摘要
Artificial intelligence is becoming increasingly important in dermatology, with studies reporting accuracy matching or exceeding dermatologists for the diagnosis of skin lesions from clinical and dermoscopic images. However, real-world clinical validation is currently lacking. We review dermatological applications of deep learning, the leading artificial intelligence technology for image analysis, and discuss its current capabilities, potential failure modes, and challenges surrounding performance assessment and interpretability. We address the following three primary applications: (i) teledermatology, including triage for referral to dermatologists; (ii) augmenting clinical assessment during face-to-face visits; and (iii) dermatopathology. We discuss equity and ethical issues related to future clinical adoption and recommend specific standardization of metrics for reporting model performance.
学科与关键词
- Deep learning for dermatologists: Part II. Current applicationsPuri, Pranav; Comfere, Nneka*; Drage, Lisa A.; Shamim, Huma; Bezalel, Spencer A.; Pittelkow, Mark R.; Davis, Mark D. P.; Wang, Michael; Mangold, Aaron R.; Tollefson, Megha M.; Lehman, Julia S.; Meves, Alexander; Yiannias, James A.; Otley, Clark C.; Carter, Rickey E.; Sokumbi, Olayemi; Hall, Matthew R.; Bridges, Alina G.; Murphree, Dennis H.Journal of the American Academy of Dermatology, 2022, 87(6): 1352-1360.被引 27
- Principles, applications, and future of artificial intelligence in dermatologyOmiye, Jesutofunmi A.*; Gui, Haiwen; Daneshjou, Roxana; Cai, Zhuo Ran; Muralidharan, VijaythaFrontiers in Medicine, 2023, 10: 1278232.被引 13
- What is AI? Applications of artificial intelligence to dermatologyDu-Harpur, X.*; Watt, F. M.; Luscombe, N. M.; Lynch, M. D.British Journal of Dermatology, 2020, 183(3): 423-430.被引 127
