Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-Ro 43-Gil Songpa-Gu, Seoul, 05505, Korea.
Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, 88 Olympic-Ro 43-Gil Songpa-Gu, Seoul, 05505, Korea.
Sci Rep. 2019 Apr 5;9(1):5746. doi: 10.1038/s41598-019-42276-w.
We aimed to establish a high-performing and robust classification strategy, using magnetic resonance imaging (MRI), along with combinations of feature extraction and selection in human and machine learning using radiomics or deep features by employing a small dataset. Using diffusion and contrast-enhanced T1-weighted MR images obtained from patients with glioblastomas and primary central nervous system lymphomas, classification task was assigned to a combination of radiomic features and (1) supervised machine learning after feature selection or (2) multilayer perceptron (MLP) network; or MR image input without radiomic feature extraction to (3) two neuro-radiologists or (4) an end-to-end convolutional neural network (CNN). The results showed similar high performance in generalized linear model (GLM) classifier and MLP using radiomics features in the internal validation set, but MLP network remained robust in the external validation set obtained using different MRI protocols. CNN showed the lowest performance in both validation sets. Our results reveal that a combination of radiomic features and MLP network classifier serves a high-performing and generalizable model for classification task for a small dataset with heterogeneous MRI protocols.
我们旨在建立一种高性能且稳健的分类策略，使用磁共振成像（MRI），结合放射组学或深度学习特征的特征提取和选择，在人类和机器学习中使用小数据集。使用从患有胶质母细胞瘤和原发性中枢神经系统淋巴瘤的患者获得的弥散和对比增强 T1 加权 MR 图像，分类任务被分配给放射组学特征的组合和（1）经过特征选择的监督机器学习，或（2）多层感知机（MLP）网络；或不进行放射组学特征提取的 MR 图像输入到（3）两位神经放射科医生或（4）端到端卷积神经网络（CNN）。结果表明，在内部验证集中，使用放射组学特征的广义线性模型（GLM）分类器和 MLP 具有相似的高性能，但 MLP 网络在使用不同 MRI 协议获得的外部验证集中仍然稳健。CNN 在两个验证集中的表现均最低。我们的结果表明，放射组学特征和 MLP 网络分类器的组合为具有异构 MRI 协议的小数据集的分类任务提供了一种高性能且可推广的模型。
