目标:研究深度学习的有效性和适用性,影像组学,及其基于磁共振成像(MRI)的整合模型,用于术前区分原发性中枢神经系统淋巴瘤(PCNSL)和胶质母细胞瘤(GBM),以及对这些模型的可解释性的探索。
方法:对来自两个医疗中心的261名患者的MRI图像和临床数据进行回顾性分析。将数据分成训练集(n=153,医疗中心1)和外部测试集(n=108,医疗中心2)。使用Pyradiomics提取影像组学特征以构建影像组学模型。深度学习网络,包括基于变压器的MobileVIT模型和基于卷积神经网络(CNN)的ConvNeXt模型,是单独训练的。通过应用“晚期融合”理论,将影像组学模型和深度学习模型进行融合,以产生最佳的Max-Fusion模型。此外,Shapley加性扩张(SHAP)和Grad-CAM用于可解释性分析。
结果:在外部测试集中,Radiomics模型的受试者工作特征曲线下面积(AUC)为0.86,MobileVIT模型的AUC为0.91,ConvNeXt模型的AUC为0.89,Max-Fusion模型的AUC为0.92.Delong测试显示,Max-Fusion模型和Radiomics模型之间的AUC存在显着差异(P=0.02)。
结论:最大融合模型,结合不同的模型,在区分PCNSL和GBM方面表现出卓越的性能,强调模型融合在医学应用中增强决策的有效性。
结论:术前非侵入性区分PCNSL和GBM有助于临床医生选择合适的治疗方案和临床管理策略。
OBJECTIVE: Research into the effectiveness and applicability of deep learning, radiomics, and their integrated models based on Magnetic Resonance Imaging (MRI) for preoperative differentiation between Primary Central Nervous System Lymphoma (PCNSL) and Glioblastoma (GBM), along with an exploration of the interpretability of these models.
METHODS: A retrospective analysis was performed on MRI images and clinical data from 261 patients across two medical centers. The data were split into a training set (n = 153, medical center 1) and an external test set (n = 108, medical center 2). Radiomic features were extracted using Pyradiomics to build the Radiomics Model. Deep learning networks, including the transformer-based MobileVIT Model and Convolutional Neural Networks (CNN) based ConvNeXt Model, were trained separately. By applying the \"late fusion\" theory, the radiomics model and deep learning model were fused to produce the optimal Max-Fusion Model. Additionally, Shapley Additive exPlanations (SHAP) and Grad-CAM were employed for interpretability analysis.
RESULTS: In the external test set, the Radiomics Model achieved an Area under the receiver operating characteristic curve (AUC) of 0.86, the MobileVIT Model had an AUC of 0.91, the ConvNeXt Model demonstrated an AUC of 0.89, and the Max-Fusion Model showed an AUC of 0.92. The Delong test revealed a significant difference in AUC between the Max-Fusion Model and the Radiomics Model (P = 0.02).
CONCLUSIONS: The Max-Fusion Model, combining different models, presents superior performance in distinguishing PCNSL and GBM, highlighting the effectiveness of model fusion for enhanced decision-making in medical applications.
CONCLUSIONS: The preoperative non-invasive differentiation between PCNSL and GBM assists clinicians in selecting appropriate treatment regimens and clinical management strategies.