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.

翻译：病理性近视（PM）是全球范围内导致视力损伤的主要眼科疾病。临床上，PM在眼底图像上的病理分布特征呈现全局-局部性，这对辅助临床医生诊断PM具有重要作用。然而，现有大多数深度神经网络集中于设计复杂架构，却鲜少探索PM的病理分布先验知识。为解决此问题，我们提出高效金字塔通道注意力（EPCA）模块，该模块通过金字塔池化和多尺度上下文融合，充分利用了PM临床病理先验知识的潜力。随后，通过堆叠一系列EPCA模块，我们构建了基于眼底图像的自动PM识别网络EPCA-Net。此外，受近期预训练-微调范式的启发，我们尝试通过冻结预训练的自然图像模型，并将EPCA及其他注意力模块作为适配器，将其适配于PM识别任务。进一步，我们通过收集公开数据集中的PM眼底图像，构建了名为PM-fundus的PM识别基准。综合实验表明，我们的EPCA-Net在PM识别任务上优于现有最优方法。结果还显示，基于预训练-微调范式的方法通过与传统微调范式部分先前方法的比较，以更少的可调参数取得了具有竞争力的性能，这为在有限医学数据场景下利用更多自然图像基础模型解决PM识别任务提供了潜在可能。