Automated skin lesion screening – a new approach
Authors:
- R. H. BarbourRBR. H. Barbour
- 1 February 2001
- journal article
- research article
- Published by Wolters Kluwer Health in Melanoma Research
- Vol. 11 (1) , 31-35
Abstract
Automated melanoma diagnosis is a popular focus of research, with numerous papers describing techniques and results. In our study, we identified two possible problems with the current method of automated diagnosis, where systems are intended to reproduce histopathology results. We propose a new method of identifying problematic skin lesions, namely attempting to reproduce algorithmically the perceptions of dermatologists as to whether the lesion should be excised. In the best case, our initial model reproduced the decision of dermatologists in over 80% of cases. These results suggest that reproducing the decision to excise may be a valuable adjunct to current methodology.Keywords
This publication has 10 references indexed in Scilit:
- Automated melanoma diagnosis: where are we at?Skin Research and Technology, 2000
- Computerized system to enhance the clinical diagnosis of pigmented cutaneous malignanciesInternational Journal of Dermatology, 1999
- Digital videomicroscopy and image analysis with automatic classification for detection of thin melanomasMelanoma Research, 1999
- Melanoma: Accuracy of clinical diagnosisAustralasian Journal of Dermatology, 1998
- Primary care in dermatology: Whose role should it be?Journal of the American Academy of Dermatology, 1996
- Computer image analysis in the diagnosis of melanomaJournal of the American Academy of Dermatology, 1994
- Neural network diagnosis of malignant melanoma from color imagesIEEE Transactions on Biomedical Engineering, 1994
- Detection of skin tumor boundaries in color imagesIEEE Transactions on Medical Imaging, 1993
- Automatic detection of irregular borders in melanoma and other skin tumorsComputerized Medical Imaging and Graphics, 1992
- Early Detection of Malignant Melanoma: The Role of Physician Examination and Self-Examination of the SkinCA: A Cancer Journal for Clinicians, 1985