研究者詳細 - 神谷　亨

論文 - 神谷　亨

分割表示757 件中 141 - 160 件目／全件表示 >>

scSE-CRNNと3種類の呼吸音変換画像による呼吸音の分類査読有り

浅谷, 陸, 神谷, 間普, 木戸

医用画像情報学会雑誌 38 ( 4 ) 152 - 159 2021年12月

U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19 査読有り

Näppi J.J., Uemura T., Watari C., Hironaka T., Kamiya T., Yoshida H.

Scientific Reports 11 ( 1 ) 2021年12月

記述言語：英語掲載種別：研究論文（学術雑誌）

The rapid increase of patients with coronavirus disease 2019 (COVID-19) has introduced major challenges to healthcare services worldwide. Therefore, fast and accurate clinical assessment of COVID-19 progression and mortality is vital for the management of COVID-19 patients. We developed an automated image-based survival prediction model, called U-survival, which combines deep learning of chest CT images with the established survival analysis methodology of an elastic-net Cox survival model. In an evaluation of 383 COVID-19 positive patients from two hospitals, the prognostic bootstrap prediction performance of U-survival was significantly higher (P < 0.0001) than those of existing laboratory and image-based reference predictors both for COVID-19 progression (maximum concordance index: 91.6% [95% confidence interval 91.5, 91.7]) and for mortality (88.7% [88.6, 88.9]), and the separation between the Kaplan–Meier survival curves of patients stratified into low- and high-risk groups was largest for U-survival (P < 3 × 10–14). The results indicate that U-survival can be used to provide automated and objective prognostic predictions for the management of COVID-19 patients.

DOI： 10.1038/s41598-021-88591-z

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85105193010&origin=inward

Detection of abnormal opacity on chest CT images using a 3D-CNN 査読有り国際誌

Koizumi, Kamiya, Aoki, Kido

International Conference on Biomedical and Bioinformatics Engineering 26 - 29 2021年11月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In recent years, the rate of deaths from cancer tends to increase in Japan. Especially the number of deaths from lung cancer is increasing. Computed tomography (CT) device is effective screening tool for early detection of lung cancer. Simultaneously, there is concern that an increase in burden on doctors will be caused by high performance of CT improving. Therefore, by presenting the "second opinion"by the computer aided diagnosis (CAD) system, it reduces the burden on the doctor. In this paper, we developed a CAD system for automatic detection of abnormal opacities such as lung nodules or ground glass opacity (GGO) on CT images from temporal subtraction image by incorporating a sparse coding technique to convolutional neural network (CNN). We extend the sparse coding and CNN to 3D and applied them to 32 cases which is obtained different time series on same subject. As a result, we obtained true positive rate (TPR) of 80.556%, false positive rate (FPR) of 22.892% and AUC of 0.768.

DOI： 10.1145/3502871.3502876

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85126727510&origin=inward

Wavelet Scattering TransformとCRNNによる呼吸音の分類

浅谷、陸、神谷、間普、木戸

電子情報通信学会医用画像研究会、信学技報 62 - 65 2021年11月

深層距離学習に基づく歯科パノラマX線画像からの歯根吸収の識別

田村、神谷、小田、田中、森本

電子情報通信学会医用画像研究会、信学技報 68 - 71 2021年11月

A generative flow-based model for volumetric data augmentation in 3D deep learning for computed tomographic colonography 査読有り国際誌

Tomoki Uemura, Janne J. Näppi, Yasuji Ryu, Chinatsu Watari, Tohru Kamiya, Hiroyuki Yoshida

International Journal of Computer Assisted Radiology and Surgery 2021年11月

Compare Derived U-Nets Using for Retinal Vessels Segmentation 査読有り国際誌

Li G., Wang X., Wang Z., Wu J., Kamiya T.

ACM International Conference Proceeding Series 1 - 8 2021年10月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

U-Net frameworks reveal potential on image segmentation tasks of the complex morphologic objects, such as capillaries. To compare the performance of vessels segmentation in fundus images, in this paper, we review U-Net and its three derived architectures: Residual Spatial Attention Network, Generative Adversarial Networks and IterNet. The networks training and testing were completed using the same image datasets under the same configurations. We calculated the accuracy and precision of segmentation results. The results showed that the cascade U-Net architecture provided better results especially on the capillaries parts.

DOI： 10.1145/3502803.3502804

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85124455424&origin=inward

Shape Restoration by Shadow Information and Photometric Stereo 査読有り国際誌

Kameda, Lu, Kamiya, Serikawa

International Symposium on Artificial Intelligence and Robotics ( SPIE ) 2021年10月

Image Quality Improvement Using Local Adaptive Neighborhood-based Dark Channel Prior 査読有り

Onoyama, Lu, Soomro, Mokhtar, Kamiya, Serikawa

International Symposium on Artificial Intelligence and Robotics 2021年10月

Underwater Image Super-resolution Using SRCNN 査読有り国際誌

Ooyama, Lu, Kamiya, Serikawa

International Symposium on Artificial Intelligence and Robotics ( SPIE ) 2021年10月

Automatic Segmentation of Finger Bone Regions from CR Images Using Improved DeepLabv3+ 査読有り

Ono, Murakami, Kamiya, Aoki

International Conference on Control, Automation and Systems ( International Conference on Control, Automation and Systems ) 1788 - 1791 2021年10月

Incorporating Ghost Module into RCAN for Super-Resolution of Satellite Images 査読有り国際誌

Ikeda, Li, Kamiya

International Conference on Control, Automation and Systems 2059 - 2063 2021年10月

Determination of Abnormality of IGBT Images Using VGG16 査読有り

Ogawa, Watanabe, Omura, Kamiya

International Conference on Control, Automation and Systems 2055 - 2058 2021年10月

Automatic Identification of CTC in Fluorescence Microscope Images Using Segmentation Algorithm of Cell Nucleus 査読有り

Hashimoto, Kamiya, Yoneda, Tanaka

International Conference on Control, Automation and Systems 2051 - 2054 2021年10月

A Classification Method for Magnetic Particle Testing Image Using U-Net 査読有り国際誌

Moritsuka, Kamiya

International Conference on Control, Automation and Systems 2047 - 2050 2021年10月

Environment Recognition from A Spherical Camera Image Based on DeepLab v3+ 査読有り

Nishida, Li, Kamiya

International Conference on Control, Automation and Systems 2043 - 2046 2021年10月

Classification of Respiratory Sounds Improved CRNN 査読有り国際誌

Asatani, Kamiya, Mabu, Kido

International Conference on Control, Automation and Systems 1804 - 1808 2021年10月

Detection of the root resorption from panoramic X-ray images using deep metric learning 査読有り国際誌

Tamura, Kamiya, Oda, Tanaka, Moritomo

International Conference on Control, Automation and Systems 1800 - 1803 2021年10月

A Method for Evaluating of Asymmetry on Cleft Lip Using Symmetry Plane 査読有り国際誌

Sawada, Kamiya, Kimura-Nomoto, Okawachi, Nozoe, Nakamura

International Conference on Control, Automation and Systems 1796 - 1799 2021年10月

Extraction of Cervical Lymph Nodes Based on Three-Dimensional Image Registration 査読有り国際誌

Shime, Kamiya, Ishida

International Conference on Control, Automation and Systems ( International Conference on Control, Automation and Systems ) 1792 - 1795 2021年10月

　前のページ - 次のページ　

<神谷 亨>

論文 - 神谷 亨

<神谷　亨>

論文 - 神谷　亨