Prof. Naoki Kobayashi Profile

Prof. Naoki Kobayashi

Professor at Saitama Medical Univ

SPIE Involvement:

Author

Publications (12)

SPIE Journal Paper | 31 May 2023 Open Access

Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image

Tanwi Biswas, Hiroyuki Suzuki, Masahiro Ishikawa, Naoki Kobayashi, Takashi Obi

JBO, Vol. 28, Issue 05, 056501, (May 2023) https://doi.org/10.1117/12.10.1117/1.JBO.28.5.056501

KEYWORDS: Hyperspectral imaging, RGB color model, Elasticity, Education and training, Tissues, Image quality, Collagen, Digital imaging, Data modeling, Data conversion

Read Abstract +

SignificanceQuantification 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.AimThe 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.ApproachH&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.ResultsThe 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.ConclusionsRGB 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.

DOWNLOAD PAPER

Proceedings Article | 7 April 2023 Presentation + Paper

Generation of RGB EVG stained image from hyperspectral H&E stained image using generative adversarial network (GAN)

Tanwi Biswas, Hiroyuki Suzuki, Masahiro Ishikawa, Naoki Kobayashi, Takashi Obi

Proceedings Volume 12471, 124710D (2023) https://doi.org/10.1117/12.2653491

KEYWORDS: Hyperspectral imaging, Tissues, Histopathology, Deep learning, Image processing

Read Abstract +

SPIE Journal Paper | 31 October 2022 Open Access

Hyperspectral imaging for tumor segmentation on pigmented skin lesions

Eleni Aloupogianni, Takaya Ichimura, Mei Hamada, Masahiro Ishikawa, Takuo Murakami, Atsushi Sasaki, Koichiro Nakamura, Naoki Kobayashi, Takashi Obi

JBO, Vol. 27, Issue 10, 106007, (October 2022) https://doi.org/10.1117/12.10.1117/1.JBO.27.10.106007

KEYWORDS: Tumors, Tissues, Skin, Image segmentation, Pathology, Data modeling, Tumor growth modeling, 3D modeling, Hyperspectral imaging, Convolution

Read Abstract +

DOWNLOAD PAPER

SPIE Journal Paper | 8 June 2022 Open Access

Hyperspectral and multispectral image processing for gross-level tumor detection in skin lesions: a systematic review

Eleni Aloupogianni, Masahiro Ishikawa, Naoki Kobayashi, Takashi Obi

JBO, Vol. 27, Issue 06, 060901, (June 2022) https://doi.org/10.1117/12.10.1117/1.JBO.27.6.060901

KEYWORDS: Multispectral imaging, Skin, Tissues, Tumors, Image processing, Cameras, Melanoma, Hyperspectral imaging, Reflectivity, Image segmentation

Read Abstract +

DOWNLOAD PAPER

SPIE Journal Paper | 15 March 2022 Open Access

Framework for estimating renal function using magnetic resonance imaging

Masahiro Ishikawa, Tsutomu Inoue, Eito Kozawa, Hirokazu Okada, Naoki Kobayashi

JMI, Vol. 9, Issue 02, 024501, (March 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.2.024501

KEYWORDS: Kidney, Magnetic resonance imaging, Image segmentation, Digital filtering, Image registration, Injuries, Blood, Feature extraction, Tissues, 3D acquisition

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Effect of formalin fixing on chromophore saliency maps derived from multi-spectral macropathology skin images

Eleni Aloupogianni, Hiroyuki Suzuki, Takaya Ichimura, Atsushi Sasaki, Hiroto Yanagisawa, Tetsuya Tsuchida, Masahiro Ishikawa, Naoki Kobayashi, Takashi Obi

Proceedings Volume 11603, 116030W (2021) https://doi.org/10.1117/12.2581926

KEYWORDS: Skin, Chromophores, Tissues, Multispectral imaging, Hemodynamics, Absorption, Statistical analysis, RGB color model, Pathology, In vivo imaging

Read Abstract +

SPIE Journal Paper | 17 October 2017 Open Access

Feature analysis of cell nuclear chromatin distribution in support of cervical cytology

Hideki Komagata, Takaya Ichimura, Yasuka Matsuta, Masahiro Ishikawa, Kazuma Shinoda, Naoki Kobayashi, Atsushi Sasaki

JMI, Vol. 4, Issue 04, 047501, (October 2017) https://doi.org/10.1117/12.10.1117/1.JMI.4.4.047501

KEYWORDS: Californium, Cell biology, Machine learning, Diagnostics, Cancer, Feature extraction, Feature selection, Matrices, Classification systems, Statistical modeling

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 1 March 2017 Paper

Extraction of glomeruli in whole slide imaging of kidney biopsy specimens

Masahiro Ishikawa, Sumire Watanabe, Natsuki Honda, Naoki Kobayashi, Tokiya Abe, Akinori Hashiguchi, Michiie Sakamoto

Proceedings Volume 10140, 101400U (2017) https://doi.org/10.1117/12.2254306

KEYWORDS: Kidney, Tissues, Biopsy, Image processing, Pathology, Computer aided diagnosis and therapy, Digital imaging, Target detection, Medical imaging

Read Abstract +

Proceedings Article | 1 March 2017 Paper

Tissue classification of liver pathological tissue specimens image using spectral features

Emi Hashimoto, Masahiro Ishikawa, Kazuma Shinoda, Madoka Hasegawa, Hideki Komagata, Naoki Kobayashi, Naoki Mochidome, Yoshinao Oda, Chika Iwamoto, Kenoki Ohuchida, Makoto Hashizume

Proceedings Volume 10140, 101400Z (2017) https://doi.org/10.1117/12.2253818

KEYWORDS: Tissues, Liver, Image classification, Pathology, Hyperspectral imaging, RGB color model, Computer aided diagnosis and therapy, Digital imaging, Medical imaging, Image analysis

Read Abstract +

SPIE Journal Paper | 3 June 2016 Open Access

Automatic quantification of morphological features for hepatic trabeculae analysis in stained liver specimens

Masahiro Ishikawa, Yuri Murakami, Sercan Taha Ahi, Masahiro Yamaguchi, Naoki Kobayashi, Tomoharu Kiyuna, Yoshiko Yamashita, Akira Saito, Tokiya Abe, Akinori Hashiguchi, Michiie Sakamoto

JMI, Vol. 3, Issue 02, 027502, (June 2016) https://doi.org/10.1117/12.10.1117/1.JMI.3.2.027502

KEYWORDS: Image enhancement, Tissues, Liver, Image analysis, Image segmentation, Pathology, Feature extraction, Cancer, Expectation maximization algorithms, Digital imaging

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 27 April 2015 Paper

An accurate method of extracting fat droplets in liver images for quantitative evaluation

Masahiro Ishikawa, Naoki Kobayashi, Hideki Komagata, Kazuma Shinoda, Masahiro Yamaguchi, Tokiya Abe, Akinori Hashiguchi, Michiie Sakamoto

Proceedings Volume 9420, 94200Y (2015) https://doi.org/10.1117/12.2081670

KEYWORDS: Liver, Pathology, Tissues, Expectation maximization algorithms, Image processing, Image filtering, Biopsy, Image classification, Microscopes, Binary data

Read Abstract +

Proceedings Article | 29 March 2013 Paper

An algorithm to evaluate the number of trabecular cell layers using nucleus arrangement applied to hepatocellular carcinoma

Hideki Komagata, Naoki Kobayashi, Ayako Katoh, Yasuka Ohnuki, Masahiro Ishikawa, Kazuma Shinoda, Masahiro Yamaguchi, Tokiya Abe, Akinori Hashiguchi, Michiie Sakamoto

Proceedings Volume 8676, 86760M (2013) https://doi.org/10.1117/12.2006319

KEYWORDS: Diagnostics, Tumors, Tissues, Feature extraction, Image filtering, Image processing, Detection and tracking algorithms, Statistical analysis, Information technology, Breast

Read Abstract +

Showing 5 of 12 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years