Title :
Simpler, Faster, More Accurate Melanocytic Lesion Segmentation Through MEDS
Author :
Peruch, Francesco ; Bogo, Federica ; Bonazza, M. ; Cappelleri, Vincenzo-Maria ; Peserico, E.
Author_Institution :
Dipt. di Ing. dell´Inf., Univ. degli Studi di Padova, Padua, Italy
Abstract :
We present a new technique for melanocytic lesion segmentation, Mimicking Expert Dermatologists´ Segmentations (MEDS), and extensive tests of its accuracy, speed, and robustness. MEDS combines a thresholding scheme reproducing the cognitive process of dermatologists with a number of optimizations that may be of independent interest. MEDS is simple, with a single parameter tuning its “tightness”. It is extremely fast, segmenting medium-resolution images in a fraction of a second even with the modest computational resources of a cell phone-an improvement of an order of magnitude or more over state-of-the-art techniques. And it is extremely accurate: very experienced dermatologists disagree with its segmentations less than they disagree with the segmentations of state-of-the-art techniques, and in fact less than they disagree with the segmentations of dermatologists of moderate experience.
Keywords :
cognition; image segmentation; medical image processing; mobile handsets; skin; MEDS; cell phone; cognitive process; computational resources; medium-resolution image segmentations; melanocytic lesion segmentation; mimicking expert dermatologist segmentations; state-of-the-art techniques; Accuracy; Histograms; Image color analysis; Image segmentation; Lesions; Robustness; Skin; Dermatoscopy; melanoma; segmentation;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2013.2283803