Computer-aided classification of melanocytic lesions using dermoscopic images

• Published in: Journal of the American Academy of Dermatology 2015-11, Vol.73 (5), p.769-776
• Main Authors: Ferris, Laura K., MD, PhD, Harkes, Jan A., MS, Gilbert, Benjamin, MS, Winger, Daniel G., MS, Golubets, Kseniya, MD, MHS, Akilov, Oleg, MD, PhD, Satyanarayanan, Mahadev, PhD
• Format: Article
• Language: English
• Subjects: basal cell carcinoma; computer-assisted diagnosis; Decision Trees; Dermatology; dermoscopy; Dermoscopy - methods; Female; Humans; Image Interpretation, Computer-Assisted - methods; information technology; machine learning; Male; melanoma; Melanoma - classification; Melanoma - pathology; skin cancer; Skin Neoplasms - classification; Skin Neoplasms - pathology
• ISSN: 0190-9622; 1097-6787
• DOI: 10.1016/j.jaad.2015.07.028

Background Computer-assisted diagnosis of dermoscopic images of skin lesions has the potential to improve melanoma early detection. Objective We sought to evaluate the performance of a novel classifier that uses decision forest classification of dermoscopic images to generate a lesion severity score. Methods Severity scores were calculated for 173 dermoscopic images of skin lesions with known histologic diagnosis (39 melanomas, 14 nonmelanoma skin cancers, and 120 benign lesions). A threshold score was used to measure classifier sensitivity and specificity. A reader study was conducted to compare the sensitivity and specificity of the classifier with those of 30 dermatology clinicians. Results The classifier sensitivity for melanoma was 97.4%; specificity was 44.2% in a test set of images. In the reader study, the classifier's sensitivity to melanoma was higher ( P