Lopatina Alina, Ropele Stefan, Sibgatulin Renat, Reichenbach Jürgen R, Güllmar Daniel
Medical Physics Group, Institute for Diagnostic and Interventional Radiology, University Hospital Jena, Jena, Germany.
Michael-Stifel-Center for Data-Driven and Simulation Science Jena, Jena, Germany.
Front Neurosci. 2020 Dec 18;14:609468. doi: 10.3389/fnins.2020.609468. eCollection 2020.
The diagnosis of multiple sclerosis (MS) is usually based on clinical symptoms and signs of damage to the central nervous system, which is assessed using magnetic resonance imaging. The correct interpretation of these data requires excellent clinical expertise and experience. Deep neural networks aim to assist clinicians in identifying MS using imaging data. However, before such networks can be integrated into clinical workflow, it is crucial to understand their classification strategy. In this study, we propose to use a convolutional neural network to identify MS patients in combination with attribution algorithms to investigate the classification decisions. The network was trained using images acquired with susceptibility-weighted imaging (SWI), which is known to be sensitive to the presence of paramagnetic iron components and is routinely applied in imaging protocols for MS patients. Different attribution algorithms were used to the trained network resulting in heatmaps visualizing the contribution of each input voxel to the classification decision. Based on the quantitative image perturbation method, we selected DeepLIFT heatmaps for further investigation. Single-subject analysis revealed veins and adjacent voxels as signs for MS, while the population-based study revealed relevant brain areas common to most subjects in a class. This pattern was found to be stable across different echo times and also for a multi-echo trained network. Intensity analysis of the relevant voxels revealed a group difference, which was found to be primarily based on the T1w magnitude images, which are part of the SWI calculation. This difference was not observed in the phase mask data.
多发性硬化症（MS）的诊断通常基于中枢神经系统损伤的临床症状和体征，这通过磁共振成像进行评估。对这些数据的正确解读需要出色的临床专业知识和经验。深度神经网络旨在协助临床医生利用成像数据识别MS。然而，在将此类网络整合到临床工作流程之前，了解其分类策略至关重要。在本研究中，我们建议使用卷积神经网络结合归因算法来识别MS患者，以研究分类决策。该网络使用通过磁敏感加权成像（SWI）获取的图像进行训练，已知SWI对顺磁性铁成分的存在敏感，并且在MS患者的成像方案中常规应用。对训练好的网络使用不同的归因算法，生成热图以可视化每个输入体素对分类决策的贡献。基于定量图像扰动方法，我们选择了DeepLIFT热图进行进一步研究。单受试者分析揭示静脉和相邻体素为MS的体征，而基于群体的研究揭示了某一类中大多数受试者共有的相关脑区。发现这种模式在不同回波时间以及多回波训练网络中都是稳定的。对相关体素的强度分析揭示了组间差异，发现其主要基于T1w幅度图像，T1w幅度图像是SWI计算的一部分。在相位掩码数据中未观察到这种差异。
