Presentation 2021-03-01
Examination of voice input and treatment detection by video analysis for endoscopic findings creation support
Chihiro Takigami, Mai Fujie, Yuichiro Yoshimura, Toshiya Nakaguchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Currently, endoscopy findings are mainly recorded by manual entry after the examination, which is burdensome due to the dependence on the physician's memory and the time required after the examination. We aim to develop a system that combines voice input and video analysis of examination findings to streamline the creation of findings and prevent omissions. For achieve smooth recognition and highly accurate item selection, we examined the recognition of input items by replacing them with short words and determined the optimal recognition words. In the video analysis, we detected the use of dyes and narrow-band light and biopsies by machine learning, suggesting the possibility of automatic recording of procedures.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Voice recognition / Endoscopic video analysis / Machine learning / Support Vector Machine
Paper # IMQ2020-12,IE2020-52,MVE2020-44
Date of Issue 2021-02-22 (IMQ, IE, MVE)

Conference Information
Committee MVE / IMQ / IE / CQ
Conference Date 2021/3/1(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Masayuki Ihara(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Hideaki Kimata(NTT) / Hideyuki Shimonishi(NEC)
Vice Chair Kiyoshi Kiyokawa(NAIST) / Mitsuru Maeda(Canon) / Kenya Uomori(Osaka Univ.) / Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.)
Secretary Kiyoshi Kiyokawa(Oosaka Inst. of Tech.) / Mitsuru Maeda(NTT) / Kenya Uomori(Univ. of ToKyo) / Kazuya Kodama(Shizuoka Univ.) / Keita Takahashi(Sony Semiconductor Solutions) / Jun Okamoto(KDDI Research) / Takefumi Hiraguri(Nagoya Inst. of Tech.)
Assistant Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Hiroaki Kudo(Nagoya Univ.) / Masaru Tsuchida(NTT) / Keita Hirai(Chiba Univ.) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) / Ryoichi Kataoka(KDDI Research)

Paper Information
Registration To Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Communication Quality
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Examination of voice input and treatment detection by video analysis for endoscopic findings creation support
Sub Title (in English)
Keyword(1) Voice recognition
Keyword(2) Endoscopic video analysis
Keyword(3) Machine learning
Keyword(4) Support Vector Machine
1st Author's Name Chihiro Takigami
1st Author's Affiliation Chiba University(Chiba Univ.)
2nd Author's Name Mai Fujie
2nd Author's Affiliation Chiba University of Clinical Engineering Center, Faculty of Medicine Hospital(Chiba Univ.)
3rd Author's Name Yuichiro Yoshimura
3rd Author's Affiliation Toyama University Hospital Medical AI Development Office(Toyama Univ.)
4th Author's Name Toshiya Nakaguchi
4th Author's Affiliation Chiba University Frontier Medical Engineering Center(Chiba Univ.)
Date 2021-03-01
Paper # IMQ2020-12,IE2020-52,MVE2020-44
Volume (vol) vol.120
Number (no) IMQ-389,IE-390,MVE-391
Page pp.pp.13-16(IMQ), pp.13-16(IE), pp.13-16(MVE),
#Pages 4
Date of Issue 2021-02-22 (IMQ, IE, MVE)