Shi Hanfeng, Wei Jiaqi, Jin Richu, Peng Jiaxin, Wang Xingyue, Hu Yan, Zhang Xiaoqing, Liu Jiang
Research Institute of Trustworthy Autonomous Systems and Department of Computer Science, Southern University of Science and Technology, Shenzhen, China.
Research Institute of Trustworthy Autonomous Systems and Department of Computer Science, Southern University of Science and Technology, Shenzhen, China; Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
Comput Med Imaging Graph. 2024 Dec;118:102463. doi: 10.1016/j.compmedimag.2024.102463. Epub 2024 Nov 19.
Parkinson's disease (PD) is a leading neurodegenerative disease globally. Precise and objective PD diagnosis is significant for early intervention and treatment. Recent studies have shown significant correlations between retinal structure information and PD based on optical coherence tomography (OCT) images, providing another potential means for early PD recognition. However, how to exploit the retinal structure information (e.g., thickness and mean intensity) from different retinal layers to improve PD recognition performance has not been studied before. Motivated by the above observations, we first propose a structural prior knowledge extraction (SPKE) module to obtain the retinal structure feature maps; then, we develop a structure-guided-and-adaption attention (SGDA) module to fully leverage the potential of different retinal layers based on the extracted retinal structure feature maps. By embedding SPKE and SGDA modules at the low stage of deep neural networks (DNNs), a retinal structure-guided-and-adaption network (RSGA-Net) is constructed for early PD recognition based on OCT images. The extensive experiments on a clinical OCT-PD dataset demonstrate the superiority of RSGA-Net over state-of-the-art methods. Additionally, we provide a visual analysis to explain how retinal structure information affects the decision-making process of DNNs.
帕金森病（PD）是全球主要的神经退行性疾病。精确客观的PD诊断对于早期干预和治疗具有重要意义。最近的研究表明，基于光学相干断层扫描（OCT）图像，视网膜结构信息与PD之间存在显著相关性，为早期PD识别提供了另一种潜在手段。然而，如何利用来自不同视网膜层的视网膜结构信息（如厚度和平均强度）来提高PD识别性能，此前尚未得到研究。受上述观察结果的启发，我们首先提出一种结构先验知识提取（SPKE）模块来获取视网膜结构特征图；然后，我们开发一种结构引导与自适应注意力（SGDA）模块，基于提取的视网膜结构特征图充分利用不同视网膜层的潜力。通过将SPKE和SGDA模块嵌入深度神经网络（DNN）的低层，构建了一种基于OCT图像的视网膜结构引导与自适应网络（RSGA-Net）用于早期PD识别。在临床OCT-PD数据集上进行的大量实验证明了RSGA-Net优于现有方法。此外，我们提供了可视化分析来解释视网膜结构信息如何影响DNN的决策过程。
