Extraction and reconstruction of retinal vasculature
Information about retinal vasculature morphology is used in grading the severity and progression of diabetic retinopathy. An image analysis system can help ophthalmologists make accurate and efficient diagnoses. This paper presents the development of an image processing algorithm for detecting and r...
| Main Authors: | , , , |
|---|---|
| Format: | Citation Index Journal |
| Language: | English |
| Published: |
2007
|
| Subjects: | |
| Online Access: | http://scholars.utp.edu.my/id/eprint/317/ http://scholars.utp.edu.my/id/eprint/317/1/paper.pdf |
| _version_ | 1848658958191951872 |
|---|---|
| author | M.H.A., Fadzil L.I., Izhar P.A., Venkatachalam T.V.N., Karunakar |
| author_facet | M.H.A., Fadzil L.I., Izhar P.A., Venkatachalam T.V.N., Karunakar |
| author_sort | M.H.A., Fadzil |
| building | UTP Institutional Repository |
| collection | Online Access |
| description | Information about retinal vasculature morphology is used in grading the severity and progression of diabetic retinopathy. An image analysis system can help ophthalmologists make accurate and efficient diagnoses. This paper presents the development of an image processing algorithm for detecting and reconstructing retinal vasculature. The detection of the vascular structure is achieved by image enhancement using contrast limited adaptive histogram equalization followed by the extraction of the vessels using bottom-hat morphological transformation. For reconstruction of the complete retinal vasculature, a region growing technique based on first-order Gaussian derivative is developed. The technique incorporates both gradient magnitude change and average intensity as the homogeneity criteria that enable the process to adapt to intensity changes and intensity spread over the vasculature region. The reconstruction technique reduces the required number of seeds to near optimal for the region growing process. It also overcomes poor performance of current seed-based methods, especially with low and inconsistent contrast images as normally seen in vasculature regions of fundus images. Simulations of the algorithm on 20 test images from the DRIVE database show that it outperforms many other published methods and achieved an accuracy range (ability to detect both vessel and non-vessel pixels) of 0.91-0.95, a sensitivity range (ability to detect vessel pixels) of 0.91-0.95 and a specificity range (ability to detect non-vessel pixels) of 0.88-0.94. © 2007 Informa UK Ltd.
|
| first_indexed | 2025-11-13T07:22:48Z |
| format | Citation Index Journal |
| id | oai:scholars.utp.edu.my:317 |
| institution | Universiti Teknologi Petronas |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-13T07:22:48Z |
| publishDate | 2007 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | oai:scholars.utp.edu.my:3172017-01-19T08:27:07Z http://scholars.utp.edu.my/id/eprint/317/ Extraction and reconstruction of retinal vasculature M.H.A., Fadzil L.I., Izhar P.A., Venkatachalam T.V.N., Karunakar TK Electrical engineering. Electronics Nuclear engineering Information about retinal vasculature morphology is used in grading the severity and progression of diabetic retinopathy. An image analysis system can help ophthalmologists make accurate and efficient diagnoses. This paper presents the development of an image processing algorithm for detecting and reconstructing retinal vasculature. The detection of the vascular structure is achieved by image enhancement using contrast limited adaptive histogram equalization followed by the extraction of the vessels using bottom-hat morphological transformation. For reconstruction of the complete retinal vasculature, a region growing technique based on first-order Gaussian derivative is developed. The technique incorporates both gradient magnitude change and average intensity as the homogeneity criteria that enable the process to adapt to intensity changes and intensity spread over the vasculature region. The reconstruction technique reduces the required number of seeds to near optimal for the region growing process. It also overcomes poor performance of current seed-based methods, especially with low and inconsistent contrast images as normally seen in vasculature regions of fundus images. Simulations of the algorithm on 20 test images from the DRIVE database show that it outperforms many other published methods and achieved an accuracy range (ability to detect both vessel and non-vessel pixels) of 0.91-0.95, a sensitivity range (ability to detect vessel pixels) of 0.91-0.95 and a specificity range (ability to detect non-vessel pixels) of 0.88-0.94. © 2007 Informa UK Ltd. 2007 Citation Index Journal PeerReviewed application/pdf en http://scholars.utp.edu.my/id/eprint/317/1/paper.pdf M.H.A., Fadzil and L.I., Izhar and P.A., Venkatachalam and T.V.N., Karunakar (2007) Extraction and reconstruction of retinal vasculature. [Citation Index Journal] http://www.scopus.com/inward/record.url?eid=2-s2.0-36248987203&partnerID=40&md5=ab6c97ebb9d65a20e31efa8998b529b7 10.1080/03091900601111201 10.1080/03091900601111201 10.1080/03091900601111201 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering M.H.A., Fadzil L.I., Izhar P.A., Venkatachalam T.V.N., Karunakar Extraction and reconstruction of retinal vasculature |
| title | Extraction and reconstruction of retinal vasculature
|
| title_full | Extraction and reconstruction of retinal vasculature
|
| title_fullStr | Extraction and reconstruction of retinal vasculature
|
| title_full_unstemmed | Extraction and reconstruction of retinal vasculature
|
| title_short | Extraction and reconstruction of retinal vasculature
|
| title_sort | extraction and reconstruction of retinal vasculature |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://scholars.utp.edu.my/id/eprint/317/ http://scholars.utp.edu.my/id/eprint/317/ http://scholars.utp.edu.my/id/eprint/317/ http://scholars.utp.edu.my/id/eprint/317/1/paper.pdf |