Abstract | ||
---|---|---|
Retinal arteriovenous nicking (AVN) assessment has been considered a very important indicator of cardiovascular and cerebrovascular diseases. A computerized method to infer the AVN presence in retinal images could increase the reproducibility and accuracy of this analysis that for now has been done by ophthalmologists in a subjective and qualitative manner. Therefore, a new approach is proposed for the AVN assessment in color fundus images. First the algorithm segments the blood vessels by means of a multi-scale line detector. The arteriovenous cross points are then detected and classified as AVN presence or absence with an SVM. The proposed approach is clearly efficient in separating normal cases from the evident or severe AVN cases. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-11755-3_36 | IMAGE ANALYSIS AND RECOGNITION, ICIAR 2014, PT II |
Keywords | Field | DocType |
Arteriovenous nicking, Fundus images, Image processing | Computer vision,Pattern recognition,Computer science,Image processing,Fundus (eye),Artificial intelligence,Retinal,Arteriovenous nicking,Retinal arteriovenous nicking | Conference |
Volume | ISSN | Citations |
8815 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Carla Pereira | 1 | 40 | 3.74 |
Diana Veiga | 2 | 15 | 5.75 |
Luís Gonçalves | 3 | 45 | 6.19 |
Manuel Ferreira | 4 | 63 | 7.20 |