Faculty Profiles - ODA, Masahiro

Papers - ODA, Masahiro

Division display 341 - 360 of about 372 ／ All the affair displays >>

Influence of Voxel-Connection Structure in Organ Segmentation Based on Conditional Random Field

Ying Yang, Masahiro Oda, Kazunari Misawa, Daniel Rueckert, Kensaku Mori

MI2016-112 Vol. 116 ( 393 ) page： 157-162 2017.1

Structured Random Forestを用いた3次元腹部CT像からのリンパ節自動検出

寳珠山裕, Holger Roth, 小田昌宏, 中村嘉彦, 三澤一成, 藤原道隆, 森健策

電子情報通信学会技術研究報告(MI) Vol. 116 ( 393 ) page： 23-28 2017.1

MISTライブラリのためのGPUプログラミング

小田紘久, 小田昌宏, 北坂孝幸, 森健策

電子情報通信学会技術研究報告(MI) Vol. 116 ( 393 ) page： 133-136 2017.1

Robust colonoscope tracking method for colon deformations utilizing coarse-to-fine correspondence findings Reviewed International coauthorship Open Access

Masahiro Oda, Hiroaki Kondo, Takayuki Kitasaka, Kazuhiro Furukawa, Ryoji Miyahara ,Yoshiki Hirooka, Hidemi Goto, Nassir Navab, Kensaku Mori

International Journal of Computer Assisted Radiology and Surgery Vol. 12 ( 1 ) page： 39-50 2017.1

Extracellular matrix directions estimation of the heart on micro-focus X-ray CT volumes Reviewed

Oda Hirohisa, Oda Masahiro, Kitasaka Takayuki, Akita Toshiaki, Mori Kensaku

MEDICAL IMAGING 2017: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING Vol. 10137 2017

Evaluation of a cardiac model using different 3D printers and materials Reviewed Open Access

Murata Masato, Hirayama Koudai, Takenouchi Sinsaku, Oda Masahiro, Mori Kensaku, Niki Kiyomi

Transactions of Japanese Society for Medical and Biological Engineering Vol. 55 ( 4 ) page： 273-273 2017

Language：Japanese Publishing type：Research paper (scientific journal)

<p>[Purpose] Models of the diseased heart produced by 3D printers are expected to provide useful information for surgical procedures. However, the precision of commercially available machines is uncertain. Therefore, we assessed the 3D models by two different methods. [Method] Using DICOM data derived from x-ray CT images of a heart, 3D models were produced by a fused deposition modeling method (FDM) and an ink-jet method. Polylactic resin (PLA) and silicone rubber (AR-G1L) were used as materials for the FDM and ink-jet methods, respectively. [Result] The model created using the FDM was produced at a reduced size due to limitations of the machine, which caused the coronary artery to collapse. It was also difficult to cut. The model created using the ink-jet method was produced at full scale and quite flexible. [Conclusion] The heart model created using the ink-jet method with silicone rubber provides excellent information for surgical treatment.</p>

DOI： 10.11239/jsmbe.55Annual.273

Open Access

CiNii Research

researchmap

Automated endoscopic image analysis based on machine learning Open Access

Mori Kensaku, Oda Masahiro, Misawa Masashi, Mori Yuichi, Kudo Shinei

Transactions of Japanese Society for Medical and Biological Engineering Vol. 55 ( 4 ) page： 344-344 2017

Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

<p>This presentation introduces automated endoscopic image diagnosis method based on machine learning. Especially we discuss effectiveness of machine learning in automated diagnosis of endoscopic images by showing automated pathological type diagnosis of colonic polyps from endocytoscopy images as examples. Machine learning research staring from perceptron or statistical pattern recognition has started in many years ago. Progress of high performance computing has enabled us to train neural network having very complex network architecture. Machine learning techniques are considered to help physicians to diagnose endoscopic images, where very higher skills are required for diagnosis. This presentation will show several automated diagnosis methods for endoscopic images. The first method classifies pathological types of colonic polyps by using hand-crafted feature values. SVM is utilized for classification. The second example is the method using CNN for automated classification. We will show these method from the technological viewpoint. Also we will discuss about training data generation.</p>

DOI： 10.11239/jsmbe.55Annual.344

Open Access

CiNii Research

Motion Vector for Outlier Elimination in Feature Matching and Its Application in SLAM Based Laparoscopic Tracking Reviewed

Wang Cheng, Oda Masahiro, Hayashi Yuichiro, Misawa Kazunari, Roth Holger, Mori Kensaku

COMPUTER ASSISTED AND ROBOTIC ENDOSCOPY AND CLINICAL IMAGE-BASED PROCEDURES Vol. 10550 page： 60-69 2017

Airway extraction from 3D chest CT volumes based on iterative extension of VOI enhanced by cavity enhancement filter Reviewed

Meng Qier, Kitasaka Takayuki, Oda Masahiro, Mori Kensaku

SPIE MEDICAL IMAGING 2017: COMPUTER-AIDED DIAGNOSIS Vol. 10134 2017

Micro-CT Guided 3D Reconstruction of Histological Images Reviewed

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

PATCH-BASED TECHNIQUES IN MEDICAL IMAGING (PATCH-MI 2017) Vol. 10530 page： 93-101 2017

Hessian-Assisted Supervoxel: Structure-Oriented Voxel Clustering and Application to Mediastinal Lymph Node Detection from CT Volumes Reviewed International coauthorship

Oda Hirosha, Bhatia Kanwal K., Oda Masahiro, Kitasaka Takayuki, Iwano Shingo, Homma Hirotoshi, Takabatake Hirotsugu, Mori Masaki, Natori Hiroshi, Schnabel Julia A., Mori Kensaku

MEDICAL IMAGING 2017: COMPUTER-AIDED DIAGNOSIS Vol. 10134 2017

3D FCN Feature Driven Regression Forest-Based Pancreas Localization and Segmentation Reviewed International coauthorship Open Access

Masahiro Oda, Natsuki Shimizu, Holger R. Roth, Ken’ichi Karasawa, Takayuki Kitasaka, Kazunari Misawa, Michitaka Fujiwara, Daniel Rueckert, Kensaku Mori

MICCAI 2017, 3rd Workshop on Deep Learning in Medical Image Analysis Vol. 10553 page： 222 - 230 2017

Extraction of membrane structure in eyeball from MR volumes Reviewed

Oda Masahiro, Kin Taichi, Mori Kensaku

SPIE MEDICAL IMAGING 2017: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING Vol. 10137 2017

Tracking and segmentation of the airways in chest CT using a fully convolutional network Reviewed

Qier Meng, Holger R. Roth, Takayuki Kitasaka, Masahiro Oda, Junji Ueno, Kensaku Mori

MICCAI 2017 Vol. 10434 LNCS page： 198 - 207 2017

TBS: Tensor-based supervoxels for unfolding the heart Reviewed International coauthorship

Hirohisa Oda, Holger R. Roth, Kanwal K. Bhatia, Masahiro Oda, Takayuki Kitasaka, Toshiaki Akita, Julia A. Schnabel, Kensaku Mori

MICCAI 2017 Vol. 10433 LNCS page： 681 - 689 2017

Comparison of the Deep-Learning-Based Automated Segmentation Methods for the Head Sectioned Images of the Virtual Korean Human Project Reviewed

Eshghi Mohammad, Roth Holger R., Oda Masahiro, Chung Min Suk, Mori Kensaku

PROCEEDINGS OF THE FIFTEENTH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS - MVA2017 page： 290 - 293 2017

Automatic Segmentation of Head Anatomical Structures from Sparsely-annotated Images Reviewed

Sugino Takaaki, Roth Holger R., Eshghi Mohammad, Oda Masahiro, Chung Min Suk, Mori Kensaku

2017 IEEE INTERNATIONAL CONFERENCE ON CYBORG AND BIONIC SYSTEMS (CBS) page： 145 - 149 2017

Influence of using 3D images and 3D-printed objects on the formation of spatial mental models of experts and novices Open Access

MAEHIGASHI Akihiro, MIWA Kazuhisa, ODA Masahiro, NAKAMURA Yoshihiko, MORI Kensaku, IGAMI Tsuyoshi

JSAI Technical Report, SIG-ALST Vol. 79 ( 0 ) 2017

Influence of using 3D images and 3D-printed objects on spatial reasoning of experts and novices

Maehigashi A., Miwa K., Oda M., Nakamura Y., Mori K., Igami T.

CogSci 2017 - Proceedings of the 39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition page： 2669 - 2674 2017

Language：Japanese Publisher：CogSci 2017 - Proceedings of the 39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition

This study focuses on the infuence of a three-dimensional (3D) graphic image and a 3D-printed object on the spatial reasoning of experts and novices in the medical field. The spatial reasoning task of this study required doctors specializing in digestive surgery to infer cross sections of a liver with a 3D image and a 3D-printed object in a situation where liver resection surgery was simulated. The task performance was compared with that of university students who conducted the same task in Maehigashi et al. (2016). The results of the analysis indicated that the doctors showed the same task performance when using the 3D image and the 3D-printed object. However, the university students learned faster and inferred the inside of a liver structure more accurately with the 3D-printed object than with the 3D image, and they performed equally to the professional doctors. Our results are then discussed in relation to previous studies.

Scopus

Hierarchical 3D fully convolutional networks for multi-organ segmentation.

Holger R. Roth, Hirohisa Oda, Yuichiro Hayashi, Masahiro Oda, Natsuki Shimizu, Michitaka Fujiwara, Kazunari Misawa, Kensaku Mori

CoRR Vol. abs/1704.06382 2017

　 PREV - NEXT 　

<ODA, Masahiro>

Papers - ODA, Masahiro