Automated detection of melanocytes related pigmented skin lesions:A clinical framework

Pathan, Sameena and Prabhu, G K and Siddalingaswamy, PC (2019) Automated detection of melanocytes related pigmented skin lesions:A clinical framework. Biomedical Signal Processing and Control, 51 (1). pp. 59-72. ISSN 1746-8094

[img] PDF
6291.pdf - Published Version
Restricted to Registered users only

Download (3MB) | Request a copy

Abstract

A clinically oriented Computer-Aided Diagnostic (CAD) system is of prime importance for the diagnosisof melanoma, since the deadly disease is associated with high morbidity and mortality. Unfortunately,the development of CAD tools is hampered by several issues, such as (i) smooth boundaries between thelesion and the surrounding skin, (ii) subtlety of features between the melanoma and non-melanoma skinlesions, and (iii) lack of reproducibility of CAD systems due to complexity. The proposed system aims toaddress the aforementioned issues. First, the lesion regions are localized by incorporating chroma baseddeformable models. Second, the lesion patterns are analyzed to detect various dermoscopic criteria.Further, a robust ensemble architecture is developed using dynamic classifier selection techniques todetect malignancy. Quantitative analysis is performed on two diverse datasets (ISBI and PH2) achievingan accuracy of 88% and 97%, sensitivity of 95% and 97% and specificity of 82% and 100% for ISBI and PH2datasets respectively.

Item Type: Article
Uncontrolled Keywords: Benign lesions, Dermoscopy, Malignant lesions, Melanocytic nevi, Pigment network Shape Color Texture
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: MIT Library
Date Deposited: 19 Mar 2019 06:57
Last Modified: 19 Mar 2019 06:57
URI: http://eprints.manipal.edu/id/eprint/153464

Actions (login required)

View Item View Item