Author, as appears in the article.: Escorcia-Gutierrez J; Torrents-Barrena J; Gamarra M; Madera N; Romero-Aroca P; Valls A; Puig D
Department: Enginyeria Informàtica i Matemàtiques
URV's Author/s: Escorcia Gutierrez, José Rafael / Puig Valls, Domènec Savi / Romero Aroca, Pedro / Valls Mateu, Aïda
Keywords: Support vector machines Retinal vasculature segmentation Feature selection Diabetic retinopathy Decision trees Blood-vessel segmentation Artificial neural networks support vector machines retinal vasculature segmentation matched-filter intelligence images gray-level fundus feature selection diabetic-retinopathy decision trees complications artificial neural networks algorithm
Abstract: Diabetic retinopathy (DR) is a complication of diabetes mellitus that appears in the retina. Clinitians use retina images to detect DR pathological signs related to the occlusion of tiny blood vessels. Such occlusion brings a degenerative cycle between the breaking off and the new generation of thinner and weaker blood vessels. This research aims to develop a suitable retinal vasculature segmentation method for improving retinal screening procedures by means of computer-aided diagnosis systems. The blood vessel segmentation methodology relies on an effective feature selection based on Sequential Forward Selection, using the error rate of a decision tree classifier in the evaluation function. Subsequently, the classification process is performed by three alternative approaches: artificial neural networks, decision trees and support vector machines. The proposed methodology is validated on three publicly accessible datasets and a private one provided by Hospital Sant Joan of Reus. In all cases we obtain an average accuracy above 96% with a sensitivity of 72% in the blood vessel segmentation process. Compared with the state-of-the-art, our approach achieves the same performance as other methods that need more computational power. Our method significantly reduces the number of features used in the segmentation process from 20 to 5 dimensions. The implementation of the three classifiers confirmed that the five selected features have a good effectiveness, independently of the classification algorithm.
Thematic Areas: Modeling and simulation Mechanics of materials Mathematics, interdisciplinary applications Materials science, multidisciplinary Ensino Engineering, multidisciplinary Engenharias iv Electrical and electronic engineering Computer science, information systems Computer science applications Biomaterials Astronomia / física
licence for use: https://creativecommons.org/licenses/by/3.0/es/
Author's mail: domenec.puig@urv.cat pedro.romero@urv.cat aida.valls@urv.cat
Author identifier: 0000-0002-0562-4205 0000-0002-7061-8987 0000-0003-3616-7809
Record's date: 2024-09-07
Papper version: info:eu-repo/semantics/publishedVersion
Link to the original source: https://www.techscience.com/cmc/v70n2/44677
Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
Papper original source: Cmc-Computers Materials & Continua. 70 (2): 2971-2989
APA: Escorcia-Gutierrez J; Torrents-Barrena J; Gamarra M; Madera N; Romero-Aroca P; Valls A; Puig D (2022). A feature selection strategy to optimize retinal vasculature segmentation. Cmc-Computers Materials & Continua, 70(2), 2971-2989. DOI: 10.32604/cmc.2022.020074
Article's DOI: 10.32604/cmc.2022.020074
Entity: Universitat Rovira i Virgili
Journal publication year: 2022
Publication Type: Journal Publications