Diabetic Retinopathy (DR) is a primary cause of blindness, necessitating early detection and diagnosis. This paper focuses on referable DR classification to enhance the applicability of the proposed method in clinical practice. We develop an advanced cross-learning DR classification method leveraging transfer learning and cross-attention mechanisms. The proposed method employs the Swin U-Net architecture to segment lesion maps from DR fundus images. The Swin U-Net segmentation model, enriched with DR lesion insights, is transferred to generate a lesion map. Both the fundus image and its segmented lesion map are used as complementary inputs for the classification model. A cross-attention mechanism is deployed to improve the model's ability to capture fine-grained details from the input pairs. Our experiments, utilizing two public datasets, FGADR and EyePACS, demonstrate a superior accuracy of 94.6%, surpassing current state-of-the-art methods by 4.4%. To this end, we aim for the proposed method to be seamlessly integrated into clinical workflows, enhancing accuracy and efficiency in identifying referable DR.

翻译：糖尿病视网膜病变（DR）是导致失明的主要原因，需要早期检测与诊断。本文聚焦于可转诊DR分类，以提升所提方法在临床实践中的适用性。我们开发了一种利用迁移学习与交叉注意力机制的先进交叉学习DR分类方法。该方法采用Swin U-Net架构从DR眼底图像中分割病灶图。融合了DR病灶知识的Swin U-Net分割模型被迁移用于生成病灶图。眼底图像及其分割病灶图均作为分类模型的互补输入。通过部署交叉注意力机制，增强了模型从输入对中捕获细粒度细节的能力。我们在FGADR和EyePACS两个公开数据集上的实验表明，该方法取得了94.6%的优异准确率，较当前最优方法提升了4.4%。为此，我们期望所提方法能无缝集成到临床工作流中，提升可转诊DR识别的准确性与效率。