The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, China.
Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, 315300, China.
Med Image Anal. 2022 Oct;81:102534. doi: 10.1016/j.media.2022.102534. Epub 2022 Jul 10.
Diabetic retinopathy (DR) is one of the most important complications of diabetes. Accurate segmentation of DR lesions is of great importance for the early diagnosis of DR. However, simultaneous segmentation of multi-type DR lesions is technically challenging because of 1) the lack of pixel-level annotations and 2) the large diversity between different types of DR lesions. In this study, first, we propose a novel Poisson-blending data augmentation (PBDA) algorithm to generate synthetic images, which can be easily utilized to expand the existing training data for lesion segmentation. We perform extensive experiments to recognize the important attributes in the PBDA algorithm. We show that position constraints are of great importance and that the synthesis density of one type of lesion has a joint influence on the segmentation of other types of lesions. Second, we propose a convolutional neural network architecture, named DSR-U-Net++ (i.e., DC-SC residual U-Net++), for the simultaneous segmentation of multi-type DR lesions. Ablation studies showed that the mean area under precision recall curve (AUPR) for all four types of lesions increased by >5% with PBDA. The proposed DSR-U-Net++ with PBDA outperformed the state-of-the-art methods by 1.7%-9.9% on the Indian Diabetic Retinopathy Image Dataset (IDRiD) and 67.3% on the e-ophtha dataset with respect to mean AUPR. The developed method would be an efficient tool to generate large-scale task-specific training data for other medical anomaly segmentation tasks.
糖尿病性视网膜病变（DR）是糖尿病最重要的并发症之一。准确地对 DR 病变进行分割对 DR 的早期诊断具有重要意义。然而，由于 1）缺乏像素级注释，2）不同类型的 DR 病变之间存在很大的差异，因此同时对多类型的 DR 病变进行分割在技术上具有挑战性。在这项研究中，首先，我们提出了一种新颖的泊松混合数据增强（PBDA）算法来生成合成图像，这可以很容易地用于扩展现有的病变分割训练数据。我们进行了广泛的实验来识别 PBDA 算法中的重要属性。我们表明，位置约束非常重要，而且一种病变的合成密度对其他类型病变的分割有共同影响。其次，我们提出了一种卷积神经网络架构，称为 DSR-U-Net++（即 DC-SC 残差 U-Net++），用于同时分割多类型的 DR 病变。消融研究表明，使用 PBDA 后，所有四种类型病变的平均精度召回曲线下面积（AUPR）提高了>5%。在印度糖尿病视网膜病变图像数据集（IDRiD）上，我们提出的具有 PBDA 的 DSR-U-Net++比最先进的方法在平均 AUPR 上的性能提高了 1.7%-9.9%；在 e-ophtha 数据集上的性能提高了 67.3%。所开发的方法将是一种有效的工具，可用于生成其他医学异常分割任务的大规模特定于任务的训练数据。
