Deep Learning in Dermatology: A Systematic Review of Current Approaches, Outcomes, and Limitations

Hyeon Ki Jeong; Christine Park; Ricardo Henao; Meenal Kheterpal

doi:10.1016/j.xjidi.2022.100150

Deep Learning in Dermatology: A Systematic Review of Current Approaches, Outcomes, and Limitations

JID Innov. 2022 Aug 23;3(1):100150. doi: 10.1016/j.xjidi.2022.100150. eCollection 2023 Jan.

Authors

Hyeon Ki Jeong^{1

2}, Christine Park¹, Ricardo Henao², Meenal Kheterpal¹

Affiliations

¹ Duke Dermatology, Duke University School of Medicine, Durham, North Carolina, USA.
² Department of Biostatistics & Bioinformatics, Duke University School of Medicine, Durham, North Carolina, USA.

Abstract

Artificial intelligence (AI) has recently made great advances in image classification and malignancy prediction in the field of dermatology. However, understanding the applicability of AI in clinical dermatology practice remains challenging owing to the variability of models, image data, database characteristics, and variable outcome metrics. This systematic review aims to provide a comprehensive overview of dermatology literature using convolutional neural networks. Furthermore, the review summarizes the current landscape of image datasets, transfer learning approaches, challenges, and limitations within current AI literature and current regulatory pathways for approval of models as clinical decision support tools.

Keywords: AI, artificial intelligence; CDS, clinical decision-support; CNN, convolutional neural network; FDA, Food and Drug Administration; ISIC, International Skin Imaging Collaboration; ML, machine learning; MNIST, Modified National Institute of Standards and Technology; SVM, support vector machine; SaMD, Software as a Medical Device.

Publication types

Review