The detection of malignant lesions in dermoscopicimages by using automatic diagnostic tools can help in reducingmortality from melanoma. In this paper, we describea fully-automatic algorithm for skin lesion segmentation indermoscopic images. The proposed approach is highly accuratewhen dealing with benign lesions, while the detection accuracysignificantly decreases when melanoma images are segmented.This particular behavior lead us to consider geometrical andcolor features extracted from the output of our algorithm forclassifying melanoma images, achieving promising results.
Melanoma detection using delaunay triangulation
BLOISI, Domenico Daniele;
2016-01-01
Abstract
The detection of malignant lesions in dermoscopicimages by using automatic diagnostic tools can help in reducingmortality from melanoma. In this paper, we describea fully-automatic algorithm for skin lesion segmentation indermoscopic images. The proposed approach is highly accuratewhen dealing with benign lesions, while the detection accuracysignificantly decreases when melanoma images are segmented.This particular behavior lead us to consider geometrical andcolor features extracted from the output of our algorithm forclassifying melanoma images, achieving promising results.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
