Name
Abstract | ||
|---|---|---|
Detecting glaucoma progression is crucial for assessing the effectivity of the treatment. This paper describes three methods for detecting progression related changes in polarimetric images of the retinal nerve fiber layer (NFL), both on a global and on a local scale. Detecting global changes proved not to be feasible due to poor reproducibility of the measurements at the pixel level. Local progression on the other hand could be detected. A distribution based approach did not work, but locating specific areas with minimum size and minimum NFL decrease did give relevant results. The described algorithm yielded a TPR of 0.42 and an FPR of 0.095 on our datasets. It proved to be able to outline suspect areas that show NFL reduction. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1007/978-3-540-39903-2_75 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
global change | Computer vision,Reproducibility,Glaucoma,Polarimetry,Nerve fiber layer,Pattern recognition,Local scale,Computer science,Artificial intelligence,Pixel | Conference |
Volume | ISSN | Citations |
2879 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 2 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Koen A. Vermeer | 1 | 76 | 6.64 |
| N. J. Reus | 2 | 0 | 0.68 |
| Frans Vos | 3 | 106 | 11.97 |
| Hans Lemij | 4 | 7 | 2.05 |
| Albert M. Vossepoel | 5 | 126 | 18.43 |