Abstract:
DR and DME are the leading causes of permanent blindness in working-age people. Automatic DR and DME grading helps ophthalmologists customize patient treatments. However, prior works either grade DR or DME, ignoring the correlation between DR and its complication, DME.
Macula and soft hard exhaust annotations are also used for grading. Automatic grading methods with image-level supervision are preferable because annotations are expensive. We present a novel cross-disease attention network (CANet) to jointly grade DR and DME by exploring their internal relationship with only image-level supervision.
Our disease-specific attention module learns useful features for individual diseases, and the disease-dependent attention module captures the internal relationship between the two diseases.
We integrate these two attention modules in a deep network to produce disease-specific and disease-dependent features and maximize DR and DME grading performance. Our network is evaluated on two public benchmark datasets, ISBI 2018 IDRiD challenge and Messidor. Our method performs best on the ISBI 2018 IDRiD challenge dataset and Messidor dataset.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
