30 April 2015 Ensemble approach for differentiation of malignant melanoma
Author Affiliations +
Proceedings Volume 9534, Twelfth International Conference on Quality Control by Artificial Vision 2015; 953415 (2015) https://doi.org/10.1117/12.2182799
Event: The International Conference on Quality Control by Artificial Vision 2015, 2015, Le Creusot, France
Abstract
Melanoma is the deadliest type of skin cancer, yet it is the most treatable kind depending on its early diagnosis. The early prognosis of melanoma is a challenging task for both clinicians and dermatologists. Due to the importance of early diagnosis and in order to assist the dermatologists, we propose an automated framework based on ensemble learning methods and dermoscopy images to differentiate melanoma from dysplastic and benign lesions. The evaluation of our framework on the recent and public dermoscopy benchmark (PH2 dataset) indicates the potential of proposed method. Our evaluation, using only global features, revealed that ensembles such as random forest perform better than single learner. Using random forest ensemble and combination of color and texture features, our framework achieved the highest sensitivity of 94% and specificity of 92%.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mojdeh Rastgoo, Mojdeh Rastgoo, Olivier Morel, Olivier Morel, Franck Marzani, Franck Marzani, Rafael Garcia, Rafael Garcia, } "Ensemble approach for differentiation of malignant melanoma ", Proc. SPIE 9534, Twelfth International Conference on Quality Control by Artificial Vision 2015, 953415 (30 April 2015); doi: 10.1117/12.2182799; https://doi.org/10.1117/12.2182799
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT


Back to Top