Title: CBIR-based diagnosis of dermatology

Authors: G. Wiselin Jiji; A. Rajesh; P. Johnson Durairaj

Addresses: Department of Computer Science and Engineering, Dr. Sivanthi Aditananr College of Engineering, Tiruchendur-628215, India ' Vikram Sarabhai Space Centre, Indian Space Research Organization, Veli, Thiruvananthapuram, India ' Department of Computer Science and Engineering, Dr. Sivanthi Aditananr College of Engineering, Tiruchendur-628215, India

Abstract: In this work, we have presented a computer aided diagnosis approach to assist the diagnosis process of dermatological diseases. The proposed framework is used to retrieve the images from skin lesions repository which in turn facilitates the dermatologist during the diagnosis process. The system used eigen disease spaces of respective diseases to converge the search space more efficiently. The results proved using receiver operating characteristic (ROC) curve that the proposed architecture has high contribute to computer-aided diagnosis (CAD) of skin lesions. Experiments on a set of 1,210 images yielded a specificity of 98.44% and a sensitivity of 86%. Our empirical evaluation has a superior retrieval and diagnosis performance when compared to the performance of other recent works.

Keywords: computer-aided diagnosis; CAD; lesion segmentation; eigen disease space; classification; dermatology; component analysis; receiver operating characteristic; ROC; diagnosis framework; skin lesion; image retrieval.

DOI: 10.1504/IJBET.2022.123147

International Journal of Biomedical Engineering and Technology, 2022 Vol.38 No.4, pp.305 - 318

Received: 25 Sep 2018
Accepted: 21 Feb 2019

Published online: 01 Jun 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article