Dr. Shota Nakamura Profile

Dr. Shota Nakamura

at Nagoya Univ. Graduate School of Medicine

SPIE Involvement:

Author

Publications (8)

Proceedings Article | 3 April 2023 Presentation + Paper

L-former: a lightweight transformer for realistic medical image generation and its application to super-resolution

Tong Zheng, Hirohisa Oda, Yuichiro Hayashi, Shota Nakamura, Masaki Mori, Hirotsugu Takabatake, Hiroshi Natori, Masahiro Oda, Kensaku Mori

Proceedings Volume 12464, 1246415 (2023) https://doi.org/10.1117/12.2653776

KEYWORDS: Transformers, Medical imaging, Super resolution, Education and training, Wavelets, Voxels, Gallium nitride, Discrete wavelet transforms, Biomedical applications, Convolution

Read Abstract +

SPIE Journal Paper | 5 April 2022 Open Access

SR-CycleGAN: super-resolution of clinical CT to micro-CT level with multi-modality super-resolution loss

Tong Zheng, Hirohisa Oda, Yuichiro Hayashi, Takayasu Moriya, Shota Nakamura, Masaki Mori, Hirotsugu Takabatake, Hiroshi Natori, Masahiro Oda, Kensaku Mori

JMI, Vol. 9, Issue 02, 024003, (April 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.2.024003

KEYWORDS: Computed tomography, Lawrencium, X-ray computed tomography, Lung, Super resolution, Lung cancer, Convolution, Image segmentation, Image resolution, Gallium nitride

Read Abstract +

Purpose: We propose a super-resolution (SR) method, named SR-CycleGAN, for SR of clinical computed tomography (CT) images to the micro-focus x-ray CT CT (μCT) level. Due to the resolution limitations of clinical CT (about 500 × 500 × 500 μm3 / voxel), it is challenging to obtain enough pathological information. On the other hand, μCT scanning allows the imaging of lung specimens with significantly higher resolution (about 50 × 50 × 50 μm3 / voxel or higher), which allows us to obtain and analyze detailed anatomical information. As a way to obtain detailed information such as cancer invasion and bronchioles from preoperative clinical CT images of lung cancer patients, the SR of clinical CT images to the μCT level is desired. Approach: Typical SR methods require aligned pairs of low-resolution (LR) and high-resolution images for training, but it is infeasible to obtain precisely aligned paired clinical CT and μCT images. To solve this problem, we propose an unpaired SR approach that can perform SR on clinical CT to the μCT level. We modify a conventional image-to-image translation network named CycleGAN to an inter-modality translation network named SR-CycleGAN. The modifications consist of three parts: (1) an innovative loss function named multi-modality super-resolution loss, (2) optimized SR network structures for enlarging the input LR image to k2-times by width and height to obtain the SR output, and (3) sub-pixel shuffling layers for reducing computing time. Results: Experimental results demonstrated that our method successfully performed SR of lung clinical CT images. SSIM and PSNR scores of our method were 0.54 and 17.71, higher than the conventional CycleGAN’s scores of 0.05 and 13.64, respectively. Conclusions: The proposed SR-CycleGAN is usable for the SR of a lung clinical CT into μCT scale, while conventional CycleGAN output images with low qualitative and quantitative values. More lung micro-anatomy information could be observed to aid diagnosis, such as the shape of bronchioles walls.

DOWNLOAD PAPER

Proceedings Article | 4 April 2022 Presentation + Paper

Coarse-to-fine cascade framework for cross-modality super-resolution on clinical/micro CT dataset

Tong Zheng, Hirohisa Oda, Yuichiro Hayashi, Shota Nakamura, Masaki Mori, Hirotsugu Takabatake, Hiroshi Natori, Masahiro Oda, Kensaku Mori

Proceedings Volume 12032, 120321T (2022) https://doi.org/10.1117/12.2611311

KEYWORDS: Computed tomography, Lawrencium, Medical imaging, Lung, Image registration, Super resolution, Computer programming, Feature extraction, Scanners, Lutetium

Read Abstract +

Proceedings Article | 10 March 2020 Presentation + Paper

Multi-modality super-resolution loss for GAN-based super-resolution of clinical CT images using micro CT image database

Tong Zheng, Hirohisa Oda, Takayasu Moriya, Takaaki Sugino, Shota Nakamura, Masahiro Oda, Masaki Mori, Hirotsugu Takabatake, Hiroshi Natori, Kensaku Mori

Proceedings Volume 11313, 1131305 (2020) https://doi.org/10.1117/12.2548929

KEYWORDS: Computed tomography, Super resolution, Lung cancer, Lung, Lawrencium, Image resolution, Databases, Cancer, Information science, Image processing

Read Abstract +

Proceedings Article | 27 March 2019 Paper

Investigation of extracting interlobular septa with Hessian analysis and radial structure tensor combined with roundness error in micro-CT volume

Xiaotian Zhao, Hirohisa Oda, Shota Nakamura, Yuichiro Hayashi, Hayato Itoh, Masahiro Oda, Kensaku Mori

Proceedings Volume 11050, 110501E (2019) https://doi.org/10.1117/12.2521646

KEYWORDS: Lung, Error analysis, Tissues, Lung cancer, Visualization, Blood vessels, Information science, Binary data, Nondestructive evaluation, Computed tomography

Read Abstract +

Proceedings Article | 15 March 2019 Presentation + Paper

Unsupervised segmentation of micro-CT images based on a hybrid of variational inference and adversarial learning

Takayasu Moriya, Holger Roth, Shota Nakamura, Hirohisa Oda, Masahiro Oda, Kensaku Mori

Proceedings Volume 10953, 109530L (2019) https://doi.org/10.1117/12.2513094

KEYWORDS: Image segmentation, Computer programming, Lung cancer, 3D image processing, Tissues, Feature extraction, Machine learning

Read Abstract +

Proceedings Article | 12 March 2018 Paper

Unsupervised segmentation of 3D medical images based on clustering and deep representation learning

Takayasu Moriya, Holger Roth, Shota Nakamura, Hirohisa Oda, Kai Nagara, Masahiro Oda, Kensaku Mori

Proceedings Volume 10578, 1057820 (2018) https://doi.org/10.1117/12.2293414

KEYWORDS: Image segmentation, Medical imaging, 3D image processing, Machine learning, Tissues, 3D acquisition, Convolution, Lung cancer, Information science

Read Abstract +

Proceedings Article | 6 March 2018 Paper

Unsupervised pathology image segmentation using representation learning with spherical k-means

Takayasu Moriya, Holger Roth, Shota Nakamura, Hirohisa Oda, Kai Nagara, Masahiro Oda, Kensaku Mori

Proceedings Volume 10581, 1058111 (2018) https://doi.org/10.1117/12.2292172

KEYWORDS: Image segmentation, Pathology, Feature extraction, Lung cancer, Lung, Visualization, Image visualization, Machine learning

Read Abstract +

Showing 5 of 8 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