BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading

Abstract

Diabetic retinopathy (DR) is a common retinal disease that leads to blindness. For diagnosis purposes, DR image grading aims to provide automatic DR grade classification, which is not addressed in conventional research methods of binary DR image classification. Small objects in the eye images, like lesions and microaneurysms, are essential to DR grading in medical imaging, but they could easily be influenced by other objects. To address these challenges, we propose a new deep learning architecture, called BiRA-Net, which combines the attention model for feature extraction and bilinear model for fine-grained classification. Furthermore, in considering the distance between different grades of different DR categories, we propose a new loss function, called grading loss, which leads to improved training convergence of the proposed approach. Experimental results are provided to demonstrate the superior performance of the proposed approach.

Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images

“…Finally, we report in table 2 the performance of our best model (using as a base loss NULS and Atomic Sub-Task modeling) in comparison with the techniques proposed in [3], [18], and [23], in the test set of both Eyepacs and Messidor. We also provide confusion matrices for the Eyepacs test set in Fig.…”

“…For performance assessment, we apply as the main metric of interest the quadratic-weighted kappa score (quad-kappa), which is typically used to assess inter-observer variability, and is very popular metric in this task. As further measures of correlation, we also analyze Average of Classification Accuracy (ACA, the mean of the diagonal in a normalized confusion matrix [23]) and the Kendallτ coefficient. We also report the mean Area Under the Receiver-Operator Curve in its multi-class extension, after considering each possible class pair [10].…”

“…For comparison purposes, we select three other recent techniques that introduce methods specifically developed to solve the DR grading task: DR|graduate [3], Bilinear Attention Net for DR Grading (Bira-Net) [23], and Quadratic-Weighted Kappa Loss (QWKL) [18].…”

Deep Learning and Its Application in Diabetic Retinopathy Screening

“…In Ref. [47], a new architecture called BiRA-Net was presented. In this deep neural network, the attention model used for feature extraction and bilinear model used for finegrained classification were combined.…”

Multi-Scale Attention Network for Diabetic Retinopathy Classification

“…The Zoom-in-Net generates suspicious areas by employing an attention mechanism. Another bilinear learning strategy [43] with an attention mechanism was also utilised for DR classification. The authors employed an attention approach to boost the meaningful features while suppress the weak ones.…”