Department of Preventive Medicine, Shantou University Medical College, Shantou, China.
School of Mathematics, Sun Yat-Sen University, Guangzhou, Guangdong, China.
Transl Vis Sci Technol. 2024 Apr 2;13(4):8. doi: 10.1167/tvst.13.4.8.
The assessment of retinal image (RI) quality holds significant importance in both clinical trials and large datasets, because suboptimal images can potentially conceal early signs of diseases, thereby resulting in inaccurate medical diagnoses. This study aims to develop an automatic method for Retinal Image Quality Assessment (RIQA) that incorporates visual explanations, aiming to comprehensively evaluate the quality of retinal fundus images (RIs).
We developed an automatic RIQA system, named Swin-MCSFNet, utilizing 28,792 RIs from the EyeQ dataset, as well as 2000 images from the EyePACS dataset and an additional 1,000 images from the OIA-ODIR dataset. After preprocessing, including cropping black regions, data augmentation, and normalization, a Swin-MCSFNet classifier based on the Swin-Transformer for multiple color-space fusion was proposed to grade the quality of RIs. The generalizability of Swin-MCSFNet was validated across multiple data centers. Additionally, for enhanced interpretability, a Score-CAM-generated heatmap was applied to provide visual explanations.
Experimental results reveal that the proposed Swin-MCSFNet achieves promising performance, yielding a micro-receiver operating characteristic (ROC) of 0.93 and ROC scores of 0.96, 0.81, and 0.96 for the "Good," "Usable," and "Reject" categories, respectively. These scores underscore the accuracy of RIQA based on Swin-MCSF in distinguishing among the three categories. Furthermore, heatmaps generated across different RIQA classification scores and various color spaces suggest that regions in the retinal images from multiple color spaces contribute significantly to the decision-making process of the Swin-MCSFNet classifier.
Our study demonstrates that the proposed Swin-MCSFNet outperforms other methods in experiments conducted on multiple datasets, as evidenced by the superior performance metrics and insightful Score-CAM heatmaps.
This study constructs a new retinal image quality evaluation system, which will contribute to the subsequent research of retinal images.
视网膜图像（RI）质量评估在临床试验和大型数据集方面都具有重要意义，因为图像质量不佳可能会掩盖疾病的早期迹象，从而导致不准确的医学诊断。本研究旨在开发一种自动视网膜图像质量评估（RIQA）方法，该方法结合了视觉解释，旨在全面评估眼底图像（RIs）的质量。
我们开发了一种自动 RIQA 系统，名为 Swin-MCSFNet，该系统使用了来自 EyeQ 数据集的 28792 张 RI，以及来自 EyePACS 数据集的 2000 张图像和来自 OIA-ODIR 数据集的另外 1000 张图像。在进行预处理（包括裁剪黑色区域、数据增强和归一化）后，我们提出了一种基于 Swin-Transformer 的 Swin-MCSFNet 分类器，用于融合多种颜色空间，以对 RIs 的质量进行分级。Swin-MCSFNet 的泛化能力在多个数据中心得到了验证。此外，为了提高可解释性，我们应用了 Score-CAM 生成的热图来提供视觉解释。
实验结果表明，所提出的 Swin-MCSFNet 具有出色的性能，在微接收器操作特征（ROC）方面的得分为 0.93，对于“良好”、“可用”和“拒绝”三个类别，ROC 得分分别为 0.96、0.81 和 0.96。这些分数表明，基于 Swin-MCSF 的 RIQA 在区分这三个类别方面具有很高的准确性。此外，在不同的 RIQA 分类得分和多种颜色空间生成的热图表明，来自多个颜色空间的视网膜图像区域对 Swin-MCSFNet 分类器的决策过程有重要贡献。
我们的研究表明，所提出的 Swin-MCSFNet 在多个数据集上的实验中表现优于其他方法，这表现在优越的性能指标和有见地的 Score-CAM 热图上。
邓惠中
