Presentation 2020-03-16
Assessing robustness of deep learning methods in dermoscopic workflow
Sourav Mishra, Hideaki Imaizumi, Toshihiko Yamasaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Our paper aims to evaluate current deep learning methods for clinical workflow in the domain of dermatology. Although deep learning methods have been successful in many cases, it has not been rigorously tested for common clinical complaints. Most projects involve data acquired in well-controlled laboratory conditions which may not reflect regular clinical evaluation. We test the robustness of deep learning methods by simulating non-ideal characteristics on user submitted images of ten classes of diseases. Assessing via imitated conditions, we have found the overall accuracy to drop and individual predictions change significantly in many cases despite of robust training.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep LearningDermatologyRobustness
Paper # PRMU2019-79
Date of Issue 2020-03-09 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2020/3/16(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT)
Secretary Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX)
Assistant Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Assessing robustness of deep learning methods in dermoscopic workflow
Sub Title (in English)
Keyword(1) Deep LearningDermatologyRobustness
1st Author's Name Sourav Mishra
1st Author's Affiliation The University of Tokyo(Univ. of Tokyo)
2nd Author's Name Hideaki Imaizumi
2nd Author's Affiliation exMedio Inc.(exMedio)
3rd Author's Name Toshihiko Yamasaki
3rd Author's Affiliation The University of Tokyo(Univ. of Tokyo)
Date 2020-03-16
Paper # PRMU2019-79
Volume (vol) vol.119
Number (no) PRMU-481
Page pp.pp.77-78(PRMU),
#Pages 2
Date of Issue 2020-03-09 (PRMU)