Presentation 2012-01-20
Simultaneous extraction of multiple organs using a combination of conditional statistical shape model and graph cuts
Junichi KAMIYAMA, Sho TOMOSHIGE, Hidefumi WATANABE, Akinobu SHIMIZU, Hidefumi KOBATAKE, Shigeru NAWANO, Mitsutaka Nemoto, Shohei HANAOKA, Yoshitaka MASUTANI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the previous report, we proposed a multi-label graph-cuts based simultaneous segmentation algorithm for multiple organs which utilizes estimated shapes of organs. The performance of the shape estimation, however, is low in the case of gallbladder whose variation in shape and pose is large, resulting in poor performance of the graph-cuts based segmentation. This study proposes a conditional statistical shape model of an organ in which information correlated with the target organ is used as a condition. We aim to boost performance of shape estimation and organ segmentation by use of the proposed model. This paper presents results of applying the proposed model to simultaneous segmentation of neighboring four organs in a CT volume and report that the performance of the proposed model was superior to that of a conventional non-conditional model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) conditional statistical shape model / non-contrast abdominal CT volume / Simultaneous segmentation of multiple organs / multi-label graph-cuts
Paper # MI2011-131
Date of Issue

Conference Information
Committee MI
Conference Date 2012/1/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Medical Imaging (MI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Simultaneous extraction of multiple organs using a combination of conditional statistical shape model and graph cuts
Sub Title (in English)
Keyword(1) conditional statistical shape model
Keyword(2) non-contrast abdominal CT volume
Keyword(3) Simultaneous segmentation of multiple organs
Keyword(4) multi-label graph-cuts
1st Author's Name Junichi KAMIYAMA
1st Author's Affiliation Tokyo University of Agriculture and Technology()
2nd Author's Name Sho TOMOSHIGE
2nd Author's Affiliation Tokyo University of Agriculture and Technology
3rd Author's Name Hidefumi WATANABE
3rd Author's Affiliation Tokyo University of Agriculture and Technology
4th Author's Name Akinobu SHIMIZU
4th Author's Affiliation Tokyo University of Agriculture and Technology
5th Author's Name Hidefumi KOBATAKE
5th Author's Affiliation Tokyo University of Agriculture and Technology
6th Author's Name Shigeru NAWANO
6th Author's Affiliation Cancer for Radiological Sciences, International University of Health and Welfare
7th Author's Name Mitsutaka Nemoto
7th Author's Affiliation Department of Radiology, University of Tokyo Hospital
8th Author's Name Shohei HANAOKA
8th Author's Affiliation Department of Radiology, University of Tokyo Hospital
9th Author's Name Yoshitaka MASUTANI
9th Author's Affiliation Department of Radiology, University of Tokyo Hospital
Date 2012-01-20
Paper # MI2011-131
Volume (vol) vol.111
Number (no) 389
Page pp.pp.-
#Pages 6
Date of Issue