Simpler, Faster, More Accurate Melanocytic Lesion Segmentation Through MEDS
Authors:
- 1 February 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 61 (2) , 557-565
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
Funding Information
- Università degli Studi di Padova
This publication has 32 references indexed in Scilit:
- Where's the naevus? Inter‐operator variability in the localization of melanocytic lesion borderSkin Research and Technology, 2011
- Fast spatial averaging: an efficient algorithm for 2D mean filteringThe Journal of Supercomputing, 2011
- Watershed segmentation of dermoscopy images using a watershed techniqueSkin Research and Technology, 2010
- Lesion border detection in dermoscopy imagesComputerized Medical Imaging and Graphics, 2009
- Border detection in dermoscopy images using statistical region mergingSkin Research and Technology, 2008
- Unsupervised border detection in dermoscopy imagesSkin Research and Technology, 2007
- Automatic lesion boundary detection in dermoscopy images using gradient vector flow snakesSkin Research and Technology, 2005
- Validation of segmentation techniques for digital dermoscopySkin Research and Technology, 2002
- The incidence of malignant melanoma in the United States: Issues as we approach the 21st centuryJournal of the American Academy of Dermatology, 1996
- The ABCD rule of dermatoscopyJournal of the American Academy of Dermatology, 1994