AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT
As retinopathies continue to be major causes of visual loss and blindness worldwide, early detection and management of these diseases will help achieve significant reduction of blindness cases. However, an efficient automatic retinal vessel segmentation approach remains a challenge. Since efficient...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Slovenian Society for Stereology and Quantitative Image Analysis
2016-07-01
|
| Series: | Image Analysis and Stereology |
| Subjects: | |
| Online Access: | http://www.ias-iss.org/ojs/IAS/article/view/1421 |
| _version_ | 1817970895001485312 |
|---|---|
| author | Temitope Mapayi Jules-Raymond Tapamo Serestina Viriri Adedayo Adio |
| author_facet | Temitope Mapayi Jules-Raymond Tapamo Serestina Viriri Adedayo Adio |
| author_sort | Temitope Mapayi |
| collection | DOAJ |
| description | As retinopathies continue to be major causes of visual loss and blindness worldwide, early detection and management of these diseases will help achieve significant reduction of blindness cases. However, an efficient automatic retinal vessel segmentation approach remains a challenge. Since efficient vessel network detection is a very important step needed in ophthalmology for reliable retinal vessel characterization, this paper presents study on the combination of difference image and K-means clustering for the segmentation of retinal vessels. Stationary points in the vessel center-lines are used to model the detection of twists in the vessel segments. The combination of arc-chord ratio with stationary points is used to compute tortuosity index. Experimental results show that the proposed K-means combined with difference image achieved a robust segmentation of retinal vessels. A maximum average accuracy of 0.9556 and a maximum average sensitivity of 0.7581 were achieved on DRIVE database while a maximum average accuracy of 0.9509 and a maximum average sensitivity of 0.7666 were achieved on STARE database. When compared with the previously proposed techniques on DRIVE and STARE databases, the proposed technique yields higher mean sensitivity and mean accuracy rates in the same range of very good specificity. In a related development, a non-normalized tortuosity index that combined distance metric and the vessel twist frequency proposed in this paper also achieved a strong correlation of 0.80 with the expert ground truth. |
| first_indexed | 2024-04-13T20:39:43Z |
| format | Article |
| id | doaj.art-4cbf8a6251ca468a9123aa561c55fbe5 |
| institution | Directory Open Access Journal |
| issn | 1580-3139 1854-5165 |
| language | English |
| last_indexed | 2024-04-13T20:39:43Z |
| publishDate | 2016-07-01 |
| publisher | Slovenian Society for Stereology and Quantitative Image Analysis |
| record_format | Article |
| series | Image Analysis and Stereology |
| spelling | doaj.art-4cbf8a6251ca468a9123aa561c55fbe52022-12-22T02:30:54ZengSlovenian Society for Stereology and Quantitative Image AnalysisImage Analysis and Stereology1580-31391854-51652016-07-0135211713510.5566/ias.1421952AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENTTemitope Mapayi0Jules-Raymond Tapamo1Serestina Viriri2Adedayo Adio3University of KwaZulu-NatalUniversity of KwaZulu-NatalUniversity of KwaZulu-NatalUniversity of Port HarcourtAs retinopathies continue to be major causes of visual loss and blindness worldwide, early detection and management of these diseases will help achieve significant reduction of blindness cases. However, an efficient automatic retinal vessel segmentation approach remains a challenge. Since efficient vessel network detection is a very important step needed in ophthalmology for reliable retinal vessel characterization, this paper presents study on the combination of difference image and K-means clustering for the segmentation of retinal vessels. Stationary points in the vessel center-lines are used to model the detection of twists in the vessel segments. The combination of arc-chord ratio with stationary points is used to compute tortuosity index. Experimental results show that the proposed K-means combined with difference image achieved a robust segmentation of retinal vessels. A maximum average accuracy of 0.9556 and a maximum average sensitivity of 0.7581 were achieved on DRIVE database while a maximum average accuracy of 0.9509 and a maximum average sensitivity of 0.7666 were achieved on STARE database. When compared with the previously proposed techniques on DRIVE and STARE databases, the proposed technique yields higher mean sensitivity and mean accuracy rates in the same range of very good specificity. In a related development, a non-normalized tortuosity index that combined distance metric and the vessel twist frequency proposed in this paper also achieved a strong correlation of 0.80 with the expert ground truth.http://www.ias-iss.org/ojs/IAS/article/view/1421clusteringdifference imagek-meansretinal vesselsegmentationtortuosity |
| spellingShingle | Temitope Mapayi Jules-Raymond Tapamo Serestina Viriri Adedayo Adio AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT Image Analysis and Stereology clustering difference image k-means retinal vessel segmentation tortuosity |
| title | AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT |
| title_full | AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT |
| title_fullStr | AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT |
| title_full_unstemmed | AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT |
| title_short | AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT |
| title_sort | automatic retinal vessel detection and tortuosity measurement |
| topic | clustering difference image k-means retinal vessel segmentation tortuosity |
| url | http://www.ias-iss.org/ojs/IAS/article/view/1421 |
| work_keys_str_mv | AT temitopemapayi automaticretinalvesseldetectionandtortuositymeasurement AT julesraymondtapamo automaticretinalvesseldetectionandtortuositymeasurement AT serestinaviriri automaticretinalvesseldetectionandtortuositymeasurement AT adedayoadio automaticretinalvesseldetectionandtortuositymeasurement |