Background: Computer-aided diagnosis of skin lesions is a growing area of research, but its application to\nnonmelanoma skin cancer (NMSC) is relatively under-studied. The purpose of this review is to synthesize the\nresearch that has been conducted on automated detection of NMSC using digital images and to assess the\nquality of evidence for the diagnostic accuracy of these technologies.\nMethods: Eight databases (PubMed, Google Scholar, Embase, IEEE Xplore, Web of Science, SpringerLink, ScienceDirect,\nand the ACM Digital Library) were searched to identify diagnostic studies of NMSC using image-based machine learning\nmodels. Two reviewers independently screened eligible articles. The level of evidence of each study was evaluated using\na five tier rating system, and the applicability and risk of bias of each study was assessed using the Quality Assessment of\nDiagnostic Accuracy Studies tool.\nResults: Thirty-nine studies were reviewed. Twenty-four models were designed to detect basal cell carcinoma, two were\ndesigned to detect squamous cell carcinoma, and thirteen were designed to detect both. All studies were conducted in\nsilico. The overall diagnostic accuracy of the classifiers, defined as concordance with histopathologic diagnosis, was high,\nwith reported accuracies ranging from 72 to 100% and areas under the receiver operating characteristic curve ranging\nfrom 0.832 to 1. Most studies had substantial methodological limitations, but several were robustly designed and\npresented a high level of evidence.\nConclusion: Most studies of image-based NMSC classifiers report performance greater than or equal to the reported\ndiagnostic accuracy of the average dermatologist, but relatively few studies have presented a high level of evidence.\nClinical studies are needed to assess whether these technologies can feasibly be implemented as a real-time aid for\nclinical diagnosis of NMSC.
Loading....