Abstract | ||
---|---|---|
Microaneurysms are the diabetic retinopathy first sign and its early detection is crucial for blindness prevention. Several approaches can be found in literature for the automatic microaneurysm segmentation, but none of them has shown the required performance. In this study, a new approach is proposed based on an organization of agents enabling microaneurysms segmentation. This multiagent model is preceded by a preprocessing phase to allow the environment construction where agents are situated and interact. Then, microaneurysms segmentation emerges from agent interaction. With this study, competitive results comparing to more traditional algorithms were achieved, specially in detecting microaneurysms close to vessels. It seems that a very efficient system for the diabetic retinopathy diagnosis can be built using MAS mechanisms. |
Year | Venue | Keywords |
---|---|---|
2013 | IMAGE ANALYSIS AND RECOGNITION | Diabetic retinopathy, Fundus images, Image processing, Multi-agent system, Red lesions |
Field | DocType | Volume |
Diabetic retinopathy,Computer vision,Early detection,Pattern recognition,Segmentation,Computer science,Multi-agent system,Preprocessor,Artificial intelligence,Blindness,Microaneurysm | Conference | 7950 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
12 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Carla Pereira | 1 | 40 | 3.74 |
Diana Veiga | 2 | 15 | 5.75 |
Jason Mahdjoub | 3 | 13 | 2.06 |
Zahia Guessoum | 4 | 309 | 44.69 |
Luís Gonçalves | 5 | 45 | 6.19 |
Manuel Ferreira | 6 | 63 | 7.20 |
João Monteiro | 7 | 99 | 20.30 |