Search

Your search keyword '"HAYASHI H"' showing total 11,220 results
Start Over Author "HAYASHI H"
11,220 results on '"HAYASHI H"'

163. Open-label phase II study of the efficacy of nivolumab for cancer of unknown primary

Author

Tanizaki, J., primary, Yonemori, K., additional, Akiyoshi, K., additional, Minami, H., additional, Ueda, H., additional, Takiguchi, Y., additional, Miura, Y., additional, Segawa, Y., additional, Takahashi, S., additional, Iwamoto, Y., additional, Kidera, Y., additional, Fukuoka, K., additional, Ito, A., additional, Chiba, Y., additional, Sakai, K., additional, Nishio, K., additional, Nakagawa, K., additional, and Hayashi, H., additional

Published
2022
Full Text
View/download PDF

183. Combining noise-to-image and image-to-image GANs: Brain MR image augmentation for tumor detection

Author

Han, C, Rundo, L, Araki, R, Nagano, Y, Furukawa, Y, Mauri, G, Nakayama, H, Hayashi, H, Han C., Rundo L., Araki R., Nagano Y., Furukawa Y., Mauri G., Nakayama H., Hayashi H., Han, C, Rundo, L, Araki, R, Nagano, Y, Furukawa, Y, Mauri, G, Nakayama, H, Hayashi, H, Han C., Rundo L., Araki R., Nagano Y., Furukawa Y., Mauri G., Nakayama H., and Hayashi H.

Abstract

Convolutional Neural Networks (CNNs) achieve excellent computer-assisted diagnosis with sufficient annotated training data. However, most medical imaging datasets are small and fragmented. In this context, Generative Adversarial Networks (GANs) can synthesize realistic/diverse additional training images to fill the data lack in the real image distribution; researchers have improved classification by augmenting data with noise-to-image (e.g., random noise samples to diverse pathological images) or image-to-image GANs (e.g., a benign image to a malignant one). Yet, no research has reported results combining noise-to-image and image-to-image GANs for further performance boost. Therefore, to maximize the DA effect with the GAN combinations, we propose a two-step GAN-based DA that generates and refines brain Magnetic Resonance (MR) images with/without tumors separately: (i) Progressive Growing of GANs (PGGANs), multi-stage noise-to-image GAN for high-resolution MR image generation, first generates realistic/diverse 256 × 256 images; (ii) Multimodal UNsupervised Image-to-image Translation (MUNIT) that combines GANs/Variational AutoEncoders or SimGAN that uses a DA-focused GAN loss, further refines the texture/shape of the PGGAN-generated images similarly to the real ones. We thoroughly investigate CNN-based tumor classification results, also considering the influence of pre-training on ImageNet and discarding weird-looking GAN-generated images. The results show that, when combined with classic DA, our two-step GAN-based DA can significantly outperform the classic DA alone, in tumor detection (i.e., boosting sensitivity 93.67% to 97.48%) and also in other medical imaging tasks.

Published
2019

184. MO50-7 Evaluation of preoperative chemotherapy and cancer genome therapy for intrahepatic cholangiocarcinoma in our hospital.

Author

Matsumoto, T., Hayashi, H., Yumoto, S., Miyamoto, H., Adachi, Y., Kanemitsu, K., Tajiri, T., Ofuchi, T., Ogawa, D., Shiraishi, Y., Takematsu, T., Itoyama, R., Kitano, Y., Nakagawa, S., Mima, K., Okabe, H., Tanaka, Y., and Baba, H.

Subjects
*NEOADJUVANT chemotherapy, *CANCER chemotherapy, *CANCER treatment, *CHOLANGIOCARCINOMA, *HOSPITALS
Published
2024
Full Text
View/download PDF

187. Developments of SOI monolithic pixel detectors

Author

Arai, Y., Miyoshi, T., Unno, Y., Tsuboyama, T., Terada, S., Ikegami, Y., Kohriki, T., Tauchi, K., Ikemoto, Y., Ichimiya, R., Ikeda, H., Hara, K., Miyake, H., Kochiyama, M., Sega, T., Hanagaki, K., Hirose, M., Hatsui, T., Kudo, T., Hirono, T., Yabashi, M., Furukawa, Y., Varner, G., Cooney, M., Hoedlmoser, H., Kennedy, J., Sahoo, H., Battaglia, M., Denes, P., Vu, C., Contarato, D., Giubilato, P., Glesener, L., Yarema, R., Lipton, R., Deptuch, G., Trimpl, M., Ohno, M., Fukuda, K., Komatsubara, H., Ida, J., Okihara, M., Hayashi, H., Kawai, Y., and Ohtomo, A.

Published
2010
Full Text
View/download PDF

190. Neurocomputers in Japan

Author

Hayashi, H., Brebbia, C. A., editor, Orszag, S. A., editor, Argyris, J., editor, Bathe, K.-J., editor, Cakmak, A. S., editor, Connor, J., editor, McCrory, R., editor, Desai, C. S., editor, Holz, K.-P., editor, Leckie, F. A., editor, Pinder, G., editor, Pont, A. R. S., editor, Seinfeld, J. H., editor, Silvester, P., editor, Spanos, P., editor, Wunderlich, W., editor, Yip, S., editor, Murthy, Thiruvalam K. S., editor, and Brebbia, Carlos A., editor

Published
1991
Full Text
View/download PDF

193. 'Lang ist die Zeit, es ereignet sich aber das Wahre':Hölderlins Poetik des ‚Ereignisses‘

Author

Hayashi, H. (Hideya), Wagner-Egelhaaf, M. (Martina), and Universitäts- und Landesbibliothek Münster

Subjects
Hölderlin, Ereignis, Hyperion, Empedokles, Tragödie, Übersetzung, Tawada, ddc:831, German poetry
Abstract

In Hölderlins Texten spielt der Zustand, in dem alles eins ist, eine große Rolle. Diese ‚ursprüngliche Einheit‘ wird in dieser Arbeit als ‚Ereignis‘ verstanden. In der ‚Ereignishaftigkeit‘ der ‚ursprünglichen Einheit‘ zeigen sich drei Aspekte. Der erste Aspekt ist die Zeitlichkeit. Das ‚Ereignis‘ im Sinne vom ‚Sich-Ereignen‘ ist ein Prozess, der in einem Augenblick vergeht und nur als schon Vergangenes oder als noch nicht Geschehenes verstanden werden kann. Der zweite Aspekt ist die Unkontrollierbarkeit für die Menschen. Hölderlins Texten liegt der Gedanke zugrunde, dass sich die Annäherung an die ‚ursprüngliche Einheit‘ ereignet, indem das Außermenschliche ins Menschliche eintritt und sich mit dem Menschlichen vereinigt. Der dritte Aspekt ist die körperliche Wirkung, die durch das Eintreten des Außermenschlichen auf die Menschen ausgeübt wird. Durch diese ‚Ereignishaftigkeit‘ stellt Hölderlins Poetik des ‚Ereignisses‘ die ‚ursprüngliche Einheit‘ mittelbar dar.

Published
2021

194. Infinite Brain MR Images: PGGAN-Based Data Augmentation for Tumor Detection

Author

Han, C, Rundo, L, Araki, R, Furukawa, Y, Mauri, G, Nakayama, H, and Hayashi, H

Subjects
46 Information and Computing Sciences, FOS: Clinical medicine, 4611 Machine Learning, Neurological, Neurosciences, Biomedical Imaging, Bioengineering, Cancer, Brain Disorders
Abstract

Due to the lack of available annotated medical images, accurate computer-assisted diagnosis requires intensive data augmentation (DA) techniques, such as geometric/intensity transformations of original images; however, those transformed images intrinsically have a similar distribution to the original ones, leading to limited performance improvement. To fill the data lack in the real image distribution, we synthesize brain contrast-enhanced magnetic resonance (MR) images—realistic but completely different from the original ones—using generative adversarial networks (GANs). This study exploits progressive growing of GANs (PGGANs), a multistage generative training method, to generate original-sized 256 × 256 MR images for convolutional neural network-based brain tumor detection, which is challenging via conventional GANs; difficulties arise due to unstable GAN training with high resolution and a variety of tumors in size, location, shape, and contrast. Our preliminary results show that this novel PGGAN-based DA method can achieve a promising performance improvement, when combined with classical DA, in tumor detection and also in other medical imaging tasks.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results