Retinal disease screening through local binary patterns

Project facts

Project promoter:
Polytechnic University of Valencia
Project Number:
ES07-0013
Target groups
Researchers or scientists
Status:
Completed
Initial project cost:
€8,300
Final project cost:
€8,264
From EEA Grants:
€ 8,264
The project is carried out in:
Spain

Description

Retinal image classification for detecting the presence of diseases is mainly a pattern recognition task. Ophthalmologists are trained to recognize these lesions, so automatic screening programs that reduce this heavy workload are highly beneficial. This project is focused on automatic detection of different retinal lesions and their later classification in order to be included in a diagnosis aid system. Its main goal is to develop a system that can detect, through image processing, the specific patterns of the most common causes of blindness in current society. During the project development, different texture descriptors will be tested together with classifiers, to investigate the discrimination capabilities in the texture of the fundus images. The main focus will lie in exploring the performance of Local Binary Patterns. The donor partner, University of Stavanger, has a long experience in texture analysis, both image textures in general and for classifying different biomedical images. This expertise can be useful for analyzing and classifying the different possible diseases that can be seen from the fundus images.

Summary of project results

The main goal of the project was to develop a system that could detect, through image processing, the specific patterns of some diseases that are among the most common causes of blindness in current society: diabetic retinopathy (DR) and age-related macular degeneration (AMD), in order to be able to carry out an automatic screening of these diseases. During the two months stay of the Spanish predoctoral researcher at the University of Stavanger, image analysis algorithms were studied and implemented that maximize detection probability and minimize false positives. Texture descriptors and classifiers were tested to investigate the discrimination capabilities in the texture of fundus images, the main focus lying in exploring Local Binary Patterns as a descriptor for fundus images. The system was validated using databases of healthy and pathological patients analysed by expert ophtalmologists. Experiments made obtained excellent results in discriminating AMD pathologies, and between good and excellent those detecting DR. Project results were presented to groups of the Department of Computer Science and Electrical Engineering of the University of Stavanger, and a paper to be sent to a peer reviewed journal is in preparation. Thanks to have provided insight into a new technique, different applications, where this technique could be applied, were identified, for example to detect the optic cup or to determinate the age through the analysis of facial images. The possibility of a postdoc stay at the host institution is forecasted.

Summary of bilateral results

The donor partner, University of Stavanger, has a long experience in texture analysis, both image textures in general and for classifying different biomedical images. This expertise was very useful for analysing and classifying the different possible diseases that can be seen from the fundus images. Joint cooperation led to reliable experiments and results. The predoctoral researcher beneficiary presented her own and the Spanish institution’s work to the biomedical data analysis group from the host institution as well as the results obtained during the project. Main relations were established between the beneficiary, members of the Spanish Labhuman at the Polytechnic University of Valencia, and the heads of the biomedical data analysis group at University of Stavanger. A joint paper is in preparation in order to disseminate the results, to be sent to the journal “Computer Methods and Programs in Biomedicine”, and further cooperation opportunities have been commented, such as a postdoc stay by the beneficiary at the Norwegian institution, after the lecture of her Thesis.