Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal Images
The automatic detection, segmentation, localization, and evaluation of the optic disc, macula, exudates, and hemorrhages are very important for diagnosing retinal diseases. One of the difficulties in detecting such regions of interest (RoIs) with computer vision is their symmetries, e.g., between th...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-03-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2073-8994/10/3/73 |
| _version_ | 1798034015369822208 |
|---|---|
| author | Dan Popescu Loretta Ichim |
| author_facet | Dan Popescu Loretta Ichim |
| author_sort | Dan Popescu |
| collection | DOAJ |
| description | The automatic detection, segmentation, localization, and evaluation of the optic disc, macula, exudates, and hemorrhages are very important for diagnosing retinal diseases. One of the difficulties in detecting such regions of interest (RoIs) with computer vision is their symmetries, e.g., between the optic disc and exudates and also between exudates and hemorrhages. This paper proposes an original, intelligent, and high-performing image processing system for the simultaneous detection and segmentation of retinal RoIs. The basic principles of the method are image decomposition in small boxes and local texture analysis. The processing flow contains three phases: preprocessing, learning, and operating. As a first novelty, we propose proper feature selection based on statistical analysis in confusion matrices for different feature types (extracted from a co-occurrence matrix, fractal type, and local binary patterns). Mainly, the selected features are chosen to differentiate between similar RoIs. The second novelty consists of local classifier fusion. To this end, the local classifiers associated with features are grouped in global classifiers corresponding to the RoIs. The local classifiers are based on minimum distances to the representatives of classes and the global classifiers are based on confidence intervals, weights, and a voting scheme. A deep convolutional neural network, based on supervised learning, for blood vessel segmentation is proposed in order to improve the RoI detection performance. Finally, the experimental results on real images from different databases demonstrate the rightness of our methodologies and algorithms. |
| first_indexed | 2024-04-11T20:38:22Z |
| format | Article |
| id | doaj.art-ebece475bc004eea94ff0c99b505b3fa |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-11T20:38:22Z |
| publishDate | 2018-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-ebece475bc004eea94ff0c99b505b3fa2022-12-22T04:04:18ZengMDPI AGSymmetry2073-89942018-03-011037310.3390/sym10030073sym10030073Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal ImagesDan Popescu0Loretta Ichim1Department of Control Engineering and Industrial Informatics, University Politehnica of Bucharest, 060042 Bucharest, RomaniaDepartment of Control Engineering and Industrial Informatics, University Politehnica of Bucharest, 060042 Bucharest, RomaniaThe automatic detection, segmentation, localization, and evaluation of the optic disc, macula, exudates, and hemorrhages are very important for diagnosing retinal diseases. One of the difficulties in detecting such regions of interest (RoIs) with computer vision is their symmetries, e.g., between the optic disc and exudates and also between exudates and hemorrhages. This paper proposes an original, intelligent, and high-performing image processing system for the simultaneous detection and segmentation of retinal RoIs. The basic principles of the method are image decomposition in small boxes and local texture analysis. The processing flow contains three phases: preprocessing, learning, and operating. As a first novelty, we propose proper feature selection based on statistical analysis in confusion matrices for different feature types (extracted from a co-occurrence matrix, fractal type, and local binary patterns). Mainly, the selected features are chosen to differentiate between similar RoIs. The second novelty consists of local classifier fusion. To this end, the local classifiers associated with features are grouped in global classifiers corresponding to the RoIs. The local classifiers are based on minimum distances to the representatives of classes and the global classifiers are based on confidence intervals, weights, and a voting scheme. A deep convolutional neural network, based on supervised learning, for blood vessel segmentation is proposed in order to improve the RoI detection performance. Finally, the experimental results on real images from different databases demonstrate the rightness of our methodologies and algorithms.http://www.mdpi.com/2073-8994/10/3/73biomedical image processingretinal image segmentationfeature selectiontexture analysisconvolutional neural networkoptic discmaculaexudateshemorrhages |
| spellingShingle | Dan Popescu Loretta Ichim Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal Images Symmetry biomedical image processing retinal image segmentation feature selection texture analysis convolutional neural network optic disc macula exudates hemorrhages |
| title | Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal Images |
| title_full | Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal Images |
| title_fullStr | Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal Images |
| title_full_unstemmed | Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal Images |
| title_short | Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal Images |
| title_sort | intelligent image processing system for detection and segmentation of regions of interest in retinal images |
| topic | biomedical image processing retinal image segmentation feature selection texture analysis convolutional neural network optic disc macula exudates hemorrhages |
| url | http://www.mdpi.com/2073-8994/10/3/73 |
| work_keys_str_mv | AT danpopescu intelligentimageprocessingsystemfordetectionandsegmentationofregionsofinterestinretinalimages AT lorettaichim intelligentimageprocessingsystemfordetectionandsegmentationofregionsofinterestinretinalimages |