文献速递神经MR

基于可解释人工智能模型的多中心术前鉴别原发性中枢神经系统淋巴瘤与胶质母细胞瘤研究

Multicenter investigation of preoperative distinction between primary central nervous system lymphomas and glioblastomas through interpretable artificial intelligence models.
PubMed 文献 · Neuroradiology · 2024-09-03

该多中心回顾性研究纳入261例患者MRI数据,训练集153例来自医学中心1,外部测试集108例来自医学中心2,构建影像组学、MobileVIT、ConvNeXt及Max-Fusion融合模型鉴别PCNSL与GBM,外部测试集AUC分别为0.86、0.91、0.89、0.92,Max-Fusion与影像组学模型AUC差异有统计学意义(P=0.02)。

要点

  • Max-Fusion模型外部测试集AUC达0.92,优于影像组学模型0.86(P=0.02)。
  • MobileVIT外部测试集AUC 0.91,ConvNeXt外部测试集AUC 0.89。
  • SHAP与Grad-CAM用于模型可解释性分析。

核心结论

  • Max-Fusion融合模型在区分PCNSL与GBM方面表现更优,突显模型融合在医学决策中的有效性。

研究设计与样本

  • 两医学中心回顾性分析,共261例患者MRI图像与临床数据,训练集153例(医学中心1),外部测试集108例(医学中心2)。

诊断标准与关键数值

  • 外部测试集中影像组学模型AUC为0.86,MobileVIT模型AUC为0.91,ConvNeXt模型AUC为0.89,Max-Fusion模型AUC为0.92。
  • Delong检验显示Max-Fusion模型与影像组学模型AUC差异有统计学意义(P=0.02)。

临床应用与阅片要点

  • 术前无创鉴别PCNSL与GBM有助于临床医生选择适当治疗方案和管理策略。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

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.

MATERIALS AND 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).

CONCLUSION: 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.

CLINICAL RELEVANCE STATEMENT: The preoperative non-invasive differentiation between PCNSL and GBM assists clinicians in selecting appropriate treatment regimens and clinical management strategies.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Yang YF, Zhao E, Shi Y, et al. Multicenter investigation of preoperative distinction between primary central nervous system lymphomas and glioblastomas through interpretable artificial intelligence models. Neuroradiology. 2024. PMID: 39225815. doi:10.1007/s00234-024-03451-7

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。