (017)DP ハイパースペクトラルイメーシングを用いた肌色計測による化粧品効果の評価 [Not invited]TOTSUKA HIRONO; NAGAOKA TAKASHI; SOTA TAKAYUKI; KIN GINSHUKU; HANAYA TSUGUO; YAMAMOTO SAWAKO; BERUMAN DAMIAN; BATISU DOMINIKU; AJURU KURISUTOFU日本皮膚科学会雑誌 2014/04
- (011)IP Hyperspectral Imaging of Latent Fingerprints and/or Palm Prints [Not invited]T. Nagaoka; A. Nakamura; H. Okuda; N. Akiba; K. Kuroki; K. Kurosawa; F. Ichikawa; A. Torao; T. Sota66th Annual Meeting of the AAFS, Seatle, USA 2014/02
- S. Kanou; S. Iitsuka; T. Nagaoka; N. Kobayashi; M. Kurahashi; S. Takeda; T. Aoki; C. Tsuji; T. Urano; T. Abe; K. MagataniIFMBE Proceedings 2014/01© Springer International Publishing Switzerland 2014. As many as 200 kinds of volatile organic compounds (VOCs) are included in human exhaled breath. Many papers using VOCs as a biomarker of respiratory diseases have been reported. However, it is very difficult to measure very low concentration of VOCs in exhaled breath with high precision. Moreover, it is also difficult to distinguish VOCs in exhaled breath and VOCs in atmosphere. Therefore, measurement of VOCs is rarely used in a clinical field because complicated and large-sized system is required for measure VOCs in exhaled breath. We are developing exhaled breath measurement system which overcame these problems. Our system analyzes exhaled breath discharged from living body by inhaling atmosphere from which VOCs were removed. In this paper, results of system improvements are reported. At first, we adopted a cold trap method with dry ice as a method of purifying atmosphere (method A). Method A needs complicated device and long processing time. Next, we changed the method into solid absorbent from method A (method B). We verified purity of purified air. Concentration of 10 kinds of VOCs contained in both exhaled breath and atmosphere were measured. Selected VOCs are as follows: benzene, cyclohexane, ethylbenzene, heptanes, hexane, isoprene, nonane, octane, toluene and xylene. Atmosphere was purified by the method A and B. Concentrations of VOCs contained in the purified air were measured by gas chromatography. As a result of measurement, almost VOCs were not detected in the purified air made by both methods. Furthermore, time to make purified air was reduced from 70 minutes to 10 minutes. Simplification of the system and shorter processing time than method A were realized by method B while keeping purity.
- (053)DO 呼気ガス分析システムの開発に向けた基礎研究 [Not invited]狩野早紀; 永岡 隆; 小林尚史; 倉橋宗重; 武田朴; 小熊剛; 辻千鶴子; 青木琢也; 浦野哲哉; 浅野浩一郎; 阿部 直; 曲谷一成第14回計測自動制御学会 システムインテグレーション部門講演会(SI2013) 2013/12
- HIBINO KAZUTO; TAKEUCHI SHIGEKI; SHIMODA OSAMU; TAKATSU MASAHISA; AKIBA NORIMITSU; KUROSAWA KENJI; KUROKI KENRO; NAKAMURA ATSUSHI; NAGAOKA TAKASHI; SOTA TAKAYUKI日本法科学技術学会誌 2013/10
- (052)DO メラノーマ診断支援装置ハイパースペクトラル・イメージャーの性能:第二報 [Not invited]AKIYAMA SAORI; KIYOHARA YOSHIO; KOGA HIROSHI; YAMAGUCHI ASATO; NAGAOKA TAKASHI; NAKAMURA ATSUSHI; SAIDA TOSHIAKI; SOTA TAKAYUKI日本皮膚悪性腫瘍学会学術大会プログラム・抄録集 2013/08
- (009)IP Hyperspectroscopic screening of melanoma [Not invited]T. Nagaoka; A. Nakamura; Y. Kiyohara; H. Koga; T. Saida; T. Sota8th World Congress of Melanoma, Hamburg, Germany 2013/07
- (051)DO 睡眠時無呼吸症候群患者における呼気中の揮発性有機化合物濃度の検討 [Not invited]AOKI TAKUYA; NAGAOKA TAKASHI; KURAHASHI MUNESHIGE; KOBAYASHI HISASHI; YAMAMORI SHINJI; IIZUKA SHINJIRO; TAKIGUCHI HIROTO; TOMOMATSU HIROMI; TOMOMATSU KATSUIN; NIIMI KYOKO; HAYAMA NAOKI; OGUMA TSUYOSHI; URANO TETSUYA; TSUJI CHIZUKO; TAKEDA SUNAO; MAGATANI KAZUSHIGE; ASANO KOICHIRO; ABE TADASHI呼吸 2013/05
- (049)DO 肺癌患者における呼気ガス中の揮発性有機化合物の検討 [Not invited]OGUMA TAKESHI; ASANO KOICHIRO; NAGAOKA TAKASHI; KOBAYASHI HISASHI; TAKIGUCHI HIROTO; TOMOMATSU KATSUYOSHI; TOMOMATSU YUMI; NIIMI KYOKO; HAYAMA NAOKI; AOKI TAKUYA; URANO TETSUYA; ABE TADASHI日本呼吸器学会誌 2013/03
- (050)DO 睡眠時無呼吸症候群における無呼吸低呼吸指数と呼気中の揮発性有機化合物の関連 [Not invited]AOKI TAKUYA; NAGAOKA TAKASHI; KURAHASHI MUNESHIGE; KOBAYASHI HISASHI; YAMAMORI SHINJI; IIZUKA SHINJIRO; TAKIGUCHI HIROTO; TOMOMATSU YUMI; TOMOMATSU KATSUYOSHI; NIIMI KYOKO; HAYAMA NAOKI; OGUMA TSUYOSHI; URANO TETSUYA; TSUJI CHIZUKO; TAKEDA SUNAO; MAGATANI KAZUSHIGE; ASANO KOICHIRO; ABE TADASHI日本呼吸器学会誌 2013/03
- (048)DO ハイパースペクトルイメージャを用いたメラノーマの自動診断−第4報− [Not invited]永岡 隆; 中村 厚; 山口麻人; 秋山彩織; 清原祥夫; 宗田孝之第13回計測自動制御学会 システムインテグレーション部門講演会(SI2012) 2012/12
- (015)DP 喫煙習慣による呼気ガスの揮発性有機化合物の変化 [Not invited]IITSUKA SHINJIRO; NAGAOKA TAKASHI; KOBAYASHI NAOFUMI; KURAHASHI MUNESHIGE; TAKEDA SUNAO; AOKI TAKUYA; TSUJI CHIZUKO; URANO TETSUYA; ABE TADASHI; MAGATANI KAZUSHIGE日本生体医工学会大会プログラム・論文集(CD-ROM) 2012/05
- (008)IP Subclinical extension of morphea-like basal cell carcinoma: hyperspectral evaluation [Not invited]T. Nagaoka; Y. Kiyohara; A. Nakamura; A. Yamaguchi; T. SotaDermatol Pract Concept., Brisbane, Australia 2012/04
- (047)DO 睡眠時無呼吸症候群患者における呼気中の揮発性有機化合物の検討 [Not invited]AOKI TAKUYA; NAGAOKA TAKASHI; KOBAYASHI HISASHI; KURAHASHI MUNESHIGE; YAMAMORI SHINJI; IIZUKA SHINJIRO; KATO SAKURAKO; HAYAMA NAOKI; URANO TETSUYA; TSUJI CHIZUKO; TAKEDA SUNAO; MAGATANI KAZUSHIGE; ABE TADASHI日本呼吸器学会誌 2012/03
- (046)DO ハイパースペクトルイメージャを用いたメラノーマの自動診断−第3報− [Not invited]永岡 隆; 中村 厚; 山口麻人; 清原祥夫; 宗田孝之第12回計測自動制御学会 システムインテグレーション部門講演会(SI2011) 2011/12
- (045)DO 足底に発生したメラノーマの自動鑑別 [Not invited]永岡 隆; 中村 厚; 奥谷 悠; 清原祥夫; 古賀弘志; 斎田俊明; 宗田孝之第27回日本皮膚悪性腫瘍学会学術大会 2011/06
- HISADA JUN'ICHIRO; AOKI TAKUYA; KOBAYASHI HISASHI; NAGAOKA TAKASHI; YAMAMORI SHINJI; INAMURA MASANORI; ISHII HIROSHI; KATO SAKURAKO; HAYAMA NAOKI; URANO TETSUYA; TAKEDA SUNAO; ABE TADASHI日本呼吸器学会雑誌 2011/03
- (043)DO ハイパースペクトルイメージャーを用いたメラノーマの自動診断−第2報− [Not invited]永岡 隆; 中村 厚; 奥谷 悠; 清原祥夫; 宗田孝之第11回計測自動制御学会 システムインテグレーション部門講演会(SI2010) 2010/12
- (042)DO ハイパースペクトルデータに基づくメラノーマの新しい非侵襲的診断法の開発 [Not invited]奥谷 悠; 中村 厚; 永岡 隆; 清原祥夫; 宗田孝之第23回日本色素細胞学会学術大会 2010/11
- (040)DO メラノーマの新しい非侵襲的診断法の開発〜ハイパースペクトルデータ(HSD)に基づくメラノーマ鑑別指標〜 [Not invited]奥谷 悠; 永岡 隆; 中村 厚; 清原祥夫; 宗田孝之第26回日本皮膚悪性腫瘍学会学術大会 2010/06
- (041)DO メラノーマの新しい非侵襲的診断法の開発〜ハイパースペクトルイメージャ(HSI)によるメラノーマの診断〜 [Not invited]清原祥夫; 奥谷 悠; 永岡 隆; 中村 厚; 宗田孝之第26回日本皮膚悪性腫瘍学会学術大会 2010/06
- (007)IP A noble melanoma discrimination index based on hyperspectral data [Not invited]H. Okutani; T. Nagaoka; A. Nakamura; Y. Kiyohara; T. Sota21st European Association for Cancer Research Congress, Oslo, Norway 2010/06
- (039)DO ハイパースペクトルカメラを用いたメラノーマの自動診断 [Not invited]永岡 隆; 中村 厚; 奥谷 悠; 會沢勝夫; 大坪真也; 清原祥夫; 宗田孝之第10回計測自動制御学会 システムインテグレーション部門講演会(SI2009) 2009/12
- (037)DO 悪性黒色腫の機械診断:可能性試験 [Not invited]NAGAOKA TAKASHI; NAKAMURA ATSUSHI; OKUTANI HARUKA; AIZAWA KATSUO; OTSUBO SHIN'YA; KIYOHARA YOSHIO; SOTA TAKAYUKI応用物理学会学術講演会講演予稿集 2009/09
- (038)DO 悪性黒色腫診断支援画像 [Not invited]NAKAMURA ATSUSHI; NAGAOKA TAKASHI; OTSUBO SHIN'YA; AIZAWA KATSUO; KIYOHARA YOSHIO; SOTA TAKAYUKI応用物理学会学術講演会講演予稿集 2009/09
- (006)IP Optical Diagnostics System of Melanoma based on Hyperspectral Imaging Technique [Not invited]A. Nakamura; T. Nagaoka; S. Ohtsubo; K. Aizawa; Y. Kiyohara; T. Sota7th World Congress on Melanoma, Vienna, Austria 2009/05
- (005)IP Melanoma Discrimination Index derived from Optical Spectra [Not invited]T. Nagaoka; A. Nakamura; K. Aizawa; S. Ohtsubo; Y. Kiyohara; T. Sota7th World Congress on Melanoma, Vienna, Austria 2009/05
- (014)DP ハイパースペクトルカメラを用いた悪性黒色腫の自動診断 [Not invited]NAGAOKA TAKASHI; NAKAMURA ATSUSHI; AIZAWA KATSUO; OTSUBO SHIN'YA; MOCHIZUKI TOORU; KIYOHARA YOSHIO; SOTA TAKAYUKI日本生体医工学会大会プログラム・論文集(CD-ROM) 2009/04
- (036)DO 色素性病変診断のためのメラニン量分布画像 [Not invited]NAKAMURA ATSUSHI; NOMURA MASAHIRO; SUZUKI ASAYOSHI; OSATO NAO; MATSUMURA AZUSA; OTSUBO SHIN'YA; AIZAWA KATSUO; SOTA TAKAYUKI; NAGAOKA TAKASHI; FURUKAWA MASAYO; KIYOHARA YOSHIO; ITO SHOSUKE; WAKAMATSU KAZUMASA日本皮膚科学会雑誌 2009/04
- (035)DO 色素性病変診断に向けたメラニン,ヘモグロビン濃度強調マップの作製 [Not invited]NAKAMURA ATSUSHI; NAGAOKA TAKASHI; OTSUBO SHIN'YA; AIZAWA KATSUO; KIYOHARA YOSHIO; SOTA TAKAYUKI日本皮膚科学会雑誌 2009/03
- (001)I講演 Automated Melanoma Recognition using Hyperspectral Image Analysis [Invited]T. NagaokaInternational Workshop HITS 2009, Tokyo Institute of Technology, Tokyo, Japan 2009/02
- (034)DO 多層モデルによる皮膚の分光特性推定 [Not invited]永岡 隆; 清原祥夫; 中村 厚; 野村将大; 鈴木麻悌; 大里奈央; 松村あずさ; 大坪真也; 會沢勝夫; 宗田孝之; 古川雅代; 伊藤祥輔; 若松一雅第9回計測自動制御学会システムインテグレーション部門講演会(SI2008) 2008/12
- (033)DO 3次元皮膚モデルを用いたメラニン濃度分布の画像化 [Not invited]NAKAMURA ATSUSHI; NAGAOKA TAKASHI; FURUKAWA MASAYO; NOMURA MASAHIRO; SUZUKI ASAYOSHI; OSATO NAO; MATSUMURA AZUSA; OTSUBO SHIN'YA; AIZAWA KATSUO; KIYOHARA YOSHIO; ITO SHOSUKE; WAKAMATSU KAZUMASA; SOTA TAKAYUKI応用物理学会学術講演会講演予稿集 2008/09
- (032)DO 3次元皮膚モデルの光学的特性 [Not invited]NAGAOKA TAKASHI; NAKAMURA ATSUSHI; FURUKAWA MASAYO; NOMURA MASAHIRO; SUZUKI ASAYOSHI; OSATO NAO; MATSUMURA AZUSA; OTSUBO SHIN'YA; AIZAWA KATSUO; KIYOHARA YOSHIO; ITO SHOSUKE; WAKAMATSU KAZUMASA; SOTA TAKAYUKI応用物理学会学術講演会講演予稿集 2008/09
- (013)DP 近赤外眼底分光画像に関するリング状照明モデルによる輝度値補正 [Not invited]NAKAMURA ATSUSHI; NAGAOKA TAKASHI; NOMURA MASAHIRO; OTSUBO SHIN'YA; AIZAWA KATSUO; SOTA TAKAYUKI日本生体医工学会大会プログラム・論文集(CD-ROM) 2008/05
- (011)DP 眼底スペクトル画像に対するリング照明に起因した照明ムラの除去 [Not invited]NAGAOKA TAKASHI; NAKAMURA ATSUSHI; SOTA TAKAYUKI; AIZAWA KATSUO; OTSUBO SHIN'YA日本糖尿病眼学会誌 2008/04
- (012)DP 近赤外光を用いた眼底スペクトル撮像装置の開発 [Not invited]NAKAMURA ATSUSHI; NAGAOKA TAKASHI; SOTA TAKAYUKI; AIZAWA KATSUO; ICHIKAWA FUMIHIKO; KANAZAWA MASAO; KEZUKA TAKESHI; SHIRAI MASAHIKO日本糖尿病眼学会誌 2008/04
- (031)DO ハイパースペクトルカメラを用いた皮膚血行動態の観察 [Not invited]永岡 隆; 清原?夫; 中村 厚; 會沢勝夫; 大坪真也; 宗田孝之; 市川文彦; 山嵜登志夫; 土居正雄; 中村勝重第8回システムインテグレーション部門講演会(SI2007) 2007/12
- (030)DO in vitro皮膚組織モデルを用いた分光学的メラニン色素濃度定量法の検討 [Not invited]NAKAMURA ATSUSHI; TANIGAWA SAYAKA; FURUKAWA MASAYO; AIZAWA KATSUO; NAGAOKA TAKASHI; OTSUBO SHIN'YA; WAKAMATSU KAZUMASA; ITO SHOSUKE; SOTA TAKAYUKI応用物理学会学術講演会講演予稿集 2007/09
- (004)IP Application of decorrelation stretching method to hyperspectral fundus image processing [Not invited]T. Nagaoka; A. Nakamura; K. Aizawa; M. Kanazawa; T. Kezuka; M. Miura; M. Usui; S. Ohtsubo; T. SotaProgress in Biomedical Optics and Imaging - Proceedings of SPIE 2007/08We have developed a near-infrared hyperspectral imaging system that can acquire both spectral and spatial data covering a 50-degree field at the fundus surface within 5 seconds. Single wavelength band reflectance images with bandwidth of 20 nm have demonstrated that choroidal vascular patterns can be clearly observed as bright images for the central wavelength ranging from 740 to 860 nm, while retinal blood vessels are seen as dark images for that ranging from 740 to 920 nm. It is desirable for clinical use to separate the choroidal vascular patterns image from the retinal blood vessels image. To this end, we have applied the decorrelation stretch to processing of spectral images. We have found the following. Original fundus spectral images have stripes noise. The decorrelation stretch emphasizes the noise and, thus, the noise has to be removed by, for example, DCT (Discrete Cosine Transform) filter beforehand. The choroidal vascular image can be successfully separated from the retinal vascular image. Furthermore, the macular is superimposed on the latter as it should be so from the viewpoint of anatomy. The result suggests that useful information may be extracted by combining hyperspectral images with the decorrelation stretch.
- (003)IP Near-infrared hyperspectral images of human ocular fundus and their processing with decorrelation stretch [Not invited]T. Nagaoka; A. Nakamura; K. Aizawa; M. Kanazawa; T. Kezuka; M. Miura; M. Usui; S. Ohtsubo; T. SotaProgress in 2007 ARVO Annual Meeting "The Aging Eye", Florida, USA 2007/05
- (010)DP ハイパースペクトル医用画像を用いたerythema indicesの観察 [Not invited]NAGAOKA TAKASHI; NAKAMURA ATSUSHI; AIZAWA KATSUO; OTSUBO SHIN'YA; KIYOHARA YOSHIO; SOTA TAKAYUKI日本生体医工学会大会プログラム・論文集(CD-ROM) 2007/04
- (009)DP ハイパースペクトル眼底画像への非相関強調の適用 [Not invited]NAGAOKA TAKASHI; NAKAMURA ATSUSHI; AIZAWA KATSUO; KANAZAWA MASAO; KEZUKA TAKESHI; MIURA MASAHIRO; USUI MASAHIKO; OTSUBO SHIN'YA; SOTA TAKAYUKI日本分光学会講演要旨集 2006/11
- (008)DP 近赤外眼底ハイパースペクトル画像撮像装置の開発 [Not invited]NAKAMURA ATSUSHI; AIZAWA KATSUO; NAGAOKA TAKASHI; ICHIKAWA FUMIHIKO; KANAZAWA MASAO; KEZUKA TAKESHI; MIURA MASAHIRO; USUI MASAHIKO; SOTA TAKAYUKI日本分光学会講演要旨集 2006/11
- (029)DO 近赤外眼底スペクトル画像撮像装置の臨床応用に向けた検討 [Not invited]TANGO MANABU; NAKAMURA ATSUSHI; AIZAWA KATSUO; NAGAOKA TAKASHI; KANAZAWA MASAO; KEZUKA TSUYOSHI; MIURA MASAHIRO; USUI MASAHIKO; ICHIKAWA FUMIHIKO; MUNETA TAKAYUKI日本レーザー医学会誌 2006/07
- (003)DP 眼底スペクトル画像上でのニュートン法を用いた照明ムラ補正 [Not invited]KUROIWA YOHEI; NAGAOKA TAKASHI; NAKAMURA ATSUSHI; AIZAWA KATSUO; OTSUBO SHIN'YA; SOTA TAKAYUKI日本生体医工学会大会プログラム・論文集 2006/05
- (004)DP 近赤外眼底スペクトル画像 [Not invited]NAKAMURA ATSUSHI; AIZAWA KATSUO; NAGAOKA TAKASHI; ICHIKAWA FUMIHIKO; KANAZAWA MASAO; KEZUKA TAKESHI; USUI MASAHIKO; SOTA TAKAYUKI日本生体医工学会大会プログラム・論文集 2006/05
- (005)DP 永久磁石を用いた3次元位置検出システムの開発(第4報) [Not invited]KUWATA EIGO; NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本生体医工学会大会プログラム・論文集 2006/05
- (006)DP 眼底スペクトル撮像装置を用いた糖尿病性網膜症由来浮腫の観察 [Not invited]TANGO MANABU; NAKAMURA ATSUSHI; AIZAWA KATSUO; NAGAOKA TAKASHI; KANAZAWA MASAO; KEZUKA TAKESHI; USUI MASAHIKO; ICHIKAWA FUMIHIKO; SOTA TAKAYUKI日本生体医工学会大会プログラム・論文集 2006/05
- (007)DP 多波長パルス分光法による多項目血液成分無侵襲計測器の開発 [Not invited]SUZAKI HIRONORI; KOBAYASHI NAOKI; NAGAOKA TAKASHI; TAKEDA SUNAO; TOGAWA TATSUO日本生体医工学会大会プログラム・論文集 2006/05
- (002)DP スペクトル画像を用いた脈絡膜血管観察 [Not invited]NAKAMURA ATSUSHI; NAGAOKA TAKASHI; SOTA TAKAYUKI; AIZAWA KATSUO; ICHIKAWA FUMIHIKO; KANAZAWA MASAO; KEZUKA TAKESHI; USUI MASAHIKO応用物理学関係連合講演会講演予稿集 2006/03
- (001)DP 眼底スペクトル画像における照明系に起因した輝度値変化の補正 [Not invited]NAGAOKA TAKASHI; NAKAMURA ATSUSHI; SOTA TAKAYUKI; AIZAWA KATSUO; OTSUBO SHIN'YA応用物理学関係連合講演会講演予稿集 2006/03
- (002)IP Development of 3-d position sensor by using permanent magnets in the digestive tract [Not invited]T. Nagaoka; A. UchiyamaThe 3rd European Medical and Biological Engineering Conference EMBEC'05, Prague, Czech Republic 2005/12Medical capsule devices such as video capsule endoscopes are finding increasing use in clinical applications. At present, technologies capable of measuring capsule position and detecting a bleeding in the digestive tract at the same time have not yet been established. The present study aims to develop a small wireless position and bleeding detection sensor. The sensor position are measured by using the phenomenon of mutual induction and Newton's law. Electromotive forces induced in the sensor are modulated to FM signals using an astable multivibrator, and the signals are passed directly through living tissue at low current and then demodulated by detectors on the surface of the body. A prototype sensor was developed and evaluated in vitro. The sensor was capable of accurately measuring capsule position up to 500 (mm) from the primary coils with an accuracy of 5 (mm), and detecting 0.5 cc blood in 500 cc physiological saline. © 2005 IEEE.
- (028)DO C-10-4 Development and Evaluation of 3-D position sensor using a permanent magnet [Not invited]Nagaoka TakashiProceedings of the Society Conference of IEICE 2005/09
- ICHIKAWA Daisuke; NAGAOKA Takashi; UCHIYAMA Akihiko; TAKEDA Sunao電気学会研究会資料. MBE, 医用・生体工学研究会 2005/07
- (026)DO 運動中の心電図計測・解析システムの開発 [Not invited]CHIYODA SHIGEO; NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本ME学会大会論文集 2005/04
- (024)DO 透過波を利用した超音波断層像構築に向けた基礎研究 [Not invited]KUWATA EIGO; NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本ME学会大会論文集 2005/04
- (025)DO 永久磁石を用いた位置検出システムの開発(第三報) [Not invited]ICHIKAWA DAISUKE; NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本ME学会大会論文集 2005/04
- (022)DO 永久磁石を用いた位置検出システムの開発(第二報) [Not invited]ICHIKAWA DAISUKE; NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本ME学会秋季大会論文集 2004/11
- (021)DO 無線式カプセル型三次元位置センサの開発 [Not invited]NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本ME学会秋季大会論文集 2004/11
- (023)DO 無侵襲Co‐Oximeterの開発 [Not invited]SUZAKI HIRONORI; KOBAYASHI NAOKI; KUBOTA HIROSHI; NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本ME学会秋季大会論文集 2004/11
- NAGAOKA T; ICHIKAWA D; UCHIYAMA A日本応用磁気学会学術講演概要集 = Digest of ... annual conference on magnetics in Japan 2004/09
- (018)DO 非観血血圧計測における耐ノイズ性向上に関する基礎的研究 [Not invited]DODA HIDENORI; USUDA TAKASHI; NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本ME学会大会論文集 2004/05
- (019)DO 永久磁石を用いた位置検出システムの開発 [Not invited]ICHIKAWA DAISUKE; NAGAOKA TAKASHI; TAKEDA SUNAO; UCHIYAMA AKIHIKO日本ME学会大会論文集 2004/05
- (017)DO カプセル型三次元位置センサの無線化への検討 [Not invited]NAGAOKA TAKASHI; UCHIYAMA AKIHIKO日本ME学会大会論文集 2004/05
- (001)IP Development of 3-D Position Sensor for capsule endoscopy [Not invited]T. Nagaoka3rd International Conference on CAPSULE ENDOSCOPY, Miami, USA 2004/02
- (016)DO 生体用カプセル型三次元位置センサの開発 [Not invited]永岡 隆; 内山明彦第17回日本エム・イー学会秋季大会 2003/10
- (015)DO 有線式カプセル型三次元位置センサを用いた大腸の蠕動運動の計測 [Not invited]永岡 隆; 武田 朴; 松本孝嗣; 高尾良彦; 穴澤貞夫; 内山明彦MEシンポジウム2003 2003/08
- (002)IO Development of the three-dimensional position sensor for capsule position detection in digestive tract [Not invited]T.Nagaoka; A.UchiyamaConference of the International Society on Biotelemetry 2003/08
- (012)DO 消化管運動計測のためのカプセル型三次元位置センサの開発とその小型化の検討 [Not invited]永岡 隆; 内山明彦平成15年電気学会電子・情報・システム部門大会講演論文集 2003/05
- (014)DO 永久磁石を用いた生体内のカプセル位置検出システムの開発 [Not invited]永岡 隆; 市川大輔; 内山明彦第42回日本エム・イー学会大会 2003/05
- (013)DO 消化管内のカプセル位置を取得する三次元位置センサの開発 [Not invited]永岡 隆; 武田 朴; 松本孝嗣; 高尾良彦; 穴澤貞夫; 内山明彦第42回日本エム・イー学会大会 2003/05
- (011)DO 消化器官の運動や生理的現象を解析するシステムの開発 -第2報- [Not invited]永岡 隆; 内山明彦電気学会研究会資料(医用・生体工学研究会) 2003/03
- (010)DO 消化器官の運動や生理的現象を解析するシステムの開発 [Not invited]永岡 隆; 長澤拓弥; 武田朴; 松本孝嗣; 高尾良彦; 穴澤貞夫; 内山明彦電気学会研究会資料(医用・生体工学研究会) 2002/10
- (009)DO 脛骨高位骨切り術シミュレーションのための軟組織の変形と干渉を考慮できる膝モデルの開発 [Not invited]永岡 隆; 川上秀夫; 米延策雄; 菅野伸彦; 萩尾圭介; 吉川秀樹; 越智隆弘; 服部麻木; 鈴木直樹第41回日本ME学会大会 2002/05
- (008)DO New Three-Dimensional Endoscopic Sonograph Using Electo-Magnetic Tracking System [Not invited]SUMIYAMA K; SUZUKI N; HATTORI A; KOIZUMI N; NAGAOKA T; UCHIYAMA Y; IKEDA K; KAKUTANI H; TAJIRI H; AOKI TJournal of Japan Society of Computer Aided Surgery : J.JSCAS 2001/12
- (007)DO Assesment of A Surgical Planning for High Tibial Osteotomy using a 3D Simulation Program [Not invited]KAWAKAMI Hideo; SUGANO Nobuhiko; HAGIO Keisuke; YONENOBU Kazuo; YOSHIKAWA Hideki; OCHI Takahiro; NAGAOKA Takashi; HATTORI Asaki; SUZUKI NaokiJournal of Japan Society of Computer Aided Surgery : J.JSCAS 2001/12
- (006)DO Development of Simulation System for High Tibia Osteotomy Using Muscle and Tendon Model [Not invited]NAGAOKA T; KAWAKAMI H; YONENOBU S; SUGANO N; HAGIO K; YOSHIKAWA H; OCHI T; HATTORI A; SUZUKI NJournal of Japan Society of Computer Aided Surgery : J.JSCAS 2001/12
- (001)IO The Development of Diagnosis Support System using 4D Imaging and VR Environment [Not invited]T.Nagaoka; N.Suzuki; A.Hattori, Richard A.Robb; K.Sumiyama; N.Koizumi; A.UchiyamaThe 5th World Multiconference on Systemics, Cybernetics and Informatics SCI, Florida, USA 2001/08
- (004)DO 四次元画像診断支援システムの開発 [Not invited]永岡 隆; 鈴木直樹; 服部麻木; Richard A.Robb; 炭山和毅; 小泉直史; 内山明彦第40回日本ME学会大会 2001/05
- (005)DO コンベックス走査式超音波内視鏡により得た超音波三次元データセットの表示法の開発 [Not invited]小泉直史; 炭山和毅; 青木照明; 鈴木直樹; 服部麻木; 永岡 隆; 内山明彦第40回日本ME学会大会 2001/05
- (002)DO The Development of Visualization Method for Four-Dimensional Image Using VR Environment [Not invited]NAGAOKA T; SUZUKI N; HATTORI A; ROBB Richard A; SUMIYAMA K; UCHIYAMA AJournal of Japan Society of Computer Aided Surgery : J.JSCAS 2000/12
- (003)DO New Three Dimensional Endoscopic Ultrasound Systems with Convex Scanning Echoendoscopes [Not invited]SUMIYAMA K; SUZUKI N; HATTORI A; KOIZUMI N; NAGAOKA T; HINO S; SUZUKI H; AOKI TJournal of Japan Society of Computer Aided Surgery : J.JSCAS 2000/12
- (001)DO 四次元CTデータセット可視化のための表示システムの開発 [Not invited]永岡 隆; 鈴木直樹; 服部麻木; 松下 聡; 高津光洋; 内山明彦第39回日本ME学会大会 2000/05
Courses
- Basic Technical Course of English for Biological Systems EngineeringBasic Technical Course of English for Biological Systems Engineering Kindai University
- Electronic Measurement and Its Application to Biological SystemsElectronic Measurement and Its Application to Biological Systems Kindai University
- Electronic CircuitsElectronic Circuits Kindai University
- Fundamental Experiments of Information TechnologyFundamental Experiments of Information Technology Kindai University
- Exercises of Fundamental Mathematics 1Exercises of Fundamental Mathematics 1 Kindai University
- BiosensorBiosensor Kindai University
Affiliated academic society
Works
- ハイパースペクトルイメージング技術の臨床応用永岡 隆 Others 2008/04 - Today位置情報と波長情報を同時に取得することができるハイパースペクトルイメージング技術を利用し、無侵襲で生体の様々な情報を計測・診断するシステムの開発を推進。早稲田大学・三鷹光器・静岡がんセンター・信州大学・国立がん研究センターなどと共同研究を実施。眼科・皮膚科・消化器外科・口腔外科用途のシステムを開発した。眼科では加齢黄斑変性を検出するシステムを開発。皮膚科ではメラノーマを高い精度で鑑別するシステムを開発し、国内外における臨床試験が進められている。特にメラノーマを鑑別するアルゴリズムの開発と、装置のインターフェースの開発に従事。アルゴリズム開発ではリモートセンシング分野で使われていたSpectral Angleの技術と、エントロピーの原理を組み合わせた独自のメラノーマ鑑別指標を開発。メラノーマを90%以上の精度で鑑別することに成功している。
- マルチスペクトル眼底カメラの撮影画像に生じる照明ムラ除去法の開発とその応用永岡 隆 Others 2006/04 -2008/03生活習慣病(成人病)の早期発見のための検査の一つとして,集団検診などで眼底画像による検査が実施されている.眼底画像は一般に眼底カメラと呼ばれる機器で撮影されることが多いが,その撮影時の照明として,リング状の照明が用いられることが多い.眼底画像を撮像するための光路を確保し,かつ十分な光量の照明を当てるためにリング照明が採用されているが,リング照明の場合,照明光が平行光とならず,被写体に対してどうしても照明ムラが発生してしまうという欠点を抱えている.当該研究課題では,この照明ムラを数学的手法により取り除き,リング照明下ながら,平行光によって照明されたような眼底画像を取得する方法の開発を推進.研究で開発したアルゴリズムを基に,コンピュータグラフィックスを用いた画像表示システムを構築し,画像本来の持つ情報を損なうことなく,照明ムラを取り除くことに成功.眼底画像全体のコントラストの向上と,暗部に隠されていた血管の走行を確認することに成功.
- 生体内三次元位置計測センサの開発とその応用永岡 隆 Others 2003/04 -2006/03食生活の欧米化により患者数の増加が予想される消化器系の疾患に対し,臨床において試験が進められているカプセル型内視鏡であるが、その位置を正確に把握できないという問題を抱えていた。そこでカプセル型内視鏡の位置を計測できる程度のサイズ・精度を持った三次元位置計測センサの開発を東京慈恵会医科大学などとの共同研究として推進.有線式の試作機における動物実験を実施し、位置計測アルゴリズムの有用性の確認を終え,臨床応用に向けた実用化研究に着手.相互誘導起電力を応用したセンサと永久磁石を用いたセンサの2種類を開発。センサの無線化,小型化,多機能化,生体外からの姿勢制御についての技術開発を推進した.特に相互誘導起電力を用いた位置センサの開発において、双方に三軸必要であったコイルを、検出側1軸、励磁側6軸とすることで、検出精度を落とすことなく、カプセル側の電子回路を小型化することを実現。
- 脛骨高位骨切り術シミュレーションのための軟組織の変形と干渉を考慮した膝モデルの開発永岡 隆 Others 2001/04 -2003/03高齢化社会の進展により患者数の増加が予想される、変形性膝関節症に対する外科的措置である脛骨高位骨切り術の手術シミュレーションシステムの開発を大阪大学医学部との共同研究として推進。術前に計測された患者のMRI画像からモデルを構築し、歩様推定に必要な各種座標系を自動的に設定できるシステムを構築。事前に術式、切除量をシミュレーションできるシステムを開発した。システムは実際の臨床現場に導入され、術中でもリアルタイムに各種パラメータをモデルに反映し、シミュレーションできる機能が高く評価された。
- 三次元CTの効果的な表示法の開発永岡 隆 Others 1999/04 -2001/03新エネルギー・産業技術総合開発機構(NEDO)における「高速コーンビーム3次元X線CT」プロジェクトにて開発された、高速コーンビーム3次元X線CTを用い、三次元CTで得られたデータを効果的に表示・診断が可能なシステムの開発を推進。また、米国Mayo Clinicとの共同研究で、4次元X線CTによって計測された犬の心臓の拍動データの解析を担当。VR空間上で膨大なデータから必要なスライドのみを容易に選択できる環境を構築。形状の把握に適しているサーフェスレンダリング法と、流体の流れを可視化できるボリュームレンダリング法を組み合わせ、心臓内の血流の状態と心臓内壁の拍動状態を同時に観察できる新しいレンダリング方法を開発した。
Research Themes
- Japan Society for the Promotion of Science:Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)Date (from‐to) : 2020/04 -2023/03Author : 永岡 隆深層学習を用いたメラノーマの自動診断システム開発に向け、要素技術の開発に取り組んだ。具体的には、AIの視野を集中させる手法の開発、敵対的生成ネットワークによるデータ加増を用いた深層学習の訓練法の開発、深層学習とサポートベクターマシーンを組み合わせ、少ないデータでも識別器が訓練できる手法の開発、mix-up、random croppingなどのデータ加増による診断性能向上の検証、その他最新の知見を取り入れた新規ネットワーク構造の採用・検討などに取り組んだ。 視野の集中に関しては、深層学習に色素病変の部分だけを投入する手法を複数組み合わせ、診断性能の向上が確認された。加増においても、中心部に病変部が残る形で、周辺の皮膚のみを差し替えることで正診率が向上する効果が確認された。深層学習はどの部分を見て診断したのかを明らかにする、ホワイトボックス化が進んでおり、本研究もその応用として実施。深層学習に見て欲しい部分をより強調して提示することで、診断性能が向上することが確認されつつある。より積極的に視野を限定するため、病変部を正確に抽出し、そのマスクを深層学習の特徴マップに重畳する手法の検討を今後進める。 本邦ではメラノーマ患者が少ない事などを鑑み、複数のデータ加増手法による診断性能の向上にも取り組んだ。今年度はパッチ加増の有用性について検証し、弱いパッチ加増がメラノーマ診断に有効であることが確認された。前述の病変部周囲のみを差し替えることによる加増効果が確認されつつあり、本研究による加増が人工知能の学習に有用であることが判明した。 今後はメラノーマ以外の希少病変、例えばCOVID-19のCTデータなどを対象に、ビックデータが必要な深層学習の訓練に資する手法の開発に取り組む予定である。
- Kindai University:All-Kindai University support project against COVID-19Date (from‐to) : 2020/04 -2021/03Author : 木村裕一; 永岡隆; 石井一成; 小塚健倫; 山田誉大; 根本充貴; 半田久志; 阿部孝司; 波部斉; 多田昌裕; 吉田久
- Japan Society for the Promotion of Science:Grants-in-Aid for Scientific ResearchDate (from‐to) : 2014 -2016Author : NAGAOKA TakashiIn this study, clinical practical application of hyper spectral imaging technology was examined. A quantitative evaluation index of cosmetics was also developed. Hyperspectral imager costs higher. By diverting the parts of existing equipment, it turned out that it can be trial-manufactured inexpensively. Experiments with healthy volunteers were conducted as a development of a cosmetic evaluation system. As a result of the analysis, effective quantitative evaluation method of cosmetics was established.
- Ministry of Education, Culture, Sports, Science and Technology:Grants-in-Aid for Scientific Research(若手研究(B))Date (from‐to) : 2011 -2013Author : Takashi NAGAOKACancer diagnostic system using hyperspectral imaging technique was newly developed. In paticular, melanoma diagnosis support system suitable for clinical field was newly developed and its practicality was verifyed. The system succeed in collecting the 200 cases without a trouble and achieved high accuracy (over 90% in sensitivity and specificity). Hyperspectral imaging system for endscopy was also developed and verifyed by animal experiment. It was confirmed that the system can measure spectra in a digestive tract. Clinical test in Swedish area is planned from now on aiming at the global launch of the melanoma diagnosis device.
- 表在性腫瘍や血管障害を診断することができるマルチスペクトルカメラの開発とその表示法の開発公益財団法人 村田学術振興財団:2007年度研究助成Date (from‐to) : 2007/04 -2008/03Author : 永岡 隆
- がんの超早期診断に資するマルチスペクトラルカメラの開発財団法人中谷電子計測技術振興財団:第24回(平成19年度)研究助成Date (from‐to) : 2007/04 -2008/03Author : 永岡 隆
- Ministry of Education, Culture, Sports, Science and Technology:Grants-in-Aid for Scientific Research(若手研究(A))Date (from‐to) : 2007 -2008Author : Takashi NAGAOKA我々はハイパースペクトル(HS)・イメージング技術を用いた診断システムの開発研究を行っている。本システムによる計測の同意が得られた被験者を計測した。スペクトルをベクトルとみなし、基準ベクトルとのなす角を計算した。得られた角度分布マップのフラクタル次元を鑑別指標と定義し、この指標の有用性を統計的手法を用い確認した。感度は84%、特異度は90%であった。本鑑別指標は悪性腫瘍の特徴を反映した高性能な指標になり得ると考えられる。
- 永久磁石を用いた生体内三次元位置センサの開発とその応用公益財団法人 立石科学技術振興財団:平成17年度研究助成Date (from‐to) : 2005/04 -2006/03Author : 永岡 隆
- カプセル型内視鏡の位置検出に適した無線式三次元位置センサの開発公益信託 小澤・吉川記念エレクトロニクス研究助成基金助成金:Date (from‐to) : 2004/04 -2005/03Author : 永岡 隆
- カプセル型医用機器等の生体内位置計測に適した小型位置センサの開発とその応用公益財団法人 マツダ財団:第20回(2004年度)マツダ研究助成Date (from‐to) : 2004/04 -2005/03Author : 永岡 隆
- 生体内に適した無線式三次元位置センサの開発と応用財団法人 倉田記念日立科学技術財団:第37回(平成16年度)倉田奨励金Date (from‐to) : 2004/04 -2005/03Author : 永岡 隆
- カプセル型生体内三次元位置センサの開発と その応用公益財団法人 カシオ科学振興財団:第22回(平成16年度)研究助成Date (from‐to) : 2004/04 -2005/03Author : 永岡 隆
- カプセル内視鏡などのカプセル型生体計測機器に適した三次元位置計測センサの開発とセンサを用いた腸蠕動運動機能の計測公益財団法人 鈴木謙三記念医科学応用研究財団:2003年度 研究助成Date (from‐to) : 2003/04 -2005/03Author : 永岡 隆
- 文部科学省:科学研究費補助金(萌芽研究)Date (from‐to) : 2005 -2005Author : 永岡 隆無線カプセル型機器の生体内での3次元位置情報は,X線などの被爆無しに長時間正確に計測することができない.本研究では,生体内の3次元位置を非侵襲かつリアルタイムに計測することができるシステムの開発を目的とした.本システムは,マーカである小型永久磁石,平面磁界センサアレイとその駆動回路,磁界測定値の集計・計算・表示装置であるPCにより構成されている.本研究ではカプセル内視鏡の直径に合わせφ8mm×3.8mmの希土類ネオジウム磁石を採用した.磁界の計測を行なうセンサアレイには,縦横それぞれ50mm間隔で3×3の格子状に磁界センサ9個を配置した.このセンサアレイ2個を300mm間隔で正対させて配置し,センサアレイ間における磁石の位置を測定対象とした.各センサから駆動回路,A/Dコンバーターを介した後にPCへと磁界分布が集積される.PCでは,永久磁石を磁気双極子とみなし,磁気双極子から発生する磁界の理論値と実測値との差が最小となる値を,永久磁石の空間位置座標として算出する.最適値の算出にはガウス・ニュートン法を用いた.これまではフラックスゲート素子を採用していたが、計測可能な最小磁界が10mGと大きいため,システムの計測範囲が狭いことが問題であった.そこで,0.1mG〜2Gまでの測定が可能であるAMR素子を採用した.また,センサに変更に伴い駆動回路,プログラムを改良した.磁気センサの感度軸方向について測定した結果,7mG付近までは計測電圧と真値との誤差が10%を下回った.この素子を利用して,フラックスゲート素子により構築したシステムと同じシステムを構築する場合,計測範囲を400mmまで広げることが可能となる.駆動回路の改良により計測可能な最小磁界をさらに小さくすることを予定している.
Industrial Property Rights
- 特許6437466:化粧品の皮膚に対する美容効果を評価するための方法 2018/11/22戸塚 広乃, ウンスク・キム, ドミニク・バティス, クリストフ・アジュール, 宗田 孝之, 永岡 隆 ロレアル 201603019668205856
- 特許第5565765号:メラノーマ鑑別指標の導出方法 2014/06/27宗田 孝之, 會沢 勝夫, 大坪 真也, 永岡 隆, 清原 祥夫 学校法人早稲田大学, 静岡県 201403001161004601
- 特開2014-023603:睡眠時無呼吸判定装置 2014/02/06倉橋 宗重, 小林 尚史, 武田 朴, 永岡 隆, 阿部 直, 浦野 哲哉, 青木 琢也, 辻 千鶴子 日本光電工業株式会社, 学校法人早稲田大学, 学校法人東海大学 201403041268070080
- 特許第5408527号:メラノーマ診断用画像の作成方法 2013/11/15宗田 孝之, 中村 厚, 大坪 真也, 會沢 勝夫, 永岡 隆, 清原 祥夫 学校法人早稲田大学, 静岡県 201403095347551950
- 特開2010-051589:非侵襲ヒト皮膚メラニン計測法及びその装置 2010/03/11宗田孝之, 中村厚, 大坪真也, 會沢勝夫, 永岡隆, 古川雅代 学校法人早稲田大学, 静岡県, 一丸ファルコス株式会社 201003093151095644
- 特開2007-173894:点光源撮影画像の補正装置および補正方法 2007/07/05永岡 隆, 宗田 孝之, 會沢 勝夫, 中村 厚, 大坪 真也 学校法人早稲田大学, テクノスマート株式会社 200903009382720388
Media Coverage
- コロナ肺炎症状の自動診断Date : 2022/04/06Publisher, broadcasting station: わかやま新報Program, newspaper magazine: わかやま新報朝刊6面 Paper
- AI時代を勝ち抜くアイデアが集結。日本青年会議所主催「超生産性向上大賞」に注目Date : 2017/11Writer: Other than myselfPublisher, broadcasting station: リンクタイズ株式会社Program, newspaper magazine: Forbes JAPAN164ページ Paper
- 生物理工学部生命情報工学科が超生産性向上大賞受賞! 内閣総理大臣賞と文部科学大臣賞のダブル受賞Date : 2017/08Writer: Other than myselfPublisher, broadcasting station: 財経新聞Program, newspaper magazine: 財経新聞オンライン版 Paper
- 診断装置開発で意見交換Date : 2014/02Writer: Other than myselfPublisher, broadcasting station: 静岡新聞Program, newspaper magazine: 静岡新聞朝刊23面 Paper
- どんとこい未来技術 「医療、環境分野で着実な実績」 早稲田大学・県立静岡がんセンター 診断数値化 がんを早期発見Date : 2008/09Writer: Other than myselfPublisher, broadcasting station: 株式会社日本経済新聞社Program, newspaper magazine: 日経産業新聞第二部A7面 Paper