Acral melanoma detection using a convolutional neural network for dermoscopy images
- 주제(기타) Multidisciplinary Sciences
- 설명문(일반) [Yu, Chanki] Sogang Univ, Grad Sch Media, Dept Media Technol, Seoul, South Korea; [Yang, Sejung] Stanford Univ, Sch Med, Dept Radiat Oncol, Med Phys Div, Palo Alto, CA 94304 USA; [Yang, Sejung; Lee, Sang Wook] Ewha Womans Univ, Dept Elect Engn, Seoul, South Korea; [Kim, Wonoh; Jung, Jinwoong; Oh, Byungho] Keimyung Univ, Coll Med, Dept Dermatol, Daegu, South Korea; [Chung, Kee-Yang] Yonsei Univ, Coll Med, Dept Dermatol, Seoul, South Korea; [Chung, Kee-Yang] Yonsei Univ, Coll Med, Cutaneous Biol Res Inst, Seoul, South Korea
- 등재 SCIE, SCOPUS
- 발행기관 PUBLIC LIBRARY SCIENCE
- 발행년도 2018
- URI http://www.dcollection.net/handler/ewha/000000151860
- 본문언어 영어
- Published As http://dx.doi.org/10.1371/journal.pone.0193321
초록/요약
Background/Purpose Acral melanoma is the most common type of melanoma in Asians, and usually results in a poor prognosis due to late diagnosis. We applied a convolutional neural network to dermoscopy images of acral melanoma and benign nevi on the hands and feet and evaluated its usefulness for the early diagnosis of these conditions. Methods A total of 724 dermoscopy images comprising acral melanoma (350 images from 81 patients) and benign nevi (374 images from 194 patients), and confirmed by histopathological examination, were analyzed in this study. To perform the 2-fold cross validation, we split them into two mutually exclusive subsets: half of the total image dataset was selected for training and the rest for testing, and we calculated the accuracy of diagnosis comparing it with the dermatologist's and non-expert's evaluation. Results The accuracy (percentage of true positive and true negative from all images) of the convolutional neural network was 83.51% and 80.23%, which was higher than the non-expert's evaluation (67.84%, 62.71%) and close to that of the expert (81.08%, 81.64%). Moreover, the convolutional neural network showed area-under-the-curve values like 0.8, 0.84 and Youden's index like 0.6795, 0.6073, which were similar score with the expert. Conclusion Although further data analysis is necessary to improve their accuracy, convolutional neural networks would be helpful to detect acral melanoma from dermoscopy images of the hands and feet.
more