Presentation 2018-09-21
[Short Paper] Automatic Segmentation of Epicardial Using Deep Learning
Ziyu Zhao, Tomoe Otoishi, Yutaro Iwamoto, Youji Tetsuka, Yuki Okada, Kiyosumi Maeda, Atsuyuki Wada, Atsunori Kashiwagi, Yanwei Chen,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The epicardial is a wall sac containing the heart and the roots of the great vessels. Epicardial adipose tissue adhere to the inside and outside of the epicardial, it is necessary to extract the epicardial to distinguish these fat tissues. A major challenge in epicardial segmentation is that in the cardiac Computed Tomography(CT) images, the epicardial exists as a very thin line and there are places where it can not be observed. Up to now, the main method of epicardial segmentation is manual extraction by experts. In this study, we propose a fully automatic method for epicardial segmentation, which is developed using U-Net, and demonstrated that it is possible to automatically segment epicardial.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep learning / Epicardial segmentation / U-Net
Paper # PRMU2018-55,IBISML2018-32
Date of Issue 2018-09-13 (PRMU, IBISML)

Conference Information
Committee PRMU / IBISML / IPSJ-CVIM
Conference Date 2018/9/20(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinichi Sato(NII) / Hisashi Kashima(Kyoto Univ.)
Vice Chair Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) / Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST)
Assistant Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Short Paper] Automatic Segmentation of Epicardial Using Deep Learning
Sub Title (in English)
Keyword(1) Deep learning
Keyword(2) Epicardial segmentation
Keyword(3) U-Net
1st Author's Name Ziyu Zhao
1st Author's Affiliation Ritsumei University(Ritsumei Univ)
2nd Author's Name Tomoe Otoishi
2nd Author's Affiliation Ritsumei University(Ritsumei Univ)
3rd Author's Name Yutaro Iwamoto
3rd Author's Affiliation Ritsumei University(Ritsumei Univ)
4th Author's Name Youji Tetsuka
4th Author's Affiliation Kusatsu General Hospital(Kusatsu General Hospita)
5th Author's Name Yuki Okada
5th Author's Affiliation Kusatsu General Hospital(Kusatsu General Hospita)
6th Author's Name Kiyosumi Maeda
6th Author's Affiliation Kusatsu General Hospital(Kusatsu General Hospita)
7th Author's Name Atsuyuki Wada
7th Author's Affiliation Kusatsu General Hospital(Kusatsu General Hospita)
8th Author's Name Atsunori Kashiwagi
8th Author's Affiliation Kusatsu General Hospital(Kusatsu General Hospita)
9th Author's Name Yanwei Chen
9th Author's Affiliation Ritsumei University(Ritsumei Univ)
Date 2018-09-21
Paper # PRMU2018-55,IBISML2018-32
Volume (vol) vol.118
Number (no) PRMU-219,IBISML-220
Page pp.pp.131-132(PRMU), pp.131-132(IBISML),
#Pages 2
Date of Issue 2018-09-13 (PRMU, IBISML)