Loading [a11y]/accessibility-menu.js
Diabetic Retinopathy Grading based on a Sparse Network Fusion of Heterogeneous ConvNeXt Models with Category Attention | IEEE Conference Publication | IEEE Xplore
Scheduled Maintenance: On Monday, 27 January, the IEEE Xplore Author Profile management portal will undergo scheduled maintenance from 9:00-11:00 AM ET (1400-1600 UTC). During this time, access to the portal will be unavailable. We apologize for any inconvenience.

Diabetic Retinopathy Grading based on a Sparse Network Fusion of Heterogeneous ConvNeXt Models with Category Attention


Abstract:

Diabetic retinopathy (DR) is an eye disease caused by high blood sugar levels that may damage vessels in the retina, leading to partial or complete loss of vision in late...Show More

Abstract:

Diabetic retinopathy (DR) is an eye disease caused by high blood sugar levels that may damage vessels in the retina, leading to partial or complete loss of vision in later stages. In recent years, convolutional neural networks (CNN) have been used to help diagnose the DR severity. However, due to the slight differences between each class and the imbalanced nature of the datasets, standard CNNs often struggle to distinguish accurately between different grades of DR. To overcome these challenges, we propose combining a novel CNN model (ConvNeXt) with category-attention blocks incorporated at multiple levels of the architecture. This generates different models that can effectively extract fine-grained features and minimize the impact of dataset imbalance. Finally, we introduce a Sparse Network Fusion technique that learns to combine the outputs of all models to consolidate their individual decisions. Extensive experiments on the challenging DDR dataset show that our proposal achieves a new state-of-the-art performance, improving by about 3% grading accuracy compared with existing methods.
Date of Conference: 23-25 July 2023
Date Added to IEEE Xplore: 22 August 2023
ISBN Information:
Conference Location: Hamamatsu, Japan

References

References is not available for this document.