Basal cell carcinoma (BCC) is the most common skin cancer, with over 2 million cases diagnosed annually in the United States. Conventionally, BCC is diagnosed by naked eye examination and dermoscopy. Suspicious lesions are either removed or biopsied for histopathological confirmation, thus lowering the specificity of non-invasive BCC diagnosis. Recently, reflectance confocal microscopy (RCM), a non-invasive diagnostic technique that can image skin lesions at cellular level resolution, has shown to improve specificity in BCC diagnosis and reduced the number needed to biopsy by 2-to-3 times. In this study, we developed and evaluated a deep learning-based artificial intelligence model to automatically detect BCC in RCM images. The proposed model achieved an area under the curve (AUC) for the receiver operator characteristic (ROC) curve of 89.7% (stack-level) and 88.3% (lesion level), a performance on par with that of RCM experts. Furthermore, the model achieved an AUC of 86.1% on a held-out test set from international collaborators, demonstrating the reproducibility and generalizability of the proposed automated diagnostic approach. These results provide a clear indication that the clinical deployment of decision support systems for the detection of BCC in RCM images has the potential for optimizing the evaluation and diagnosis of skin cancer patients.
Keywords: Artificial Intelligence; Basal Cell Carcinoma; Reflectance Confocal Microscopy.
Copyright © 2021 The Authors. Published by Elsevier Inc. All rights reserved.