Presentation | 2018-07-24 Estimation of postmortem time for Ai-CT images by using Deep Learning Shota Chai, Yasushi Hirano, Shoji Kido, Kazuyuki Kinoshita, Kunihiro Inai, Sakon Noriki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Although estimation of postmortem time is important for criminal investigation or sudden in-hospital death in the middle of the night, the accuracy of estimation is not high enough because the estimation is done by observation from the outside of the body and antemortem medical records in Japan. Furthermore the estimation depends on medical doctors' subjectivity and their experiences. In this study, we developed a method for estimating an objective and highly accurate postmortem time for Autopsy imaging (Ai) CT images. The method we developed extracted features by using autoencoder which is one of the Deep Learning techniques. As a result of the experiment, the mean absolute error between the actual and estimated postmortem time was 1.64 hours. It was shown that the proposed method had higher accuracy comparing with the method based on texture analysis. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Ai-CT / Deep Learning / Estimation of postmortem time / Autopsy imaging |
Paper # | MI2018-28 |
Date of Issue | 2018-07-17 (MI) |
Conference Information | |
Committee | MI |
---|---|
Conference Date | 2018/7/24(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | aiina (Morioka, Iwate) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Medical Imaging, etc. |
Chair | Kensaku Mori(Nagoya Univ.) |
Vice Chair | Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.) |
Secretary | Yoshiki Kawata(Aichi Inst. of Tech.) / Yuichi Kimura(Nagoya Inst. of Tech.) |
Assistant | Ryo Haraguchi(Univ. of Hyogo) / Yasushi Hirano(Yamaguchi Univ.) |
Paper Information | |
Registration To | Technical Committee on Medical Imaging |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Estimation of postmortem time for Ai-CT images by using Deep Learning |
Sub Title (in English) | |
Keyword(1) | Ai-CT |
Keyword(2) | Deep Learning |
Keyword(3) | Estimation of postmortem time |
Keyword(4) | Autopsy imaging |
1st Author's Name | Shota Chai |
1st Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
2nd Author's Name | Yasushi Hirano |
2nd Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
3rd Author's Name | Shoji Kido |
3rd Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
4th Author's Name | Kazuyuki Kinoshita |
4th Author's Affiliation | University of Fukui(Univ. of Fukui) |
5th Author's Name | Kunihiro Inai |
5th Author's Affiliation | University of Fukui(Univ. of Fukui) |
6th Author's Name | Sakon Noriki |
6th Author's Affiliation | University of Fukui(Univ. of Fukui) |
Date | 2018-07-24 |
Paper # | MI2018-28 |
Volume (vol) | vol.118 |
Number (no) | MI-150 |
Page | pp.pp.33-37(MI), |
#Pages | 5 |
Date of Issue | 2018-07-17 (MI) |