nnMobileNet: Rethinking CNN for Retinopathy Research

TL;DR

This paper presents an optimized MobileNet CNN architecture that outperforms vision transformer models in retinal disease detection tasks, offering a more efficient alternative for medical diagnostics.

Contribution

We redesigned and optimized MobileNet for retinal disease detection, demonstrating it surpasses ViT models in accuracy and efficiency on multiple benchmarks.

Findings

Optimized MobileNet outperforms ViT models in RD benchmarks.

Modified CNN achieves higher accuracy in diabetic retinopathy grading.

Code available for reproducibility and further research.

Abstract

Over the past few decades, convolutional neural networks (CNNs) have been at the forefront of the detection and tracking of various retinal diseases (RD). Despite their success, the emergence of vision transformers (ViT) in the 2020s has shifted the trajectory of RD model development. The leading-edge performance of ViT-based models in RD can be largely credited to their scalability-their ability to improve as more parameters are added. As a result, ViT-based models tend to outshine traditional CNNs in RD applications, albeit at the cost of increased data and computational demands. ViTs also differ from CNNs in their approach to processing images, working with patches rather than local regions, which can complicate the precise localization of small, variably presented lesions in RD. In our study, we revisited and updated the architecture of a CNN model, specifically MobileNet, to enhance its utility in RD diagnostics. We found that an optimized MobileNet, through selective modifications, can surpass ViT-based models in various RD benchmarks, including diabetic retinopathy grading, detection of multiple fundus diseases, and classification of diabetic macular edema. The code is available at https://github.com/Retinal-Research/NN-MOBILENET