Presentation | 2018-05-18 Electronic Cleansing for CT Colonography using Deep Learning Rie Tachibana, Janne J. Nappi, Toru Hironaka, Hiroyuki Yoshida, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Although colonoscopy is considered as a standard procedure for colon cancer screening, CT colonography (CTC) has recently been widely accepted as an alternative to colonoscopy. Currently, however, CTC requires pre-examination cathartic bowel cleansing, which is a well-known barrier of patient adherence to colorectal cancer screening. In this study, we developed an electronic cleansing scheme based on deep learning for virtually removing residual feces and fluid tagged by an orally administered contrast agent in CTC images. In our scheme, a deep convolutional neural network was used to generate multi-material labeled images from cut-plane images extracted at multiple angles at each voxel of a CTC volume. Electronically cleansed CTC images are generated from the multi-material labeled images by keeping only the materials labeled as soft tissue and removing all of the other materials including tagged fecal materials. Preliminary results showed that our deep-learning based method was able to classify voxels of the CTC volumes to multi-material classes with high accuracy when increased number of angled cut-plane images are used, and thus, our scheme was able to accurately remove residual fecal materials from the CTC images. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | CT colonography / Electronic cleansing / Deep learning |
Paper # | SIP2018-8,IE2018-8,PRMU2018-8,MI2018-8 |
Date of Issue | 2018-05-10 (SIP, IE, PRMU, MI) |
Conference Information | |
Committee | PRMU / MI / IE / SIP |
---|---|
Conference Date | 2018/5/17(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Shinichi Sato(NII) / Kensaku Mori(Nagoya Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Masahiro Okuda(Univ. of Kitakyushu) |
Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.) / Kazuya Kodama(NII) / Hideaki Kimata(NTT) / Shogo Muramatsu(Niigata Univ.) / Naoyuki Aikawa(TUS) |
Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Yoshiki Kawata(Aichi Inst. of Tech.) / Yuichi Kimura(Nagoya Inst. of Tech.) / Kazuya Kodama(Nagoya Univ.) / Hideaki Kimata(KDDI Research) / Shogo Muramatsu(Chiba Inst. of Tech.) / Naoyuki Aikawa(Takushoku Univ.) |
Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Ryo Haraguchi(Univ. of Hyogo) / Yasushi Hirano(Yamaguchi Univ.) / Yasutaka Matsuo(NHK) / Kazuya Hayase(NTT) / Masayoshi Nakamoto(Hiroshima Univ.ひろ) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Medical Imaging / Technical Committee on Image Engineering / Technical Committee on Signal Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Electronic Cleansing for CT Colonography using Deep Learning |
Sub Title (in English) | |
Keyword(1) | CT colonography |
Keyword(2) | Electronic cleansing |
Keyword(3) | Deep learning |
1st Author's Name | Rie Tachibana |
1st Author's Affiliation | National Institute of Technology, Oshima College(NIT, Oshima College) |
2nd Author's Name | Janne J. Nappi |
2nd Author's Affiliation | Massachusetts General Hospital/Harvard Medical School(MGH/HMS) |
3rd Author's Name | Toru Hironaka |
3rd Author's Affiliation | Massachusetts General Hospital/Harvard Medical School(MGH/HMS) |
4th Author's Name | Hiroyuki Yoshida |
4th Author's Affiliation | Massachusetts General Hospital/Harvard Medical School(MGH/HMS) |
Date | 2018-05-18 |
Paper # | SIP2018-8,IE2018-8,PRMU2018-8,MI2018-8 |
Volume (vol) | vol.118 |
Number (no) | SIP-33,IE-34,PRMU-35,MI-36 |
Page | pp.pp.35-37(SIP), pp.35-37(IE), pp.35-37(PRMU), pp.35-37(MI), |
#Pages | 3 |
Date of Issue | 2018-05-10 (SIP, IE, PRMU, MI) |