The Performance of SolarScan

Results of the 2016 International Skin Imaging Collaboration International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images

“…8 In 2005 Menzies et al reported on the performance of SolarScan® and included a reader study of 78 lesions (13 melanomas, 63 nevi, and 2 lentigines). 11 The computer classifier had a sensitivity of 85% and specificity of 65%; this compared to a mean sensitivity and specificity of 79.5% and 50.8% for the 13 human readers. Differences in study design make comparisons of our computer algorithm results to these data challenging, highlighting the importance of creating open datasets like ours.…”

Skin Cancer Diagnosis by Lesion, Physician, and Examination Type

“…The meta-analysis included 100 studies (eTable 3 in Supplement 1). These studies were conducted in Asia, Europe (the majority), North America, Oceania, and South America, and were published between 1988 and 2021 (eTable 4 in Supplement 1). Only 4 studies reported participants’ race and ethnicity in the datasets, and among these, most lesions involved White participants (eTable 5 in Supplement 1).…”

Diagnostic Accuracy of Novel Optical Imaging Techniques for Melanoma Detection: A Systematic Review and Meta‐Analysis

“…The PRISMA flowchart [11] is shown in Figure 1. Initially, we identified 16,239 records via database searching, of which 136 studies [23–158] were found eligible. In addition, via citation searching, we found 5 more eligible studies [159–163].…”