研究者詳細 - 森　健策

論文 - 森　健策

分割表示 1,841 件中 201 - 220 件目／全件表示 >>

Classification of COVID-19 cases from chest CT volumes using hybrid model of 3D CNN and 3D MLP-mixer 招待有り査読有り

Masahiro Oda, Tong Zheng, Yuichiro Hayashi, Yoshito Otake, Masahiro Hashimoto, Toshiaki Akashi, Shigeki Aoki, Kensaku Mori

Proc.SPIE 2023年2月

A semantic segmentation method for laparoscopic images using semantically similar groups 査読有り

Leo Uramoto, Yuichiro Hayashi, Masahiro Oda, Takayuki Kitasaka, Kazunari Misawa, Kensaku Mori

Proc.SPIE 2023年2月

Oesophagus Achalasia Diagnosis from Esophagoscopy Based on a Serial Multi-scale Network 招待有り

Jiang K., Oda M., Hayashi Y., Shiwaku H., Misawa M., Mori K.

Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization 11 巻 ( 4 ) 頁： 1 - 10 2023年2月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization

Oesophageal achalasia is a primary oesophageal motility disorder disease. To diagnose oesophagus achalasia, physicians recommend endoscopic evaluation of the oesophagus. However, a low sensitivity still accompanies esophagoscopy on oesophagus achalasia diagnosis. Thus, a quantitative diagnosis system is needed to support physicians diagnose achalasia from the esophagoscopy video. This paper proposes a Serial Multi-scale Network for classifying achalasia images from the esophagoscopy video. The proposed method contains two main components, a Dense-pooling Net, and a Serial Multi-scale Dilated encoder. We construct the Dense-pooling Net using a convolution neural network with dense mixed-pooling connections to extract features. We design the Serial Multi-scale Dilated encoder based on a residual-style dilated encoder. We combine the dilated encoder and spatial attention modules to focus on features we need. We trained and evaluated our method with a dataset that was extracted from several esophagoscopy videos of achalasia patients. The evaluation results reveal a state-of-the-art accuracy of achalasia diagnosis. Furthermore, we developed a real-time computer-aided achalasia diagnosis system with the trained network. In the real-time test, the achalasia diagnosis system can stably output the diagnosis results in only (Formula presented.) seconds. The extended experiments demonstrate that the constructed diagnosis system can diagnose achalasia from esophagoscopy videos.

DOI： 10.1080/21681163.2022.2159534

Scopus

CiNii Research

KST-Mixer: kinematic spatio-temporal data mixer for colon shape estimation 招待有り Open Access

Oda M., Furukawa K., Navab N., Mori K.

Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization 11 巻 ( 4 ) 頁： 1 - 7 2023年1月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization

We propose a spatio-temporal mixing kinematic data estimation method to estimate the shape of the colon with deformations caused by colonoscope insertion. Endoscope tracking or a navigation system that navigates physicians to target positions is needed to reduce such complications as organ perforations. Although many previous methods focused to track bronchoscopes and surgical endoscopes, few number of colonoscope tracking methods were proposed because the colon largely deforms during colonoscope insertion. The deformation causes significant tracking errors. Colon deformation should be considered in the tracking process. We propose a colon shape estimation method using a Kinematic Spatio-Temporal data Mixer (KST-Mixer) that can be used during colonoscope insertions to the colon. Kinematic data of a colonoscope and the colon, including positions and directions of their centerlines, are obtained using electromagnetic and depth sensors. The proposed method separates the data into sub-groups along the spatial and temporal axes. The KST-Mixer extracts kinematic features and mix them along the axes multiple times. We evaluated colon shape estimation accuracies in phantom studies. The proposed method achieved 11.92 mm mean Euclidean distance error, the smallest of the previous methods. Statistical analysis indicated that the proposed method significantly reduced the error compared to the previous methods.

DOI： 10.1080/21681163.2022.2151938

Open Access

Scopus

CiNii Research

人工知能（AI）の最新動向　RSNA2022におけるAI関連セッション査読有り

インナービジョン 38 巻 ( 2 ) 頁： 33 - 34 2023年1月

A semantic segmentation method for laparoscopic images using semantically similar groups 招待有り査読有り

Uramoto L., Hayashi Y., Oda M., Kitasaka T., Misawa K., Mori K.

Progress in Biomedical Optics and Imaging Proceedings of SPIE 12466 巻 2023年

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）出版者・発行元：Progress in Biomedical Optics and Imaging Proceedings of SPIE

In this paper, we present a segmentation method for laparoscopic images using semantically similar groups for multi-class semantic segmentation. Accurate semantic segmentation is a key problem for computer assisted surgeries. Common segmentation models do not explicitly learn similarities between classes. We propose a model that, in addition to learning to segment an image into classes, also learns to segment it into human-defined semantically similar groups. We modify the LinkNet34 architecture by adding a second decoder with an auxiliary task of segmenting the image into these groups. The feature maps of the second decoder are merged into the final decoder. We validate our method against our base model LinkNet34 and a larger LinkNet50. We find that our proposed modification increased the performance both with mean Dice (average +1.5%) and mean Intersection over Union metrics (average +2.8%) on two laparoscopic datasets.

DOI： 10.1117/12.2654636

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/miigp/miigp2023.html#UramotoHOKMM23

L-former: A Lightweight Transformer for Realistic Medical Image Generation and its Application to Super-resolution 招待有り査読有り

Zheng T., Oda H., Hayashi Y., Nakamura S., Mori M., Takabatake H., Natori H., Oda M., Mori K.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE 12464 巻 2023年

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）出版者・発行元：Progress in Biomedical Optics and Imaging - Proceedings of SPIE

Medical image analysis approaches such as data augmentation and domain adaption need huge amounts of realistic medical images. Generating realistic medical images by machine learning is a feasible approach. We propose L-former, a lightweight Transformer for realistic medical image generation. L-former can generate more reliable and realistic medical images than recent generative adversarial networks (GANs). Meanwhile, L-former does not consume as high computational cost as conventional Transformer-based generative models. L-former uses Transformers to generate low-resolution feature vectors at shallow layers, and uses convolutional neural networks to generate high-resolution realistic medical images at deep layers. Experimental results showed that L-former outperformed conventional GANs by FID scores 33.79 and 76.85 on two datasets, respectively. We further conducted a downstream study by using the images generated by L-former to perform a super-resolution task. A high PSNR score of 27.87 proved L-former’s ability to generate reliable images for super-resolution and showed its potential for applications in medical diagnosis.

DOI： 10.1117/12.2653776

Web of Science

Scopus

Boundary-aware Feature and Prediction Refinement for Polyp Segmentation 査読有り

ie Qiu, Yuichiro Hayashi, Masahiro Oda, Takayuki Kitasaka, Kensaku Mori, ``Boundary-aware Feature and Prediction Refinement for Polyp Segmentation

Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization 2022年12月

Classification and visual explanation for COVID-19 pneumonia from CT images using triple learning. 招待有り査読有り Open Access

Kato S, Oda M, Mori K, Shimizu A, Otake Y, Hashimoto M, Akashi T, Hotta K

Scientific reports 12 巻 ( 1 ) 頁： 20840 2022年12月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Scientific Reports

This study presents a novel framework for classifying and visualizing pneumonia induced by COVID-19 from CT images. Although many image classification methods using deep learning have been proposed, in the case of medical image fields, standard classification methods are unable to be used in some cases because the medical images that belong to the same category vary depending on the progression of the symptoms and the size of the inflamed area. In addition, it is essential that the models used be transparent and explainable, allowing health care providers to trust the models and avoid mistakes. In this study, we propose a classification method using contrastive learning and an attention mechanism. Contrastive learning is able to close the distance for images of the same category and generate a better feature space for classification. An attention mechanism is able to emphasize an important area in the image and visualize the location related to classification. Through experiments conducted on two-types of classification using a three-fold cross validation, we confirmed that the classification accuracy was significantly improved; in addition, a detailed visual explanation was achieved comparison with conventional methods.

DOI： 10.1038/s41598-022-24936-6

Open Access

Scopus

PubMed

その他リンク： https://www.nature.com/articles/s41598-022-24936-6

Positive-gradient-weighted object activation mapping: visual explanation of object detector towards precise colorectal-polyp localisation 招待有り査読有り国際誌 Open Access

Itoh, H; Misawa, M; Mori, Y; Kudo, SE; Oda, M; Mori, K

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 17 巻 ( 11 ) 頁： 2051 - 2063 2022年11月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：International Journal of Computer Assisted Radiology and Surgery

Purpose: Precise polyp detection and localisation are essential for colonoscopy diagnosis. Statistical machine learning with a large-scale data set can contribute to the construction of a computer-aided diagnosis system for the prevention of overlooking and miss-localisation of a polyp in colonoscopy. We propose new visual explaining methods for a well-trained object detector, which achieves fast and accurate polyp detection with a bounding box towards a precise automated polyp localisation. Method: We refine gradient-weighted class activation mapping for more accurate highlighting of important patterns in processing a convolutional neural network. Extending the refined mapping into multiscaled processing, we define object activation mapping that highlights important object patterns in an image for a detection task. Finally, we define polyp activation mapping to achieve precise polyp localisation by integrating adaptive local thresholding into object activation mapping. We experimentally evaluate the proposed visual explaining methods with four publicly available databases. Results: The refined mapping visualises important patterns in each convolutional layer more accurately than the original gradient-weighted class activation mapping. The object activation mapping clearly visualises important patterns in colonoscopic images for polyp detection. The polyp activation mapping localises the detected polyps in ETIS-Larib, CVC-Clinic and Kvasir-SEG database with mean Dice scores of 0.76, 0.72 and 0.72, respectively. Conclusions: We developed new visual explaining methods for a convolutional neural network by refining and extending gradient-weighted class activation mapping. Experimental results demonstrated the validity of the proposed methods by showing that accurate visualisation of important patterns and localisation of polyps in a colonoscopic image. The proposed visual explaining methods are useful for the interpreting and applying a trained polyp detector.

DOI： 10.1007/s11548-022-02696-y

Pattern Analysis of Substantia Nigra in Parkinson Disease by Fifth-Order Tensor Decomposition and Multi-sequence MRI 査読有り

Hayato Itoh, Tao Hu, Masahiro Oda, Shinji Saiki, Koji Kamagata, Nobutaka Hattori, Shigeki Aoki,Kensaku Mori

LNCS13594 2022年10月

Enhancing Model Generalization for Substantia Nigra Segmentation Using a Test-time Normalization-Based Method 査読有り

Tao Hu, Hayato Itoh, Masahiro Oda, Yuichiro Hayashi, Zhongyang Lu, Shinji Saiki, Nobutaka Hattori, Koji Kamagata, Shigeki Aoki, Kanako K. Kumamaru, Toshiaki Akashi, Kensaku Mori

LNCS13437 頁： 736 - 744 2022年9月

Geometric Constraints for Self-supervised Monocular Depth Estimation on Laparoscopic Images with Dual-task Consistency 査読有り

Wenda Li, Yuichiro Hayashi, Masahiro Oda, akayuki Kitasaka, Kazunari Misawa, Kensaku Mori

LNCS13434 頁： 467 - 477 2022年9月

Confocal Laser Scanning Microscope Image Super Resolution for Biomedical Research Based on Two-Stage Generative Adversarial Network 招待有り査読有り

Yunheng WU, Masahiro ODA, Yuichiro HAYASHI, Takanori TAKEBE, Shogo NAGATA, Shuntaro KAWAMURA, Kensaku MORI

頁： 138 - 139 2022年7月

Co-Training for Semi-Supervised CT Segmentation of COVID-19 招待有り査読有り

Kai LIU, Masahiro ODA, Tong ZHENG, Yuichiro HAYASHI, Yoshito OTAKE, Masahiro HASHIMOTO, Toshiaki AKASHI, Shigeki AOKI, Kensaku MORI

頁： 114 - 115 2022年7月

A Novel Centroid-attention based Hybrid Model for Subarachnoid Hemorrhage Classification on Imbalanced Data 招待有り査読有り

Zhongyang LU, Masahiro ODA,1, Yuichiro HAYASHI, Tao Hu, Hayato ITOH, Takeyuki WATADANI, Osamu ABE，Kensaku MORI

頁： 104 - 105 2022年7月

テンソル分解を用いた黒質緻密部の3 次元パターン表現に関する初期的検討招待有り査読有り

伊東隼人, 小田昌宏, 斉木臣二, 服部信考, 鎌形康司, 青木茂樹, 森健策

第41回日本医用画像工学会大会予稿集頁： 124 - 125 2022年7月

境界情報を考慮する損失関数を用いたFCN による腹部 CT 像からの臓器領域抽出に関する研究招待有り査読有り

大野真奈, 申忱, Holger R. Roth, 小田昌宏, 林雄一郎, 三澤一成, 森健策

第41回日本医用画像工学会大会予稿集頁： 106 - 107 2022年7月

GNN による血管名自動命名手法における臓器特徴の利用に関する検討招待有り査読有り

出口智也, 林雄一郎, 北坂孝幸, 小田昌宏, 三澤一成, 森健策

　第41回日本医用画像工学会大会予稿集 2022年7月

大腸外科領域における情報支援内視鏡外科手術システムの開発招待有り査読有り

]長谷川寛, 北口大地, 小島成浩, 竹下修由, 森健策, 伊藤雅昭

日本コンピュータ外科学会誌第31回日本コンピュータ外科学会大会特集号 24 巻 ( 2 ) 2022年6月

　前のページ - 次のページ　

<森 健策>

論文 - 森 健策

<森　健策>

論文 - 森　健策