Efficient Pyramid Channel Attention Network for Pathological Myopia Recognition

TL;DR

This paper introduces EPCA-Net, an efficient neural network leveraging pathology priors and pyramid pooling for improved pathological myopia recognition from fundus images, demonstrating superior performance and effective use of pretraining.

Contribution

The paper proposes the EPCA module and EPCA-Net architecture that incorporate clinical pathology priors with pyramid pooling, and explores pretraining-and-finetuning for PM recognition.

Findings

EPCA-Net outperforms state-of-the-art methods in PM recognition.

Pretraining-and-finetuning achieves competitive results with fewer parameters.

Constructed PM-fundus benchmark for evaluation.

Abstract

Pathological myopia (PM) is the leading ocular disease for impaired vision worldwide. Clinically, the characteristic of pathology distribution in PM is global-local on the fundus image, which plays a significant role in assisting clinicians in diagnosing PM. However, most existing deep neural networks focused on designing complex architectures but rarely explored the pathology distribution prior of PM. To tackle this issue, we propose an efficient pyramid channel attention (EPCA) module, which fully leverages the potential of the clinical pathology prior of PM with pyramid pooling and multi-scale context fusion. Then, we construct EPCA-Net for automatic PM recognition based on fundus images by stacking a sequence of EPCA modules. Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters. In addition, we construct a PM recognition benchmark termed PM-fundus by collecting fundus images of PM from publicly available datasets. The comprehensive experiments demonstrate the superiority of our EPCA-Net over state-of-the-art methods in the PM recognition task. The results also show that our method based on the pretraining-and-finetuning paradigm achieves competitive performance through comparisons to part of previous methods based on traditional fine-tuning paradigm with fewer tunable parameters, which has the potential to leverage more natural image foundation models to address the PM recognition task in limited medical data regime.