Computer-aided classification of melanocytic lesions using dermoscopic images
- 1 November 2015
- journal article
- Published by Elsevier BV in Journal of the American Academy of Dermatology
- Vol. 73 (5), 769-776
- https://doi.org/10.1016/j.jaad.2015.07.028
Abstract
Computer-assisted diagnosis of dermoscopic images of skin lesions has the potential to improve melanoma early detection. We sought to evaluate the performance of a novel classifier that uses decision forest classification of dermoscopic images to generate a lesion severity score. 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. 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 < .001) and specificity was lower (P < .001) than that of clinicians. This is a retrospective study using existing images primarily chosen for biopsy by a dermatologist. The size of the test set is small. Our classifier may aid clinicians in deciding if a skin lesion should be biopsied and can easily be incorporated into a portable tool (that uses no proprietary equipment) that could aid clinicians in noninvasively evaluating cutaneous lesions.Keywords
This publication has 9 references indexed in Scilit:
- Clinical performance of the Nevisense system in cutaneous melanoma detection: an international, multicentre, prospective and blinded clinical trial on efficacy and safetyBritish Journal of Dermatology, 2014
- Performance of a dermoscopy-based computer vision system for the diagnosis of pigmented skin lesions compared with visual evaluation by experienced dermatologistsArtificial Intelligence in Medicine, 2014
- Evidence-Based DermoscopyDermatologic Clinics, 2013
- On the Comparison of Diagnosis and Management of Melanoma Between Dermatologists and MelaFindJAMA Dermatology, 2013
- Does skin cancer screening save lives?Cancer, 2012
- Impact of digital dermoscopy analysis on the decision to follow up or to excise a pigmented skin lesion: a multicentre studySkin Research and Technology, 2011
- The Performance of MelaFindArchives of Dermatology, 2011
- Even patients with changing moles face long dermatology appointment wait-times: A study of simulated patient calls to dermatologistsJournal of the American Academy of Dermatology, 2006
- The Measurement of Observer Agreement for Categorical DataBiometrics, 1977