Paper: | MP-P6.7 |
Session: | Biomedical Imaging I |
Time: | Monday, September 17, 14:30 - 17:10 |
Presentation: |
Poster
|
Title: |
AUTOMATIC DETECTION AND DIAGNOSIS OF DIABETIC RETINOPATHY |
Authors: |
Katia Estabridis; University of California, Irvine | | |
| Rui J. P. de Figueiredo; University of California, Irvine | | |
Abstract: |
A CAD system has been developed for diabetic retinopathy (DR). The system detects the fovea, blood vessel network, optic disk, as well as lesions associated with DR. The diagnosis is based on the number, type and location of abnormalities relative to the fovea. Detection of normal retinal components was done as part of the overall system development and the work has been reported in literature. Lesion detection is accomplished through the process of eliminating the normal retinal components. Remaining objects in the image include the background and abnormalities if present. The image is partitioned in 2 regions: fovea and non-fovea, which have different backgrounds. Filtering and statistical adaptive thresholding are applied to the remaining data. The diagnostics and final system’s layer is a knowledge-based system. |