Best Practices for Clinical Skin Image Acquisition in Translational Artificial Intelligence Research

• Published in: Journal of investigative dermatology Vol. 143; no. 7; pp. 1127 - 1132
• Main Authors: Phung, Michelle, Muralidharan, Vijaytha, Rotemberg, Veronica, Novoa, Roberto Andres, Chiou, Albert Sean, Sadée, Christoph Y., Rapaport, Bailie, Yekrang, Kiana, Bitz, Jared, Gevaert, Olivier, Ko, Justin Meng, Daneshjou, Roxana
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.07.2023
• Subjects: Algorithms; Artificial Intelligence; Dermatologists; Dermoscopy - methods; Humans; Melanoma - pathology; Skin Neoplasms - diagnostic imaging; Skin Neoplasms - pathology; AI
• ISSN: 0022-202X; 1523-1747; 1523-1747
• DOI: 10.1016/j.jid.2023.02.035

Recent advances in artificial intelligence research have led to an increase in the development of algorithms for detecting malignancies from clinical and dermoscopic images of skin diseases. These methods are dependent on the collection of training and testing data. There are important considerations when acquiring skin images and data for translational artificial intelligence research. In this paper, we discuss the best practices and challenges for light photography image data collection, covering ethics, image acquisition, labeling, curation, and storage. The purpose of this work is to improve artificial intelligence for malignancy detection by supporting intentional data collection and collaboration between subject matter experts, such as dermatologists and data scientists.