Suman Supriya, Tiwari Anil Kumar, Sachan Shreya, Singh Kuldeep, Meena Seema, Kumar Sakshi
Interdisciplinary Research Division: Smart Healthcare, Indian Institute of Technology, Jodhpur, 342030, Rajasthan, India.
Department of Electrical Engineering, Indian Institute of Technology Jodhpur, 342030, Rajasthan, India.
Comput Methods Programs Biomed. 2025 Apr;261:108585. doi: 10.1016/j.cmpb.2025.108585. Epub 2025 Jan 15.
Hypertensive Retinopathy (HR) is a retinal manifestation resulting from persistently elevated blood pressure. Severity grading of HR is essential for patient risk stratification, effective management, progression monitoring, timely intervention, and minimizing the risk of vision impairment. Computer-aided diagnosis and artificial intelligence (AI) systems play vital roles in the diagnosis and grading of HR. Over the years, very limited research has been conducted for the grading of HR. Nevertheless, there are no publicly available datasets for HR grading. Moreover, one of the key challenges observed is high-class imbalance.
To address these issues, in this paper, we develop "HRSG: Expert-Annotated Hypertensive Retinopathy Severity Grading" dataset, classifying HR severity into four distinct classes: normal, mild, moderate, and severe. Further, to enhance the grading performance on limited datasets, this paper introduces a novel hybrid architecture that combines the strengths of pretrained ResNet-50 via transfer learning, and a modified Vision Transformer (ViT) architecture enhanced with a combination of global self-attention and locality self-attention mechanisms. The locality self-attention addresses the common issue of a lack of inductive bias in ViT architecture. This architecture effectively captures both local and global contextual information, resulting in a robust and resilient classification model. To overcome class imbalance, Decouple Representation and Classifier (DRC) - based training approach is proposed. This method improves the model's ability to learn effective features while preserving the original dataset's distribution, leading to better diagnostic accuracy.
Performance evaluation results show the competence of the proposed method in accurately grading the severity of HR. The proposed method achieved an average accuracy of 0.9688, sensitivity of 0.9435, specificity of 0.9766, F1-score of 0.9442, and precision of 0.9474. The comparative results indicate that the proposed method outperforms existing HR methods, state-of-the-art CNN models, and baseline pretrained ViT models. Additionally, we compared our method with a CNNViT model, which combines a shallow CNN architecture with 3 convolution blocks consisting of a convolution layer, a batch normalization layer, a max pooling layer, and lightweight ViT architecture, due to limited datasets. In comparison with the CNNViT, the proposed method achieved superior performance, demonstrating its effectiveness.
The experimental results demonstrate the efficacy of the proposed method in accurately grading HR severity.
高血压性视网膜病变（HR）是血压持续升高导致的一种视网膜表现。HR的严重程度分级对于患者风险分层、有效管理、病情进展监测、及时干预以及降低视力损害风险至关重要。计算机辅助诊断和人工智能（AI）系统在HR的诊断和分级中发挥着重要作用。多年来，针对HR分级的研究非常有限。然而，目前尚无公开可用的HR分级数据集。此外，观察到的一个关键挑战是高度的类别不平衡。
为了解决这些问题，在本文中，我们开发了“HRSG：专家标注的高血压性视网膜病变严重程度分级”数据集，将HR严重程度分为四个不同类别：正常、轻度、中度和重度。此外，为了提高在有限数据集上的分级性能，本文引入了一种新颖的混合架构，该架构通过迁移学习结合了预训练的ResNet - 50的优势，以及一种经过改进的视觉Transformer（ViT）架构，该架构通过全局自注意力和局部自注意力机制的组合得到增强。局部自注意力解决了ViT架构中缺乏归纳偏置的常见问题。这种架构有效地捕捉了局部和全局上下文信息，从而产生了一个强大且有弹性的分类模型。为了克服类别不平衡，提出了基于解耦表示和分类器（DRC）的训练方法。该方法提高了模型学习有效特征的能力，同时保留了原始数据集的分布，从而获得了更好的诊断准确性。
性能评估结果表明了所提出方法在准确分级HR严重程度方面的能力。所提出的方法实现了平均准确率为0.9688、灵敏度为0.9435、特异性为0.9766、F1分数为0.9442以及精确率为0.9474。比较结果表明，所提出的方法优于现有的HR方法、当前最先进的卷积神经网络（CNN）模型和基线预训练的ViT模型。此外，由于数据集有限，我们将我们的方法与一个CNNViT模型进行了比较，该模型结合了一个具有3个由卷积层、批归一化层、最大池化层组成的卷积块的浅层CNN架构和轻量级ViT架构。与CNNViT相比，所提出的方法取得了更好的性能，证明了其有效性。
实验结果证明了所提出方法在准确分级HR严重程度方面的有效性。
