Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China.
Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China.
Artif Intell Med. 2022 Apr;126:102259. doi: 10.1016/j.artmed.2022.102259. Epub 2022 Feb 25.
As one of the most common diabetic complications, diabetic retinopathy (DR) can cause retinal damage, vision loss and even blindness. Automated DR grading technology has important clinical significance, which can help ophthalmologists achieve rapid and early diagnosis. With the popularity of deep learning, DR grading based on the convolutional neural networks (CNNs) has become the mainstream method. Unfortunately, although the CNN-based method can achieve satisfactory diagnostic accuracy, it lacks significant clinical information. In this paper, a lesion-attention pyramid network (LAPN) is presented. The pyramid network integrates the subnetworks with different resolutions to get multi-scale features. In order to take the lesion regions in the high-resolution image as the diagnostic evidence, the low-resolution network calculates the lesion activation map (using the weakly-supervised localization method) and guides the high-resolution network to concentrate on the lesion regions. Furthermore, a lesion attention module (LAM) is designed to capture the complementary relationship between the high-resolution features and the low-resolution features, and to fuse the lesion activation map. Experiment results show that the proposed scheme outperforms other existing approaches, and the proposed method can provide lesion activation map with lesion consistency as an additional evidence for clinical diagnosis.
作为最常见的糖尿病并发症之一，糖尿病视网膜病变（DR）可导致视网膜损伤、视力丧失甚至失明。自动 DR 分级技术具有重要的临床意义，可以帮助眼科医生实现快速和早期诊断。随着深度学习的普及，基于卷积神经网络（CNNs）的 DR 分级已成为主流方法。不幸的是，尽管基于 CNN 的方法可以达到令人满意的诊断准确性，但它缺乏重要的临床信息。本文提出了一种病变注意金字塔网络（LAPN）。该金字塔网络集成了具有不同分辨率的子网，以获取多尺度特征。为了将高分辨率图像中的病变区域作为诊断证据，低分辨率网络计算病变激活图（使用弱监督定位方法），并指导高分辨率网络集中于病变区域。此外，设计了一个病变注意模块（LAM），以捕获高分辨率特征和低分辨率特征之间的互补关系，并融合病变激活图。实验结果表明，所提出的方案优于其他现有方法，并且该方法可以提供具有病变一致性的病变激活图，作为临床诊断的附加证据。
