Combining Fine- and Coarse-Grained Classi fiers for Diabetic Retinopathy Detection

Muhammad Naseer Bajwa, Yoshinobu Taniguchi, Muhammad Imran Malik, Wolfgang Neumeier, Andreas Dengel, Sheraz Ahmed

In: Medical Image Understanding and Analysis. Medical Image Understanding and Analysis (MIUA-2019) 23rd Conference on Medical Image Understanding and Analysis July 24-26 Liverpool United Kingdom Springer 2019.


Visual artefacts of early diabetic retinopathy in retinal fundus images are usually small in size, inconspicuous, and scattered all over retina. Detecting diabetic retinopathy requires physicians to look at the whole image and fixate on some specific regions to locate potential biomarkers of the disease. Therefore, getting inspiration from ophthalmologist, we propose to combine coarse-grained classifiers that detect discriminating features from the whole images, with a recent breed of _ne-grained classifiers that discover and pay particular attention to pathologically significant regions. To evaluate the performance of this proposed ensemble, we used publicly available EyePACS and Messidor datasets. Extensive experimentation for binary, ternary and quaternary classification shows that this ensemble largely outperforms individual image classifiers as well as most of the published works in most training setups for diabetic retinopathy detection. Furthermore, the performance of fine-grained classifiers is found notably superior than coarse-grained image classifiers encouraging the development of task-oriented fine-grained classifiers modelled after specialist ophthalmologists.

MIUA19-Diabetic_Retinopathy_Detection-FinalVersion.pdf (pdf, 2 MB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz