Braeker Norbert, Schmitz Cornelia, Wagner Natalie, Stanicki Badrudin J, Schröder Christina, Ehret Felix, Fürweger Christoph, Zwahlen Daniel R, Förster Robert, Muacevic Alexander, Windisch Paul
Department of Radiation Oncology, Kantonsspital Winterthur, Winterthur, CHE.
Data Science, Propulsion Academy, Zurich, CHE.
Cureus. 2022 Feb 21;14(2):e22435. doi: 10.7759/cureus.22435. eCollection 2022 Feb.
Background Neural networks for analyzing MRIs are oftentimes trained on particular combinations of perspectives and acquisition sequences. Since real-world data are less structured and do not follow a standard denomination of acquisition sequences, this impedes the transition from deep learning research to clinical application. The purpose of this study is therefore to assess the feasibility of classifying the acquisition sequence from a single MRI slice using convolutional neural networks. Methods A total of 113 MRI slices from 52 patients were used in a transfer learning approach to train three convolutional neural networks of different complexities to predict the acquisition sequence, while 27 slices were used for internal validation. The model then underwent external validation on 600 slices from 273 patients belonging to one of four classes (T1-weighted without contrast enhancement, T1-weighted with contrast enhancement, T2-weighted, and diffusion-weighted). Categorical accuracy was noted, and the results of the predictions for the validation set are provided with confusion matrices. Results The neural networks achieved a categorical accuracy of 0.79, 0.81, and 0.84 on the external validation data. The implementation of Grad-CAM showed no clear pattern of focus except for T2-weighted slices, where the network focused on areas containing cerebrospinal fluid. Conclusion Automatically classifying the acquisition sequence using neural networks seems feasible and could be used to facilitate the automatic labelling of MRI data.
背景 用于分析磁共振成像（MRI）的神经网络通常是针对特定的视角和采集序列组合进行训练的。由于现实世界中的数据结构较差，且不遵循采集序列的标准命名，这阻碍了从深度学习研究向临床应用的转变。因此，本研究的目的是评估使用卷积神经网络从单个MRI切片中对采集序列进行分类的可行性。方法 采用迁移学习方法，使用来自52名患者的总共113个MRI切片来训练三个不同复杂度的卷积神经网络，以预测采集序列，同时使用27个切片进行内部验证。然后，该模型在来自273名患者的600个切片上进行外部验证，这些切片属于四类之一（无对比增强的T1加权、有对比增强的T1加权、T2加权和扩散加权）。记录分类准确率，并通过混淆矩阵提供验证集的预测结果。结果 神经网络在外部验证数据上的分类准确率分别为0.79、0.81和0.84。Grad-CAM的实施显示，除了T2加权切片外，没有明显的聚焦模式，在T2加权切片中，网络聚焦于包含脑脊液的区域。结论 使用神经网络自动对采集序列进行分类似乎是可行的，并且可用于促进MRI数据的自动标注。
