Advance

ISHIKAWA Masahiro

    Department of Electronic Engineering and Computer Science　Associate Professor
Last Updated :2024/05/15

Researcher Information

Research funding number

  • 70540417

J-Global ID

Research Interests

  • pattern recognition   Image processing   Spectral Imaging   

Research Areas

  • Informatics / Perceptual information processing

Published Papers

  • Tanwi Biswas; Hiroyuki Suzuki; Masahiro Ishikawa; Naoki Kobayashi; Takashi Obi
    Journal of Biomedical Optics SPIE-Intl Soc Optical Eng 28 (05) 1083-3668 2023/05 [Refereed]
     
    Significance: Quantification of elastic fiber in the tissue specimen is an important aspect of diagnosing different diseases. Though hematoxylin and eosin (H&E) staining is a routinely used and less expensive tissue staining technique, elastic and collagen fibers cannot be differentiated using it. So, in conventional pathology, special staining technique, such as Verhoeff's van Gieson (EVG), is applied physically for this purpose. However, the procedure of EVG staining is very expensive and time-consuming. Aim: The goal of our study is to propose a deep-learning-based computerized method for the generation of RGB EVG stained tissue from hyperspectral H&E stained one to save the time and cost of conventional EVG staining procedure. Approach: H&E stained hyperspectral image and EVG stained RGB whole slide image of human pancreatic tissue have been leveraged for this experiment. CycleGAN-based deep learning model has been proposed for digital stain conversion while images from source and target domains are of different modalities (hyperspectral and RGB) with different channel dimensions. A set of three basis functions have been introduced for calculating one of the losses of the proposed method, which retains the relevant features of EVG stained image within the reduced channel dimension of the H&E stained one. Results: The experimental results showed that a set of three basis functions including linear discriminant function and transmittance spectrum of eosin and hematoxylin better retained the essential properties of the elastic fiber to be discriminated from collagen fiber within the reduced dimension of the hyperspectral H&E stained image. Also, only a smaller number of paired training data with our proposed training method contributed significantly to the generation of more realistic EVG stained image with more precise identification of elastic fiber. Conclusions: RGB EVG stained image is generated from hyperspectral H&E stained image for which our model has performed two types of image conversion simultaneously: hyperspectral to RGB and H&E to EVG. The experimental results show that the intentionally designed set of three basis functions contains more relevant information and prove the effectiveness of our proposed method in generating realistic RGB EVG stained image from hyperspectral H&E stained one. Keywords: H&E stained image; Verhoeff’s van Gieson stained image; digital stain conversion; generative adversarial network; hyperspectral imaging; image-to-image translation.
  • Eleni Aloupogianni; Masahiro Ishikawa; Takaya Ichimura; Mei Hamada; Takuo Murakami; Atsushi Sasaki; Koichiro Nakamura; Naoki Kobayashi; Takashi Obi
    Skin Research and Technology Wiley 29 (2) 0909-752X 2023/02 [Refereed]
     
    Abstract Background Hyperspectral imaging (HSI) is an emerging modality for the gross pathology of the skin. Spectral signatures of HSI could discriminate malignant from benign tissue. Because of inherent redundancies in HSI and in order to facilitate the use of deep‐learning models, dimension reduction is a common preprocessing step. The effects of dimension reduction choice, training scope, and number of retained dimensions have not been evaluated on skin HSI for segmentation tasks. Materials and methods An in‐house dataset of HSI signatures from pigmented skin lesions was prepared and labeled with histology. Eleven different dimension reduction methods were used as preprocessing for tumor margin detection with support vector machines. Cluster‐wise principal component analysis (ClusterPCA), a new variant of PCA, was proposed. The scope of application for dimension reduction was also investigated. Results The components produced by ClusterPCA show good agreement with the expected optical properties of skin chromophores. Random forest importance performed best during classification. However, all methods suffered from low sensitivity and generalization. Conclusion Investigation of more complex reduction and segmentation schemes with emphasis on the nature of HSI and optical properties of the skin is necessary. Insights on dimension reduction for skin tissue could facilitate the development of HSI‐based systems for cancer margin detection at gross level.
  • Eleni Aloupogianni; Takaya Ichimura; Mei Hamada; Masahiro Ishikawa; Takuo Murakami; Atsushi Sasaki; Koichiro Nakamura; Naoki Kobayashi; Takashi Obi
    Journal of Biomedical Optics SPIE-Intl Soc Optical Eng 27 (10) 1083-3668 2022/10 [Refereed]
     
    Abstract Significance: Malignant skin tumors, which include melanoma and nonmelanoma skin cancers, are the most prevalent type of malignant tumor. Gross pathology of pigmented skin lesions (PSL) remains manual, time-consuming, and heavily dependent on the expertise of the medical personnel. Hyperspectral imaging (HSI) can assist in the detection of tumors and evaluate the status of tumor margins by their spectral signatures. Aim: Tumor segmentation of medical HSI data is a research field. The goal of this study is to propose a framework for HSI-based tumor segmentation of PSL. Approach: An HSI dataset of 28 PSL was prepared. Two frameworks for data preprocessing and tumor segmentation were proposed. Models based on machine learning and deep learning were used at the core of each framework. Results: Cross-validation performance showed that pixel-wise processing achieves higher segmentation performance, in terms of the Jaccard coefficient. Simultaneous use of spatio-spectral features produced more comprehensive tumor masks. A three-dimensional Xception-based network achieved performance similar to state-of-the-art networks while allowing for more detailed detection of the tumor border. Conclusions: Good performance was achieved for melanocytic lesions, but margins were difficult to detect in some cases of basal cell carcinoma. The frameworks proposed in this study could be further improved for robustness against different pathologies and detailed delineation of tissue margins to facilitate computer-assisted diagnosis during gross pathology.
  • Yuki Hara; Keita Nagawa; Yuya Yamamoto; Kaiji Inoue; Kazuto Funakoshi; Tsutomu Inoue; Hirokazu Okada; Masahiro Ishikawa; Naoki Kobayashi; Eito Kozawa
    Scientific Reports Springer Science and Business Media LLC 12 (1) 2022/08 
    Abstract We evaluated a multiclass classification model to predict estimated glomerular filtration rate (eGFR) groups in chronic kidney disease (CKD) patients using magnetic resonance imaging (MRI) texture analysis (TA). We identified 166 CKD patients who underwent MRI comprising Dixon-based T1-weighted in-phase (IP)/opposed-phase (OP)/water-only (WO) images, apparent diffusion coefficient (ADC) maps, and T2* maps. The patients were divided into severe, moderate, and control groups based on eGFR borderlines of 30 and 60 mL/min/1.73 m2. After extracting 93 texture features (TFs), dimension reduction was performed using inter-observer reproducibility analysis and sequential feature selection (SFS) algorithm. Models were created using linear discriminant analysis (LDA); support vector machine (SVM) with linear, rbf, and sigmoid kernels; decision tree (DT); and random forest (RF) classifiers, with synthetic minority oversampling technique (SMOTE). Models underwent 100-time repeat nested cross-validation. Overall performances of our classification models were modest, and TA based on T1-weighted IP/OP/WO images provided better performance than those based on ADC and T2* maps. The most favorable result was observed in the T1-weighted WO image using RF classifier and the combination model was derived from all T1-weighted images using SVM classifier with rbf kernel. Among the selected TFs, total energy and energy had weak correlations with eGFR.
  • Hyperspectral and multispectral image processing for gross-level tumor detection in skin lesions: a systematic review
    Eleni Aloupogianni; Masahiro Ishikawa; Naoki Kobayashi; Takashi Obi
    Journal of Biomedical Optics 27 (6) 1 - 28 2022/06 [Refereed]
     
    Abstract Significance: Skin cancer is one of the most prevalent cancers worldwide. In the advent of medical digitization and telepathology, hyper/multispectral imaging (HMSI) allows for noninvasive, nonionizing tissue evaluation at a macroscopic level. Aim: We aim to summarize proposed frameworks and recent trends in HMSI-based classification and segmentation of gross-level skin tissue. Approach: A systematic review was performed, targeting HMSI-based systems for the classification and segmentation of skin lesions during gross pathology, including melanoma, pigmented lesions, and bruises. The review adhered to the 2020 Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. For eligible reports published from 2010 to 2020, trends in HMSI acquisition, preprocessing, and analysis were identified. Results: HMSI-based frameworks for skin tissue classification and segmentation vary greatly. Most reports implemented simple image processing or machine learning, due to small training datasets. Methodologies were evaluated on heavily curated datasets, with the majority targeting melanoma detection. The choice of preprocessing scheme influenced the performance of the system. Some form of dimension reduction is commonly applied to avoid redundancies that are inherent in HMSI systems. Conclusions: To use HMSI for tumor margin detection in practice, the focus of system evaluation should shift toward the explainability and robustness of the decision-making process.
  • Registration of Histopathological Heterogeneous Stained Images Utilizing GAN Based Domain Adaptation Technique
    Tanwi BISWAS; Hiroyuki SUZUKI; Masahiro ISHIKAWA; Naoki KOBAYASHI; Takashi OBI
    IIEEJ Transactions on Image Electronics and Visual Computing 10 (1) 19 - 27 2022/06 [Refereed]
  • Tsutomu Inoue; Eito Kozawa; Masahiro Ishikawa; Naoki Kobayashi; Hirokazu Okada
    Kidney International Elsevier BV 101 (5) 1083 - 1083 0085-2538 2022/05 
    Berchtold et al. reported that corticomedullary differentiation (CMD) abnormality in the apparent diffusion coefficient (ADC) for diffusion-weighted magnetic resonance (MR) imaging affords an index that is significantly correlated with prognosis in chronic kidney disease. 1 We express our gratitude for their kind attention to our previous studies. 2 ,3 The major difference between our study and that of the Berchtold’s group is the setting of the objective variable: we performed multiple regression analysis using the continuous variable, the annual rate of change in estimated glomerular filtration rate (estimated glomerular filtration rate [eGFR] slope; in ml/min per 1.73 m2 per year), as the quantitative objective variable, whereas Berchtold et al. performed Cox proportional analysis using the composite end point of a >30% decline in eGFR or initiation of renal replacement therapy as the qualitative objective variable. The loss of CMD is a feature of images, not only diffusion-weighted images, demonstrating decreased eGFR and correlates with eGFR. 4 Also, from conventional renal MR images, such as T1-weighted images, it is well known that the corticomedullary border is obscured in kidneys with reduced function. The Berchtold’s group reported that CMD abnormality in the ADC was a significant explanatory variable for the end point even after adjustment for eGFR; however, we think it is essential to compare it with other MR images to prove its relation to kidney fibrosis. Whether the significant association between the CMD and the end point set in their article is limited to diffusion-weighted imaging is an important issue to be examined in the future.
  • Masahiro Ishikawa; Tsutomu Inoue; Eito Kozawa; Hirokazu Okada; Naoki Kobayashi
    Journal of Medical Imaging SPIE-Intl Soc Optical Eng 9 (02) 2329-4302 2022/03 
    Abstract Purpose: Nephrologists have empirically predicted renal function from renal morphology. In diagnosing a case of renal dysfunction of unknown course, acute kidney injury and chronic kidney disease are diagnosed from blood tests and an imaging study including magnetic resonance imaging (MRI), and an examination/treatment policy is determined. A framework for the estimation of renal function from water images obtained using the Dixon method is proposed to provide information that helps clinicians reach a diagnosis by accurately estimating renal function on the basis of renal MRI. Approach: The proposed framework consists of four steps. First, the kidney area is extracted by MRI using the Dixon method with a U-net by deep learning. Second, the extracted renal region is registered with the target mask. Third, the kidney features are calculated based on the target mask classification information created by a specialist. Fourth, the estimated glomerular filtration rate (eGFR) representing the renal function is estimated using a regression support vector machine from the calculated features. Results: For the accuracy evaluation, we conducted an experiment to estimate the eGFR when MRI was performed and the eGFR slope, which is the annual rate of decline in eGFR. When the accuracy was evaluated for 165 subjects, the eGFR was estimated to have a root mean square error (RMSE) of 11.99 and a correlation coefficient of 0.83. Moreover, the eGFR slope was estimated to have an RMSE of 4.8 and a correlation coefficient of 0.5. Conclusions: Therefore, the proposed method shows the possibility of estimating the prognosis of renal function based on water images obtained by the Dixon method.
  • Tsutomu Inoue; Eito Kozawa; Masahiro Ishikawa; Daichi Fukaya; Hiroaki Amano; Yusuke Watanabe; Koji Tomori; Naoki Kobayashi; Mamoru Niitsu; Hirokazu Okada
    Scientific Reports Springer Science and Business Media LLC 11 (1) 2021/11 
    Abstract Magnetic resonance imaging (MRI) is playing an increasingly important role in evaluating chronic kidney disease (CKD). It has the potential to be used not only for evaluation of physiological and pathological states, but also for prediction of disease course. Although different MRI sequences have been employed in renal disease, there are few studies that have compared the different sequences. We compared several multiparametric MRI sequences, and compared their results with the estimated glomerular filtration rate. Principal component analysis showed a similarity between T1 values and tissue perfusion (arterial spin labelling), and between fractional anisotropy (diffusion tensor imaging) and apparent diffusion coefficient values (diffusion-weighted imaging). In multiple regression analysis, only T2* values, derived from the blood oxygenation level-dependent (BOLD) MRI sequence, were associated with estimated glomerular filtration rate slope after adjusting for degree of proteinuria, a classic prognostic factor for CKD. In receiver operating characteristic curve analysis, T2* values were a good predictor of rapid deterioration, regardless of the degree of proteinuria. This suggests further study of the use of BOLD-derived T2* values in the workup of CKD, especially to predict the disease course.
  • Tsutomu Inoue; Eito Kozawa; Masahiro Ishikawa; Hirokazu Okada
    Nutrients MDPI AG 13 (6) 2037 - 2037 2021/06 
    Magnetic resonance imaging (MRI) is indispensable in clinical medicine for the morphological and tomographic evaluation of many parenchymal organs. With varied imaging methods, diverse biological information, such as the perfusion volume and measurements of metabolic products, can be obtained. In addition to conventional MRI for morphological assessment, diffusion-weighted MRI/diffusion tensor imaging is used to evaluate white matter structures in the brain; arterial spin labeling is used for cerebral blood flow evaluation; magnetic resonance elastography for fatty liver and cirrhosis evaluation; magnetic resonance spectroscopy for evaluation of metabolites in specific regions of the brain; and blood oxygenation level-dependent imaging for neurological exploration of eating behavior, obesity, and food perception. This range of applications will continue to expand in the future. Nutritional science is a multidisciplinary and all-inclusive field of research; therefore, there are many different applications of MRI. We present a literature review of MRI techniques that can be used to evaluate the nutritional status, particularly in patients on dialysis. We used MEDLINE as the information source, conducted a keyword search in PubMed, and found that, as a nutritional evaluation method, MRI has been used frequently to comprehensively and quantitatively evaluate muscle mass for the determination of body composition.
  • Visual Induced Motion Sickness with Flat Display under Different Ambient Illuminance Conditions
    ◎山下 大岳; 松浦 歩; 石川 雅浩; 小林 直樹
    生体医工学 59 (1) 24 - 30 1881-4379 2021/04 [Refereed]
  • デジタル画像解析を用いたIgA腎症腎生検糸球体病変定量化
    橋口 明典; 石川 雅浩; 城 謙輔; 坂本 直樹; 山内 暁; 大塚 武; 福西 宗憲; 清水 章; 久野 敏; 片渕 律子; 川村 哲也
    日本腎臓学会誌 (一社)日本腎臓学会 62 (4) 317 - 317 0385-2385 2020/07
  • Binary Malignancy Classification of Skin Tissue Using Reflectance and Texture Features from Macropathology Multi-Spectral Images
    Eleni Aloupogianni; Hiroyuki SUZUKI; Takaya ICHIMURA; Atsushi SASAKI; Hiroto YANAGISAWA; Tetsuya TSUCHIDA; Masahiro ISHIKAWA; Naoki KOBAYASHI; Takashi OBI
    IIEEJ Transactions on Image Electronics and Visual Computing Vol. 7 (No. 2) 2019/12 [Refereed]
  • Semi-Automatic Calibration Method for a Bed-Monitoring System Using Infrared Image Depth Sensors
    Hideki Komagata; Erika Kakinuma; Masahiro Ishikawa; Kazuma Shinoda; Naoki Kobayashi
    Sensors MDPI 19 (20) 4581-1 - 4581-20 2019/10 [Refereed]
  • Detection of pancreatic tumor cell nuclei via a hyperspectral analysis of pathological slides based on stain spectra
    Masahiro Ishikawa; Chisato Okamoto; Kazuma Shinoda; Hideki Komagata; Chika Iwamoto; Kenoki Ohuchida; Makoto Hashizume; Akinobu Shimizu; and Naoki Kobayashi
    Biomedical Optics Express The Optical Society 10 (9) 4568 - 4588 2019/09 [Refereed]
     
    Abstract Hyperspectral imaging (HSI) provides more detailed information than red-green-blue (RGB) imaging, and therefore has potential applications in computer-aided pathological diagnosis. This study aimed to develop a pattern recognition method based on HSI, called hyperspectral analysis of pathological slides based on stain spectrum (HAPSS), to detect cancers in hematoxylin and eosin-stained pathological slides of pancreatic tumors. The samples, comprising hyperspectral cubes of 420-750 nm, were harvested for HSI and tissue microarray (TMA) analysis. As a result of conducting HAPSS experiments with a support vector machine (SVM) classifier, we obtained maximal accuracy of 94%, a 14% improvement over the widely used RGB images. Thus, HAPSS is a suitable method to automatically detect tumors in pathological slides of the pancreas.
  • Elastic and collagen fibers discriminant analysis using H&E stained hyperspectral images
    Lina Septiana; Hiroyuki Suzuki; Masahiro Ishikawa; Takashi Obi; Naoki Kobayashi; Nagaaki Ohyama; Takaya Ichimura; Atsushi Sasaki; Erning Wihardjo; Dini Andiani
    Optical Review The Optical Society of Japan 26 (4) 369 - 379 2019/05 [Refereed]
  • Kei Sugiyama; Tsutomu Inoue; Eito Kozawa; Masahiro Ishikawa; Akira Shimada; Naoki Kobayashi; Junji Tanaka; Hirokazu Okada
    Nephrology Dialysis Transplantation Oxford University Press (OUP) 35 (6) 964 - 970 0931-0509 2018/11 
    Abstract Background Although chronic hypoxia and fibrosis may be a key to the progression of chronic kidney disease (CKD), a noninvasive means of measuring these variables is not yet available. Here, using blood oxygen level–dependent (BOLD) and diffusion-weighted (DW) magnetic resonance imaging (MRI), we assessed changes in renal tissue oxygenation and fibrosis, respectively, and evaluated their correlation with prognosis for renal function. Methods The study was conducted under a single-center, longitudinal, retrospective observational design. We examined the prognostic significance of T2* values of BOLD-MRI and apparent diffusion coefficient (ADC) values on DW-MRI and other clinical parameters. The rate of decline in estimated glomerular filtration rate (eGFR) was calculated by linear regression analysis using changes in eGFR during the observation period. Results A total of 91 patients were enrolled, with a mean age of 55.8 ± 15.6 years. Among patients, 51 (56.0%) were males and 38 (41.8%) had diabetes mellitus. The mean eGFR was 49.2 ± 28.9 mL/min/1.73 m2 and the mean observation period was 5.13 years. ADC values of DW-MRI but not T2* values of BOLD-MRI were well correlated with eGFR at the initial time point. The mean annual rate of decline in eGFR during the 5-year observation period was −1.92 ± 3.00 mL/min/1.73 m2. On multiple linear regression analysis, the rate of decline in eGFR was significantly correlated with eGFR at the start point, period average amount of proteinuria and T2* values, but not with ADC values (t = 2.980, P = 0.004). Conclusions Reduced oxygenation as determined by low T2* values on BOLD-MRI is a clinically useful marker of CKD progression.
  • Joint optimization of multispectral filter arrays and demosaicking for pathological images
    Kazuma SHINODA; Maru KAWASE; Madoka HASEGAWA; Masahiro ISHIKAWA; Hideki KOMAGATA; Naoki KOBAYASHI
    IIEEJ Transactions on Image Electronics and Visual Computing The Institute of Image Electronics Engineers of Japan (IIEEJ) 6 (1) 13 - 21 2018/06 [Refereed]
  • Hideki Komagata; Takaya Ichimura; Yasuka Matsuta; Masahiro Ishikawa; Kazuma Shinoda; Naoki Kobayashi; Atsushi Sasaki
    Journal of Medical Imaging SPIE 4 (4) 2329-4310 2017/10 [Refereed]
     
    Cytology, a method of estimating cancer or cellular atypia from microscopic images of scraped specimens, is used according to the pathologist's experience to diagnose cases based on the degree of structural changes and atypia. Several methods of cell feature quantification, including nuclear size, nuclear shape, cytoplasm size, and chromatin texture, have been studied. We focus on chromatin distribution in the cell nucleus and propose new feature values that indicate the chromatin complexity, spreading, and bias, including convex hull ratio on multiple binary images, intensity distribution from the gravity center, and tangential component intensity and texture biases. The characteristics and cellular classification accuracies of the proposed features were verified through experiments using cervical smear samples, for which clear nuclear morphologic diagnostic criteria are available. In this experiment, we also used a stepwise support vector machine to create a machine learning model and a cross-validation algorithm with which to derive identification accuracy. Our results demonstrate the effectiveness of our proposed feature values.
  • Emi Hashimoto; Masahiro Ishikawa; Kazuma Shinoda; Madoka Hasegawa; Hideki Komagata; Naoki Kobayashi; Naoki Mochidome; Yoshinao Oda; Chika Iwamoto; Kenoki Ohuchida; Makoto Hashizume
    MEDICAL IMAGING 2017: DIGITAL PATHOLOGY SPIE-INT SOC OPTICAL ENGINEERING 10140 0277-786X 2017 [Refereed]
     
    In digital pathology diagnosis, accurate recognition and quantification of the tissue structure is an important factor for computer-aided diagnosis. However, the classification accuracy of cytoplasm is low in Hematoxylin and eosin ( HE) stained liver pathology specimens because the RGB color values of cytoplasm are almost similar to that of fibers. In this paper, we propose a new tissue classification method for HE stained liver pathology specimens by using hyperspectral image. At first we select valid spectra from the image to make a clear distinction between fibers and cytoplasm, and then classify five types of tissue based on the bag of features (BoF). The average classification accuracy for all tissues was improved by 11% in the case of using BoF of RGB and selected spectra bands in comparison with using only RGB. In particular, the improvement reached to 24% for fibers and 5% for cytoplasm.
  • Masahiro Ishikawa; Yuri Murakami; Sercan Taha Ahi; Masahiro Yamaguchi; Naoki Kobayashi; Tomoharu Kiyuna; Yoshiko Yamashita; Akira Saito; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    SPIE journal of Medical Imaging SPIE 3 (2) 027502 - 027502 2329-4302 2016/06 [Refereed]
     
    Abstract This paper proposes a digital image analysis method to support quantitative pathology by automatically segmenting the hepatocyte structure and quantifying its morphological features. To structurally analyze histopathological hepatic images, we isolate the trabeculae by extracting the sinusoids, fat droplets, and stromata. We then measure the morphological features of the extracted trabeculae, divide the image into cords, and calculate the feature values of the local cords. We propose a method of calculating the nuclear-cytoplasmic ratio, nuclear density, and number of layers using the local cords. Furthermore, we evaluate the effectiveness of the proposed method using surgical specimens. The proposed method was found to be an effective method for the quantification of the Edmondson grade.
  • Multispectral Filter Array Considering Transparent Wavelength and Arrangement
    柳悠大; 篠田一馬; 長谷川まどか; 加藤茂夫; 石川雅浩; 駒形英樹; 小林直樹
    電子情報通信学会論文誌D 電子情報通信学会 2016/04 [Refereed][Invited]
  • Yudai Yanagi; Kazuma Shinoda; Madoka Hasegawa; Shigeo Kato; Masahiro Ishikawa; Hideki Komagata; Naoki Kobayashi 0009
    Image Processing: Algorithms and Systems XIV Ingenta 1 - 5 2016
  • Shu Ogawa; Kazuma Shinoda; Madoka Hasegawa; Shigeo Kato; Masahiro Ishikawa; Hideki Komagata; Naoki Kobayashi
    IMAGE AND SIGNAL PROCESSING (ICISP 2016) SPRINGER INT PUBLISHING AG 9680 157 - 166 0302-9743 2016 [Refereed]
     
    Multispectral images have been studied in various fields such as remote sensing and sugar content prediction in fruits. One of the systems that captures multispectral images uses a multispectral filter array based on a color filter array. In this system, demosaicking processing is required because the captured multispectral images are mosaicked. However, demosaicking is more difficult for multispectral images than for RGB images owing to the low density between the observed pixels in multispectral images. Therefore, we propose a demosaicking method for multispectral images based on spatial gradient and inter-channel correlation. Experimental results demonstrate that our proposed method outperforms the existing methods and is effective.
  • Feature Analyses of Trabecular Pattern of Hepatocellular Carcinoma Using Graph Structure
    Hideki Komagata; Masahiro Ishikawa; Naoki Kobayashi; Kazuma Shinoda; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    IIEEJ(The Institute of Image Electronics Engineers of Japan) 2015/12 [Refereed]
  • M. A. Aziz; H. Kanazawa; Y. Murakami; F. Kimura; M. Yamaguchi; T. Kiyuna; Y. Yamashita; A. Saito; M. Ishikawa; N. Kobayashi; T. Abe; A. Hashiguchi
    Analytical Cellular Pathology Hindawi Limited 2014 1 - 2 2210-7177 2015/06 [Refereed]
  • Kazuma Shinoda; Naoki Kobayashi; Ayako Katoh; Hideki Komagata; Masahiro Ishikawa; Yuri Murakami; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG E98A (4) 1006 - 1020 1745-1337 2015/04 [Refereed]
     
    Region of interest (ROI) coding is a useful function for many applications. JPEG2000 supports ROI coding and can decode ROIs preferentially regardless of the shape and number of the regions. However, if the number of regions is quite large, the ROI coding performance of JPEG2000 declines because the code-stream includes many useless non-ROI codes. This paper proposes a wavelet-based ROI coding method suited for multiple ROIs. The proposed wavelet transform does not access any non-ROIs when transforming the ROIs. Additionally, the proposed method eliminates the need for unnecessary coding of the bits in the higher bit planes of non-ROI regions by adding an ROI map to the code-stream. The experimental results show that the proposed method achieves a higher peak signal-to-noise ratio than the ROI coding of JPEG2000. The proposed method can be applied to both max-shift and scaling-based ROI coding.
  • Masahiro Ishikawa; Naoki Kobayashi; Hideki Komagata; Kazuma Shinoda; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    Progress in Biomedical Optics and Imaging - Proceedings of SPIE SPIE 9420 1605-7422 2015 [Refereed]
     
    The steatosis in liver pathological tissue images is a promising indicator of nonalcoholic fatty liver disease (NAFLD) and the possible risk of hepatocellular carcinoma (HCC). The resulting values are also important for ensuring the automatic and accurate classification of HCC images, because the existence of many fat droplets is likely to create errors in quantifying the morphological features used in the process. In this study we propose a method that can automatically detect, and exclude regions with many fat droplets by using the feature values of colors, shapes and the arrangement of cell nuclei. We implement the method and confirm that it can accurately detect fat droplets and quantify the fat droplet ratio of actual images. This investigation also clarifies the effective characteristics that contribute to accurate detection.
  • Masahiro Ishikawa; Naoki Kobayashi; Hideki Komagata; Kazuma Shinoda; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    MEDICAL IMAGING 2015: DIGITAL PATHOLOGY SPIE-INT SOC OPTICAL ENGINEERING 9420 0277-786X 2015 [Refereed]
     
    The steatosis in liver pathological tissue images is a promising indicator of nonalcoholic fatty liver disease (NAFLD) and the possible risk of hepatocellular carcinoma (HCC). The resulting values are also important for ensuring the automatic and accurate classification of HCC images, because the existence of many fat droplets is likely to create errors in quantifying the morphological features used in the process. In this study we propose a method that can automatically detect, and exclude regions with many fat droplets by using the feature values of colors, shapes and the arrangement of cell nuclei. We implement the method and confirm that it can accurately detect fat droplets and quantify the fat droplet ratio of actual images. This investigation also clarifies the effective characteristics that contribute to accurate detection.
  • Kazuma Shinoda; Shu Ogawa; Yudai Yanagi; Madoka Hasegawa; Shigeo Kato; Masahiro Ishikawa; Hideki Komagata; Naoki Kobayashi
    2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA) IEEE 697 - 703 2015 [Refereed]
     
    A single-shot multispectral camera equipped with a filter array has the potential to promote a fast and low-cost multispectral imaging system. We focus on the design of a multispectral filter array and demosaicking in this paper and propose a pathology-specific multispectral imaging system. The spectral sensitivities and patterns of the filter array are optimized by using training data of real pathological tissues. The mosaicked image is demosaicked by considering the designed filter array. We show the effectiveness of the proposed imaging system by comparing the recovered spectrum and RGB image with conventional methods.
  • Yamashita, Yoshiko; Kiyuna, Tomoharu; Sakamoto, Michiie; Hashiguchi, Akinori; Ishikawa, Masahiro; Murakami, Yuri; Yamaguchi, Masahiro
    ANALYTICAL CELLULAR PATHOLOGY 774 - 779 2210-7177 2014
  • Segmentation of Sinusoids in Hematoxylin and Eosin Stained Liver Specimens Using an Orientation-Selective Filter
    Masahiro Ishikawa; Sercan Taha Ahi; Fumikazu Kimura; Masahiro Yamaguchi; Hiroshi Nagahashi; Akinori Hashiguchi; Michiie Sakamoto
    Open journal of medical imaging vol.3 (No.4) pp.144-155  2013/12 [Refereed]
  • Masahiro Ishikawa; Sercan Taha Ahi; Yuri Murakami; Fumikazu Kimura; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    Progress in Biomedical Optics and Imaging - Proceedings of SPIE 8676 1605-7422 2013 [Refereed]
     
    The analysis of hepatic tissue structure is required for quantitative assessment of liver histology. Especially, a cord-like structure of liver cells, called trabecura, has important information in the diagnosis of hepatocellular carcinoma (HCC). However, the extraction of trabeculae is thought to be difficult because liver cells take on various colors and appearances depending on tissue conditions. In this paper, we propose an approach to extract trabeculae from images of hematoxyline and eosin stained liver tissue slide by extracting the rest of trabeculae: sinusoids and stromal area. The sinusoids are simply extracted based on the color information, where the image is corrected by an orientation selective filtering before segmentaion. The stromal area mainly consists of fiber, and often includes lymphocytes densely. Therefore, in the proposed method, fiber region and lymphocytes are extracted separately, then, stromal region is determined based on the extracted results. The determination of stroma is performed based on superpixels, to obtain precise boundaries. Once the regions of sinusoids and stroma are obtained, trabeculae can be segmented as the remaining region. The proposed method was applied to 10 test images of normal and HCC liver tissues, and the results were evaluated based on the manual segmentation. As a result, we confirmed that both sensitivity and specificity of the extraction of trabeculae reach around 90%. © 2013 SPIE.
  • Hideki Komagata; Naoki Kobayashi; Ayako Katoh; Yasuka Ohnuki; Masahiro Ishikawa; Kazuma Shinoda; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    Progress in Biomedical Optics and Imaging - Proceedings of SPIE 8676 1605-7422 2013 [Refereed]
     
    Recent advances in information technology have improved pathological virtual-slide technology and diagnostic support system studies of pathological images. Diagnostic support systems utilize quantitative indices determined by image processing. In previous studies on diagnostic support systems, carcinomatous areas of breast or lung have been recognized by the feature quantities of nuclear sizes, complexities, and internuclear distances based on graph theory, among other features. Improving recognition accuracy is important for the addition of new feature quantities. We focused on hepatocellular carcinoma (HCC) and investigated new feature quantities of histological images of HCC. One of the most important histological features of HCC is the trabecular pattern. For diagnosing cancer, it is important to recognize the tumor cell trabeculae. We propose a new algorithm for calculating the number of cell layers in histological images of HCC in tissue sections stained by hematoxylin and eosin. For the calculation, we used a Delaunay diagram that was based on the median points of nuclei, deleted the sinusoid and fat droplet regions from the Delaunay diagram, and counted the Delaunay lines while applying a thinning algorithm. Moreover, we experimented with the calculation of the number of cell layers with our method for different histological grades of HCC. The number of cell layers discriminated tumor differentiations and Edmondson grades therefore, our algorithm may serve as an index of HCC for diagnostic support systems. © 2013 SPIE.
  • Masahiro Ishikawa; Sercan Taha Ahi; Yuri Murakami; Fumikazu Kimura; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    MEDICAL IMAGING 2013: DIGITAL PATHOLOGY SPIE-INT SOC OPTICAL ENGINEERING 8676 0277-786X 2013 [Refereed]
     
    The analysis of hepatic tissue structure is required for quantitative assessment of liver histology. Especially, a cord-like structure of liver cells, called trabecura, has important information in the diagnosis of hepatocellular carcinoma (HCC). However, the extraction of trabeculae is thought to be difficult because liver cells take on various colors and appearances depending on tissue conditions. In this paper, we propose an approach to extract trabeculae from images of hematoxyline and eosin stained liver tissue slide by extracting the rest of trabeculae: sinusoids and stromal area. The sinusoids are simply extracted based on the color information, where the image is corrected by an orientation selective filtering before segmentaion. The stromal area mainly consists of fiber, and often includes lymphocytes densely. Therefore, in the proposed method, fiber region and lymphocytes are extracted separately, then, stromal region is determined based on the extracted results. The determination of stroma is performed based on superpixels, to obtain precise boundaries. Once the regions of sinusoids and stroma are obtained, trabeculae can be segmented as the remaining region. The proposed method was applied to 10 test images of normal and HCC liver tissues, and the results were evaluated based on the manual segmentation. As a result, we confirmed that both sensitivity and specificity of the extraction of trabeculae reach around 90%.
  • Hideki Komagata; Naoki Kobayashi; Ayako Katoh; Yasuka Ohnuki; Masahiro Ishikawa; Kazuma Shinoda; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    MEDICAL IMAGING 2013: DIGITAL PATHOLOGY SPIE-INT SOC OPTICAL ENGINEERING 8676 0277-786X 2013 [Refereed]
     
    Recent advances in information technology have improved pathological virtual-slide technology and diagnostic support system studies of pathological images. Diagnostic support systems utilize quantitative indices determined by image processing. In previous studies on diagnostic support systems, carcinomatous areas of breast or lung have been recognized by the feature quantities of nuclear sizes, complexities, and internuclear distances based on graph theory, among other features. Improving recognition accuracy is important for the addition of new feature quantities. We focused on hepatocellular carcinoma (HCC) and investigated new feature quantities of histological images of HCC. One of the most important histological features of HCC is the trabecular pattern. For diagnosing cancer, it is important to recognize the tumor cell trabeculae. We propose a new algorithm for calculating the number of cell layers in histological images of HCC in tissue sections stained by hematoxylin and eosin. For the calculation, we used a Delaunay diagram that was based on the median points of nuclei, deleted the sinusoid and fat droplet regions from the Delaunay diagram, and counted the Delaunay lines while applying a thinning algorithm. Moreover, we experimented with the calculation of the number of cell layers with our method for different histological grades of HCC. The number of cell layers discriminated tumor differentiations and Edmondson grades; therefore, our algorithm may serve as an index of HCC for diagnostic support systems.
  • White matter alteration in idiopathic normal pressure hydrocephalus:tract-based spatial statistics study
    T. Hattori; K. Ito; S. Aoki; T. Yuasa; R. Sato; M. Ishikawa; H. Sawaura; M. Hori; H. Mizusawa
    2012/10 [Refereed]
  • ISHIKAWA Masahiro; UCHIDA Hidaka; MAEDA Yoshinobu; YAMAMOTO Masanobu; IGARASHI Masato; SUDA Takeshi; NOMOTO Minoru; AOYAGI Yutaka
    Medical Imaging and Information Sciences MEDICAL IMAGING AND INFORMATION SCIENCES 23 (5) 130 - 135 0910-1543 2006/06 [Refereed]
     
    Chronic liver disease causes health problem such as hepatic failure or hepatocellular carcinoma. As the disease progresses, some fibroses become apparent, and, as such, influence a vascular structure. We have proposed, previously, a method to extract various vascular features from CTAP images. In this paper we suggested that the method improved in this paper should be applicable to CTAP images of 9 patients. It reveals that the vascular-structure analysis can be useful for estimating liver fibrosis level.
  • ISHIKAWA Masahiro; UCHIDA Hidaka; TAMAKI Toru; YAMAMOTO Masanobu; IGARASHI Masato; SUDA Takeshi; AOYAGI Yutaka
    Medical Imaging and Information Sciences MEDICAL IMAGING AND INFORMATION SCIENCES 22 (3) 210 - 219 0910-1543 2005 [Refereed]
     
    Liver cirrhosis is usually diagnosed with histological findings of liver biopsy sample. However, liver biopsy, sampling liver tissues from a living donor, is an invasive technique, in which a direct puncture of the liver is needed. On the other hand, higher resolution of recent computed tomography(CT) has a potential to replace histology with objective and digital images, which are available without any invasive techniques. Here we present a system extracting various features of three-dimensional vasculature in the liver from images of CT aiming an objective and noninvasive diagnosis of liver cirrhosis.

Books etc

  • ,Annual Review 2016
    井上勉; 小澤栄人; 石川雅浩; 岡田浩一 中外医学社 2016/01
  • Annual Review 2016
    井上勉; 小澤栄人; 石川雅浩; 岡田浩一 中外医学社 2016/01
  • 「情報機器操作入門－らくらくパソコン活用術－」
    山本 正信,三河 賢治,山本 瑞恵,石川 雅浩6番目 学術図書出版社 2007/04 
    大学生活に必要なコンピュータの基礎知識に関する書籍。その中で、メールの受信や送信についての章を記載。
  • 情報機器操作入門－らくらくパソコン活用術－
    山本 正信; 三河 賢治; 山本 瑞恵; 石川 雅浩; 目 学術図書出版社 2007/04 
    大学生活に必要なコンピュータの基礎知識に関する書籍。その中で、メールの受信や送信についての章を記載。

Conference Activities & Talks

  • ハイパースペクトル画像を用いたki-67陽性核推定法の開発
    石川 雅浩; 吉田 結真; 中野 夏澄; 黒田 真代; 茅野 秀一; 小林 直樹
    第50回画像電子学会年次大会  2022/08
  • 病理標本解析のための可視・近赤外ハイパースペクトル画像統合システムの開発
    中村 駿; 石川 雅浩; 小林 直樹
    第50回画像電子学会年次大会  2022/08
  • マルチスペクトル画像を用いたマクロ病理解析法の一手法  [Not invited]
    ◎山崎 滉仁; 石川 雅浩; 市村 隆也; 浜田 芽衣; 佐々木 惇; 村上 拓生; 竹治 真明; 常深 祐一郎; 中村 晃一郎; 小尾 高史; エレニ アロポジアンニ; 小林 直樹
    第50回画像電子学会年次大会  2022/08
  • Exploratory Data Analysis on Hyper-spectral Images of Pigmented Skin Lesions  [Not invited]
    Eleni ALOUPOGIANNI; Takaya ICHIMURA; Mei HAMADA; Takuo MURAKAMI; Atsushi SASAKI; Koichiro NAKAMURA; Masahiro ISHIKAWA; Naoki KOBAYASHI; Takashi OBI
    第41回日本医用画像工学会大会  2022/07
  • Design of a Hyper-Spectral Imaging System for Gross Pathology of Pigmented Skin Lesions  [Not invited]
    Eleni Aloupogianni; Masahiro Ishikawa; Takaya Ichimura; Atsushi Sasaki; Naoki Kobayashi; Takashi Obi
    43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society  2021/11  online
  • Registration of Histopathological Heterogeneous Stained Images Utilizing Gan Based Domain Adaptation Technique  [Not invited]
    Tanwi Biswas; Hiroyuki Suzuki; Masahiro Ishikawa; Naoki Kobayashi; Takashi Obi
    The 7th IIEEJ International Conference on Image Electronics and Visual Computing  2021/09  online
  • 濃度共起行列を用いた腎機能推定法の検討  [Not invited]
    ◎金子 夏実; 石川 雅浩; 井上 勉; 小澤 栄人; 岡田 浩一; 小林 直樹
    画像電子学会 第295回研究会  2021/02  オンライン開催
  • Effect of formalin fixing on chromophore saliency maps derived from multi-spectral macropathology skin images  [Not invited]
    Eleni Aloupogianni; Hiroyuki Suzuki; Takaya Ichimura; Atsushi Sasaki; Hiroto Yanagisawa; Tetsuya Tsuchida; Masahiro Ishikawa; Naoki Kobayashi; Takashi Obi
    Medical Imaging 2021: Digital Pathology  2021/02  San Diego, California, United States (online)
  • Binary Malignancy Classification of Skin Tissue using Reflectance and Texture Features from Macropathology Multi-Spectral Images  [Not invited]
    ◎Takashi OBI; Eleni ALOUPOGIANNI; Hiroyuki SUZUKI; Takaya ICHIMURA; Atsushi SASAKI; Hiroto YANAGISAWA; Tetsuya TSUCHIDA; Masahiro ISHIKAWA; Naoki KOBAYASHI
    International Joint Symposium 2020 The 15th International Workshop on Biomaterials in Interface Science and The 11th Symposium on Innovative Dental-Engineering Alliance (IDEA)  2020/12  online
  • Conversion of H&E Stained to EVG Stained Histological Images using CycleGAN  [Not invited]
    ◎Tanwi BISWAS; Hiroyuki SUZUKI; Masahiro ISHIKAWA; Naoki KOBAYASHI; Takashi OBI
    第39回日本医用画像工学会大会  2020/09  オンライン開催
  • スペクトル情報と色補正を用いた肝病理標本画像の組織分類  [Not invited]
    橋本 江美; 石川 雅浩; 篠田 一馬; 長谷川 まどか; 駒形 英樹; 小林 直樹; 持留 直樹; 岩本 千佳; 大内田 研宙; 小田 義直; 橋爪 誠
    2017/05
  • Fundamental Technologies for Integration of Multiscale Spatiotemporal Morphology in Multidisciplinary Computational Anatomy - Progress Overview FY2016 -  [Not invited]
    ◎Akinobu Shimizu; Shigeru Nawano; Iwao Hasegawa; Naoki Kobayashi; Hayaru Shono; Atsushi Saito; Hideki Komagata; (Masahiro Ishikawa); Kazuma Shinoda; Marius Linguraru
    The 3rd International Symposium on Multidisciplinary Computational Anatomy  2017/03
  • 3D reconstruction of pancreatic ducts and collagen fibers from pathological images of pancreas serial sections  [Not invited]
    ◎Hideki Komagata; (Masahiro Ishikawa); Kazuma Shinoda; Naoki Kobayashi; Chika Iwamoto; Kenoki Ohuchida; and Makoto Hashizume
    Image Electronics and Visual Computing Workshop (IEVC)  2017/03
  • Extraction of glomerulus in whole slide imaging of kidney biopsy specimens  [Not invited]
    ◎(M.Ishikawa); T.Abe; A.Hashiguchi; M.Sakamoto; N.Kobayashi
    SPIE Medical Imaging 2017  2017/02
  • Tissue classification of liver pathological tissue specimens image using spectral features  [Not invited]
    ◎E.Hashimoto; (M.Ishikawa); K.Shinoda; M.Hasegawa; H.Komagata; N.Kobayashi; N.Mochidome; Y.Oda; K.Ohuchida; M.Hashizume; C.Iwamoto
    SPIE Medical Imaging  2017/02
  • T2* values in blood oxygen level-dependent MRI may predict prognosis in chronic kidney disease  [Not invited]
    ◎Kei Sugiyama; Tsutomu Inoue; Eiso Kozawa; (Masahiro Ishikawa); Hiroaki Amano; Takeru Kusano; Naoki Kobayashi; Hirokazu Okada
    American Society of Nephrology  2016/11
  • Demosaicking Method for Multispectral Images Based on Spatial Gradient and Inter-channel Correlation  [Not invited]
    ◎Shu Ogawa; Kazuma Shinoda; Madoka Hasegawa; Shigeo Kato; (Masahiro Ishikawa); Hideki Komagata; Naoki Kobayashi
    MSC2016  2016/09  Bueno Aires, Argentina  IEEE
  • 腎functional MRIは慢性腎臓病の腎機能予後を予測する  [Not invited]
    ◎杉山圭; 井上勉; 小澤栄人; (石川雅浩); 田中淳司; 小林直樹; 高根裕史; 友利浩司; 瀬戸建; 小野淳; 天野博明; 伊藤悠人; 岡田浩一
    第59回 日本腎臓学会学術総会  2016/06
  • マルチスペクトル画像を使用した肝病理組織標本の組織分類の検討  [Not invited]
    ◎橋本江美; (石川雅浩); 篠田一馬; 長谷川まどか; 加藤茂夫; 駒形英樹; 小林直樹
    2016年 電子情報通信学会総合大会 情報・システム講演論文集2  2016/03  九州大学  電子情報通信学会
  • マルチスペクトル画像による色素量補正を用いたHE染色肝病理画像中の構造認識  [Not invited]
    ◎(石川雅浩); 橋本江美; 篠田一馬; 長谷川まどか; 加藤茂夫; 駒形英樹; 小林直樹
    2016年 電子情報通信学会総合大会 情報・システム講演論文集2  2016/03  九州大学  電子情報通信学会
  • Apparent diffusion coefficient values of diffusion-weighted magnetic resonance images could predict the prognosis for chronic kidney disease  [Not invited]
    ◎Kei Sugiyama; Tsutomu Inoue; Eito Kozawa; (Masahiro Ishikawa); Naoki Kobayashi; Junji Tanaka; and Hirokazu Okada
    第5回CKD-Frontier  2016/02
  • Kidney ADC values of diffusion-weighted MRI predict prognosis of CKD  [Not invited]
    ◎Kei Sugiyama; Tsutomu Inoue; Eito Kozawa; (Masahiro Ishikawa); Naoki Kobayashi; Junji Tnaka; Hirokazu Okada
    2016/02
  • Fundamental Technologies for Integration of Multiscale Spatiotemporal Morphology in Multidisciplinary Computational Anatomy - Plan of Five Years and Progress Overview FY2015 -  [Not invited]
    ◎Akinobu Shimizu; Iwao Hasegawa; Naoki Kobayashi; Hayaru Shono; Shigeru Nawano; Issei Sato; Hideki Komagata; (Masahiro Ishikawa); and Kazuma Shinoda
    2016/02
  • Optimal transparent wavelength and arrangement for multispectral filter array  [Not invited]
    ◎Yudai Yanagi; Kazuma Shinoda; Madoka Hasegawa; Shigeo Kato; (Masahiro Ishikawa); Hideki Komagata; and Naoki Kobayashi
    IS&T International Symposium on Electronic Imaging  2016/02
  • EVG染色病理画像における糸球体構造認識  [Not invited]
    ◎(石川雅浩); 本田夏樹; 阿部時也; 橋口明典; 小林直樹
    第１２回 日本病理学会カンファレンス  2015/07
  • 自動コロニーカウント機能付き透析液清 浄化支援システムの使用評価  [Not invited]
    ◎知久 大輝; (石川 雅浩); 川邉 学; 小林 直樹; 小林 祐子; 藤江 遼平; 本多 仁; 大濱 和也; 高根 裕史; 岡田 浩一,
    2015/05
  • 機能的MRI(magnetic resonance imaging)を用いた慢性腎臓病評価法の検討  [Not invited]
    ◎井上 勉; 小澤 栄人; (石川 雅浩); 高根 裕史; 友利 浩司; 小林 直樹; 田中 淳 司; 鈴木 洋通; 岡田 浩一,
    2015/04
  • 腎生検画像における糸球体構造認識  [Not invited]
    ◎(石川雅浩),渡邊すみれ,阿部時也,橋口明典,小林直樹
    医用画像情報学会  2015/02
  • 3テスラMRIによるASL(arterial spin labeling)を用いた腎灌流量の評価  [Not invited]
    ◎井上 勉; 小澤 栄人; (石川 雅浩); 菊田 知宏; 渡辺 裕輔; 高根 裕史; 小林 直 樹; 鈴木 洋通; 岡田 浩一,
    2015/02
  • An accurate extracting method of fat droplets in liver images for quantitative evaluation  [Not invited]
    (M. Ishikawa); N. Kobayashi; H. Komagata; K. Shinoda; M. Yamaguchi; T. Abe; A. Hashiguchi; M. Sakamoto
    SPIE Medical Imaging  2015/02
  • AUTOMATIC DETECTION OF UNUSUAL ALIGNED NUCLEI ON HCC HISTOPATHOLOGICAL IMAGES  [Not invited]
    H. Komagata; N. Kobayashi; (M. Ishikawa); M. Yamaguchi; T. Kiyuna; A. Saito; T. Abe; A. Hashiguchi; M. Sakamoto
    The 4th IIEEJ International Workshop(IEVC2014)  2014/10
  • Development of a Prototype for Hepatocellular Carcinoma Classification based on Morphological Features Automatically Measured in Whole Slide Images  [Not invited]
    Y. Yamashita; T. Kiyuna; M. Sakamoto; A. Hashiguchi; (M. Ishikawa); Y. Murakami; M. Yamaguchi
    2nd International Congress of the International Academy of Digital Pathology(IADP)  2014/10
  • Enhancing Automatic Classification of Hepatocellular Carcinoma Images through Image Masking, Tissue Changes, and Trabecular Features  [Not invited]
    M. A. Aziz; H. Kanazawa; Y. Murakami; F. Kimura; M. Yamaguchi; T. Kiyuna; Y. Yamashita; A. Saito; (M. Ishikawa); N. Kobayashi; T. Abe; A. Hashiguchi
    2nd International Congress of the International Academy of Digital Pathology(IADP)  2014/10
  • Color Processing in Pathology Image Analysis System for Liver Biopsy  [Not invited]
    Y. Murakami; M. Yamaguchi; T. Abe; A. Hashiguchi; Y. Yamashita; A. Saito; (M. Ishikawa); N. Kobayashi; M. Sakamoto
    22nd Color and Imaging Conference(CIC22)  2014/10
  • HE染色肝病理標本における組織構造定量化によるコンピュータ診断支援  [Invited]
    ◎(石川 雅浩),坂本 享宇,橋口 明典,山口 雅浩,小林 直樹,村上 百合,齋藤 彰
    第15回情報フォトニクス研究グループ研究会  2014/09
  • HE染色肝病理標本における組織構造定量化によるがん検出精度向上の検討  [Not invited]
    ◎(石川 雅浩),藤田 悠介,Maulana Abdul Aziz,村上 百合,山口 雅浩,小林 直樹,喜友名 朝春,齋藤 彰,阿部 時也,橋口 明典,坂元 亨宇
    第33回 日本医用画像工学会大会  2014/07
  • A study of eccentric quantitation approach for chromatin distribution in cytodiagnosis  [Not invited]
    ◎駒形 英樹; 大貫 泰佳; (石川 雅浩); 小林 直樹; 市村 隆也; 後藤 義也; 清水 道生(埼玉医科大学)
    The institute of image electronics engineers of japan in hiroshima  2014/06  東京都新宿区
  • A Study of Appropriate Task Stressors forMental Stress Assessment Using Bio-signals  [Not invited]
    ◎N. Kobayashi; N. Ohta; (M. Ishikawa); T. Furusawa
    日本生医工学会大会  2014/06
  • Development of viable cell count technology for cleanliness of dialysis fluid  [Not invited]
    ◎(石川 雅浩); 川邊 学; 駒形 英樹; 加納 隆; 小林 直樹(埼玉医科大学)
    The institute of image electronics engineers of japan in hiroshima  2014/02  広島県広島市
  • High speed algorithm to calculate feature quantities of nuclei graph structures in hepatic histological images  [Not invited]
    ◎駒形英樹; 小林直樹; (石川雅浩); 篠田一馬; 山口雅浩; 阿部時也; 橋口明典; 坂元亨宇
    JAMIT Frontier 2014  2014/01  沖縄県那覇市
  • A method to extract fat drops from liver biopsy image using machine learning algorithm  [Not invited]
    ◎(石川雅浩); 小林直樹; 駒形英樹; 山口雅浩; 阿部時也; 橋口明典; 坂元亨宇
    JAMIT Frontier 2014  2014/01  沖縄県那覇市
  • HE染色肝病理組織標本における索状構造の配列の乱れ定量化法の提案  [Not invited]
    ◎(石川 雅浩); 福井智也; 藤田悠介; 村上百合; 山口雅浩; 阿部時也; 橋口明典; 坂本亨宇; 齋藤彰
    日本医用画像工学会 大会  2013/08
  • Automatic segmentation of hepatocellular structure from HE-stained liver tissue  [Not invited]
    ◎(MasahiroIshikawa); Sercan Taha Ahi; Yuri Murakami; Fumikazu Kimura; Masahiro Yamaguchi; Tokiya Abe; Akinori Hashiguchi; Michiie Sakamoto
    SPIE Medical Imaging 2013: Digital Pathology  2013/02
  • 肝病理組織における索状構造解析のための形態的特徴の自動計測  [Not invited]
    ◎(石川雅浩); 福井智也; 村上百合; 山口雅浩; 阿部時也; 橋口明典; 坂元亨宇
    電子情報通信学会 医用画像研究会  2013/01  沖縄

MISC

Industrial Property Rights

  • 特願2017-165001:画像処理装置、画像処理方法、画像処理プログラム  2017年/08/30
    石川雅浩, 小林直樹, 中野和也
  • 特開2015-154718(P2015-154718A):自動コロニー数カウント法、自動コロニー数カウントプログラム  2015/08/27
    石川雅浩, 川邉学, 小林直樹, 加納隆, 駒形英樹  埼玉医科大学

Awards & Honors

  • 2022/06 画像電子学会 優秀論文賞
  • 2017/03 IEVC IEVC2017 Best Paper Award
     JPN international_society
  • 2015/02 SPIE Medical Imaging(CUMU LAUDE)
     USA international_society
  • 2014/09 IEVC2014 Best Paper Award
     THA international_society
  • 2013/12 日本医用画像工学会 大会奨励賞
     JPN
  • 2013/05 MI研究奨励賞(電子情報通信学会 医用画像研究会)
     JPN
  • 2013/02 Poster Award Honorable mention(SPIE Medical Imaging 2013)
  • 2005/06 金森奨励賞(医用画像情報学会)
     JPN

Research Grants & Projects

  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Young Scientists (B)
    Date (from‐to) : 2017/04 - Today 
    Author : Masahiro Ishikawa
     
    This study attempted to develop an unstained specimen digital staining method for use with autofluorescent images. After determining an autofluorescent image suitable for digital staining, the autofluorescent image and stain image were aligned and digital staining could be implemented using deep learning. However, the study also found that autofluorescence cannot be confirmed for some cell nuclei, proving that further technique improvements will be required in the future.
  • IgA腎症予後分類のブラッシュアップのための前向きコホート研究の推進とハイリスク患者の透析移行を阻止する治療法の開発
    AMED：
    Date (from‐to) : 2017/04 - Today 
    Author : 石川雅浩
  • スーパーピクセルを用いた病理画像中の構造認識法の開発
    日本私立学校振興・共済事業団：
    Date (from‐to) : 2015/04 - Today 
    Author : 石川雅浩
  • がん超早期診断・治療機器の総合研究開発
    独立行政法人 新エネルギー・産業技術総合開発機構：
    Date (from‐to) : 2013/04 - Today
  • 日本学術振興会：科学研究費助成事業 基盤研究(B)
    Date (from‐to) : 2023/04 -2028/03 
    Author : 石川 雅浩; 中野和也; 橋口明典; 山口雅浩
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Research (Exploratory)
    Date (from‐to) : 2021/07 -2024/03 
    Author : 石川 雅浩; 鈴木 賢治; 小林 直樹; 橋口 明典
  • 腎functional MRIとAIによる慢性腎臓病の進行リスク評価システムの構築
    AMED：
    Date (from‐to) : 2019/04 - Today
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
    Date (from‐to) : 2014/07 -2019/03 
    Author : Shimizu Akinobu; SAITO atsushi; LINGURARU George, Marius; SHINODA kazuma; KOMAGATA hideki; ISHIKAWA masahiro
     
    Main research achievements are summarized as follows. First we proposed several methods to construct a spatio-temporal statistical model of time series data, such as statistical parameter estimation from a small sample data, modeling with smoothness constraint along a time axis, modeling with nested and neighboring constraints, and modeling of organs with topological changes along a time axis. These methods were used to construct spatio-temporal models of human embryos and children. Secondly, we proposed super-resolution techniques using dictionary learning and deep learning, and applied them to a CT volume. Third we reconstructed 3D tissue structure from pathological images using machine learning techniques. Fourth, hyper-spectral image processing of pathological images was conducted to improve accuracy in tissue classification. Fifth, we proposed a simultaneous optimization algorithm of segmentation and a statistical model, and used for organ recognition of a CT volume.
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Young Scientists (B)
    Date (from‐to) : 2015/04 -2018/03 
    Author : Ishikawa Masahiro; Tokiya Abe
     
    This study aimed to develop a function estimation method using structure recognition in transplanted renal pathology tissue images and machine learning. By targeting whole slide images, we determined the cortex and medullary regions in a transplanted renal pathology specimen, extracted the glomerulus, and developed a quantification method for the number of peripheral fibers. We also examined a structure recognition method using spectral images, which proved that it could recognize the organization structure more accurately than conventional methods using the RGB value. Finally, we estimated the transplant renal functions with clinical data , which showed the possibility that this method can estimate the functions at a maximum accuracy of 85%.
  • 清浄化予測機能付き透析液管理システムの開発
    研究成果最適展開支援プログラム（A-STEP）探索タイプ：
    Date (from‐to) : 2014/12 -2015/03 
    Author : 石川雅浩

Other link

researchmap


Copyright © MEDIA FUSION Co.,Ltd. All rights reserved.