Title

Modified watershed technique and post-processing for segmentation of skin lesions in dermoscopy images

Abstract

In previous research, a watershed-based algorithm was shown to be useful for automatic lesion segmentation in dermoscopy images, and was tested on a set of 100 benign and malignant melanoma images with the average of three sets of dermatologist-drawn borders used as the ground truth, resulting in an overall error of 15.98%. In this study, to reduce the border detection errors, a neural network classifier was utilized to improve the first-pass watershed segmentation; a novel "edge object value (EOV) threshold" method was used to remove large light blobs near the lesion boundary; and a noise removal procedure was applied to reduce the peninsula-shaped false-positive areas. As a result, an overall error of 11.09% was achieved.

Department(s)

Electrical and Computer Engineering

Second Department

Chemistry

Sponsor(s)

National Institute of Health (U.S.)

Keywords and Phrases

Malignant Melanoma; Neural Network; Segmentation; Watershed

Library of Congress Subject Headings

Image processing

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2011 Elsevier, All rights reserved.


Share

 
COinS