Presentation 2020-03-06
Performance improvement by bone removal based on watershed algorithm and texture analysis in extravasation detection using contrast CT images
Hiroki Kimura, Kumiko Arai, Yuichiro Yoshimura, Takaaki Nakada, Shigeto Oda, Toshiya Nakaguchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We are investigating an automatic detection method for extravasation using contrast-enhanced CT images in order to reduce the burden on doctors in emergency medicine. In this paper, we propose a bone removal method based on the watershed algorithm for bone removal, which is one of the important factors in the detection process, and improve its performance. In addition, the number of false positive was reduced by using a random forest learner to classify candidate area using texture feature. By using the proposed bone removal method, the sensitivity was improved and the detectability was improved compared to the conventional method. In addition, false positives were reduced by about 35% compared to previous studies by classifying candidate regions corresponding to bone misdetection.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) contrast-enhanced CT images / extravasation / machine learning / Random Forest method / texture analysis
Paper # IMQ2019-34,IE2019-116,MVE2019-55
Date of Issue 2020-02-27 (IMQ, IE, MVE)

Conference Information
Committee IE / IMQ / MVE / CQ
Conference Date 2020/3/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyushu Institute of Technology
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hideaki Kimata(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Kenji Mase(Nagoya Univ.) / Hideyuki Shimonishi(NEC)
Vice Chair Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Mitsuru Maeda(Canon) / Kenya Uomori(Osaka Univ.) / Masayuki Ihara(NTT) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.)
Secretary Kazuya Kodama(NTT) / Keita Takahashi(NHK) / Mitsuru Maeda(Shizuoka Univ.) / Kenya Uomori(Sony Semiconductor Solutions) / Masayuki Ihara(Nagoya Univ.) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.)
Assistant Kyohei Unno(KDDI Research) / Norishige Fukushima(Nagoya Inst. of Tech.) / Hiroaki Kudo(Nagoya Univ.) / Masaru Tsuchida(NTT) / Keita Hirai(Chiba Univ.) / Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(NTT) / Shogo Fukushima(Univ. of ToKyo) / Chikara Sasaki(KDDI Research) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT)

Paper Information
Registration To Technical Committee on Image Engineering / Technical Committee on Image Media Quality / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Communication Quality
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Performance improvement by bone removal based on watershed algorithm and texture analysis in extravasation detection using contrast CT images
Sub Title (in English)
Keyword(1) contrast-enhanced CT images
Keyword(2) extravasation
Keyword(3) machine learning
Keyword(4) Random Forest method
Keyword(5) texture analysis
1st Author's Name Hiroki Kimura
1st Author's Affiliation Graduate of Science and Engineering, Chiba University(Chiba Univ)
2nd Author's Name Kumiko Arai
2nd Author's Affiliation Department of Emergency and Critical Care Medicine(Chiba Univ)
3rd Author's Name Yuichiro Yoshimura
3rd Author's Affiliation Center for Frontier Medical Engineering, Chiba University(Chiba Univ)
4th Author's Name Takaaki Nakada
4th Author's Affiliation Department of Emergency and Critical Care Medicine(Chiba Univ)
5th Author's Name Shigeto Oda
5th Author's Affiliation Department of Emergency and Critical Care Medicine(Chiba Univ)
6th Author's Name Toshiya Nakaguchi
6th Author's Affiliation Center for Frontier Medical Engineering, Chiba University(Chiba Univ)
Date 2020-03-06
Paper # IMQ2019-34,IE2019-116,MVE2019-55
Volume (vol) vol.119
Number (no) IMQ-454,IE-456,MVE-457
Page pp.pp.93-96(IMQ), pp.93-96(IE), pp.93-96(MVE),
#Pages 4
Date of Issue 2020-02-27 (IMQ, IE, MVE)