A Feature Selection Strategy to Optimize Retinal Vasculature Segmentation

作     者：Jose Escorcia-Gutierrez Jordina Torrents-Barrena Margarita Gamarra Natasha Madera Pedro Romero-Aroca Aida Valls Domenec Puig 

作者机构：Electronic and Telecommunications Engineering ProgramUniversidad Autónoma del CaribeBarranquilla080001Colombia Department of Computational Science and ElectronicUniversidad de la CostaCUCBarranquilla080001Colombia Ophthalmology ServiceUniversitari Hospital Sant JoanInstitut de Investigacio Sanitaria Pere VirgiliReus43201Spain Departament d’Enginyeria Informàtica i MatemàtiquesEscola Tècnica Superior d’EnginyeriaUniversitat Rovira i VirgiliTarragona43007Spain 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第70卷第2期

页      面：2971-2989页

核心收录：

学科分类：07[理学] 08[工学] 071102[理学-系统分析与集成] 0831[工学-生物医学工程（可授工学、理学、医学学位）] 0710[理学-生物学] 0711[理学-系统科学] 1002[医学-临床医学] 1001[医学-基础医学(可授医学、理学学位)] 0837[工学-安全科学与工程] 0805[工学-材料科学与工程（可授工学、理学学位）] 081101[工学-控制理论与控制工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 081103[工学-系统工程] 

基　　金：This work has been funded by the research project PI18/00169 from Instituto de Salud Carlos III&FEDER funds.University Rovira i.Virgili also provided funds with Project 2019PFR-B2-61 

主　　题：Diabetic retinopathy artificial neural networks decision trees support vector machines feature selection retinal vasculature segmentation 

摘      要：Diabetic retinopathy (DR) is a complication of diabetesmellitus thatappears in the retina. Clinitians use retina images to detect DR pathologicalsigns related to the occlusion of tiny blood vessels. Such occlusion brings adegenerative cycle between the breaking off and the new generation of thinnerand weaker blood vessels. This research aims to develop a suitable retinalvasculature segmentation method for improving retinal screening proceduresby means of computer-aided diagnosis systems. The blood vessel segmentationmethodology relies on an effective feature selection based on SequentialForward Selection, using the error rate of a decision tree classifier in theevaluation function. Subsequently, the classification process is performed bythree alternative approaches: artificial neural networks, decision trees andsupport vector machines. The proposed methodology is validated on threepublicly accessible datasets and a private one provided by Hospital Sant Joanof Reus. In all cases we obtain an average accuracy above 96% with a sensitivityof 72% in the blood vessel segmentation process. Compared with the state-ofthe-art, our approach achieves the same performance as other methods thatneed more computational *** method significantly reduces the numberof features used in the segmentation process from 20 to 5 dimensions. Theimplementation of the three classifiers confirmed that the five selected featureshave a good effectiveness, independently of the classification algorithm.