Biomedical Engineering Program, University of Calgary, Canada; Department of Radiology, University of Calgary, Canada.
Department of Radiology, University of Calgary, Canada; Alberta Children's Hospital Research Institute, University of Calgary, Canada.
Neuroimage Clin. 2023;38:103405. doi: 10.1016/j.nicl.2023.103405. Epub 2023 Apr 17.
Parkinson's disease (PD) is a severe neurodegenerative disease that affects millions of people. Early diagnosis is important to facilitate prompt interventions to slow down disease progression. However, accurate PD diagnosis can be challenging, especially in the early disease stages. The aim of this work was to develop and evaluate a robust explainable deep learning model for PD classification trained from one of the largest collections of T1-weighted magnetic resonance imaging datasets.
A total of 2,041 T1-weighted MRI datasets from 13 different studies were collected, including 1,024 datasets from PD patients and 1,017 datasets from age- and sex-matched healthy controls (HC). The datasets were skull stripped, resampled to isotropic resolution, bias field corrected, and non-linearly registered to the MNI PD25 atlas. The Jacobian maps derived from the deformation fields together with basic clinical parameters were used to train a state-of-the-art convolutional neural network (CNN) to classify PD and HC subjects. Saliency maps were generated to display the brain regions contributing the most to the classification task as a means of explainable artificial intelligence.
The CNN model was trained using an 85%/5%/10% train/validation/test split stratified by diagnosis, sex, and study. The model achieved an accuracy of 79.3%, precision of 80.2%, specificity of 81.3%, sensitivity of 77.7%, and AUC-ROC of 0.87 on the test set while performing similarly on an independent test set. Saliency maps computed for the test set data highlighted frontotemporal regions, the orbital-frontal cortex, and multiple deep gray matter structures as most important.
The developed CNN model, trained on a large heterogenous database, was able to differentiate PD patients from HC subjects with high accuracy with clinically feasible classification explanations. Future research should aim to investigate the combination of multiple imaging modalities with deep learning and on validating these results in a prospective trial as a clinical decision support system.
帕金森病（PD）是一种严重的神经退行性疾病，影响着数百万人。早期诊断对于促进及时干预以减缓疾病进展非常重要。然而，准确的 PD 诊断可能具有挑战性，尤其是在疾病早期阶段。本研究旨在开发和评估一种基于最大的 T1 加权磁共振成像数据集之一训练的强大可解释深度学习模型，用于 PD 分类。
共收集了来自 13 项不同研究的 2041 例 T1 加权 MRI 数据集，包括 1024 例 PD 患者数据集和 1017 例年龄和性别匹配的健康对照组（HC）数据集。对数据集进行了颅骨剥离、等体分辨率重采样、偏置场校正，并进行非线性配准到 MNI PD25 图谱。从变形场中导出的雅可比映射图与基本临床参数一起用于训练最先进的卷积神经网络（CNN），以对 PD 和 HC 受试者进行分类。生成显著图以显示对分类任务贡献最大的脑区，作为人工智能解释的一种手段。
CNN 模型使用按诊断、性别和研究分层的 85%/5%/10%训练/验证/测试分割进行训练。该模型在测试集上的准确率为 79.3%、精密度为 80.2%、特异性为 81.3%、敏感性为 77.7%和 AUC-ROC 为 0.87，在独立测试集上表现相似。为测试集数据计算的显著图突出了额颞叶区域、眶额皮层和多个深部灰质结构作为最重要的区域。
基于大型异质数据库训练的开发的 CNN 模型能够以高精度区分 PD 患者和 HC 受试者，具有临床可行的分类解释。未来的研究应旨在探索多种成像模式与深度学习的结合，并在前瞻性试验中验证这些结果，作为临床决策支持系统。
