상위피인용논문
Seung Seog Han 1,8, Ilwoo Park 2,8, Sung Eun Chang 3,8, Woohyung Lim 4, Myoung Shin Kim 5, Gyeong Hun Park 6, Je Byeong Chae 7, Chang Hun Huh 7, Jung-Im Na 7
1I Dermatology Clinic, Seoul, Korea
2Department of Radiology, Chonnam National University Medical School and Hospital, Gwangju, Korea
3Department of Dermatology, Asan Medical Center, Ulsan University College of Medicine, Seoul, Korea
4LG Sciencepark, Seoul, Korea
5Department of Dermatology, Sanggye Paik Hospital, Inje University College of Medicine, Seoul, Korea
6Department of Dermatology, Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Dongtan, Korea
7Department of Dermatology, Seoul National University Bundang Hospital, Seongnam, Korea
8These authors contributed equally to this work as co-first authors.
Correspondence: Jung-Im Na
Abstract
Although deep learning algorithms have demonstrated expert-level performance, previous efforts were mostly binary classifications of limited disorders. We trained an algorithm with 220,680 images of 174 disorders and validated it using Edinburgh (1,300 images; 10 disorders) and SNU datasets (2,201 images; 134 disorders). The algorithm could accurately predict malignancy, suggest primary treatment options, render multi-class classification among 134 disorders, and improve the performance of medical professionals. The area under the curves for malignancy detection were 0.928 ± 0.002 (Edinburgh) and 0.937 ± 0.004 (SNU). The area under the curves of primary treatment suggestion (SNU) were 0.828 ± 0.012, 0.885 ± 0.006, 0.885 ± 0.006, and 0.918 ± 0.006 for steroids, antibiotics, antivirals, and antifungals, respectively. For multi-class classification, the mean top-1 and top-5 accuracies were 56.7 ± 1.6% and 92.0 ± 1.1% (Edinburgh) and 44.8 ± 1.2% and 78.1 ± 0.3% (SNU), respectively. With the assistance of our algorithm, the sensitivity and specificity of 47 clinicians (21 dermatologists and 26 dermatology residents) for malignancy prediction (SNU; 240 images) were improved by 12.1% (P < 0.0001) and 1.1% (P < 0.0001), respectively. The malignancy prediction sensitivity of 23 non-medical professionals was significantly increased by 83.8% (P < 0.0001). The top-1 and top-3 accuracies of four doctors in the multi-class classification of 134 diseases (SNU; 2,201 images) were increased by 7.0% (P = 0.045) and 10.1% (P = 0.0020), respectively. The results suggest that our algorithm may serve as augmented intelligence that can empower medical professionals in diagnostic dermatology.
논문정보
관련 링크
연구자 키워드
연구자 ID
관련분야 연구자보기
소속기관 논문보기
관련분야 논문보기