Can automated dermoscopy image analysis instruments provide added benefit for the dermatologist? A study comparing the results of three systems
- 1 November 2007
- journal article
- research article
- Published by Oxford University Press (OUP) in British Journal of Dermatology
- Vol. 157 (5), 926-933
- https://doi.org/10.1111/j.1365-2133.2007.08168.x
Abstract
Instruments designed to provide computer program-driven diagnosis of dermoscopic images of lesions are now commercially available. Multiple publications tout the improved diagnostic accuracy of these instruments compared with that of clinicians.Our aim was to evaluate the actual usefulness of these instruments for dermatologists practising in a pigmented lesion clinic.Over a 4-month period we subjected lesions, which were being evaluated in one of our clinics, to automated computer diagnosis performed by three commercially available instruments. We intentionally included three groups of lesions: group 1 lesions were suspicious melanocytic lesions that were scheduled to be excised; group 2 lesions were nonmelanocytic lesions; group 3 lesions were clinically obvious melanomas. The automated diagnoses provided by the instruments were compared with the dermoscopy diagnosis of experienced physicians and with histopathology.We included a total of 107 lesions. One imaging system's computer algorithm was unable to analyse one third of the lesions. All three instruments' computer algorithms were able to identify the clinically obvious melanomas (group 3) correctly. However, all three systems tended to overdiagnose by incorrectly classifying most seborrhoeic keratoses (group 2) as potential malignant lesions. Concerning the suspect melanocytic lesions (group 1), which are precisely the lesions for which a dermatologist would welcome a second opinion, we found significant variability in the diagnostic accuracy of the instruments tested. However, all three systems providing computer-assisted diagnosis had a tendency to overdiagnose benign melanocytic lesions as potential melanomas.Although the image analysis systems tested by us correctly identified the clinically obvious melanomas, they were not able to discriminate between most dysplastic naevi and early malignant melanoma. Thus, for the moment these computer-assisted diagnostic imaging machines provide little to no added benefit for the experienced dermatologist/dermoscopist.Keywords
This publication has 19 references indexed in Scilit:
- Evaluation of digital dermoscopy in a pigmented lesion clinic: Clinician versus computer assessment of malignancy riskJournal of the American Academy of Dermatology, 2007
- Melanocytic skin lesions and pregnancy: digital dermoscopy analysisSkin Research and Technology, 2007
- Dysplastic naevus vs. in situ melanoma: digital dermoscopy analysisBritish Journal of Dermatology, 2005
- Digital image analysis for diagnosis of cutaneous melanoma. Development of a highly effective computer algorithm based on analysis of 837 melanocytic lesionsBritish Journal of Dermatology, 2004
- Validation of segmentation techniques for digital dermoscopySkin Research and Technology, 2002
- Automated diagnosis of pigmented skin lesionsInternational Journal of Cancer, 2002
- Dermoscopic diagnosis by a trained clinician vs. a clinician with minimal dermoscopy training vs. computer-aided diagnosis of 341 pigmented skin lesions: a comparative studyBritish Journal of Dermatology, 2002
- Digital dermoscopy analysis for automated diagnosis of pigmented skin lesionsClinics in Dermatology, 2002
- Segmentation of digitized dermatoscopic images by two-dimensional color clusteringIEEE Transactions on Medical Imaging, 1999
- Techniques for a structural analysis of dermatoscopic imageryComputerized Medical Imaging and Graphics, 1998