文献速递神经肿瘤

多模态神经影像与机器学习预测胶质母细胞瘤生存期

Predicting survival in glioblastoma with multimodal neuroimaging and machine learning.
PubMed 文献 · J Neurooncol · 2023-09-05

回顾性纳入华盛顿大学医学中心神经外科脑肿瘤服务的133例胶质母细胞瘤患者(平均年龄60.8岁,中位生存期14.1个月,57.9%男性),术前完成结构神经影像和静息态功能MRI,用人口学、皮层厚度和静息态功能网络连接训练深度神经网络按生存期(<1年、1-2年、>2年)分类;模型交叉验证与留出法联合准确率90.6%,最强人口学预测因子为诊断时年龄和性别,最强皮层厚度预测区域包括颞上沟、海马旁回、距状沟周围、三角部及颞中区域,最强功能连接特征主要涉及背侧和腹侧躯体运动、视觉及扣带岛盖网络。

要点

  • 深度神经网络基于术前多模态神经影像可将胶质母细胞瘤患者生存期分为<1年、1-2年、>2年,联合交叉验证与留出法准确率90.6%。
  • 最强人口学预测因子为诊断时年龄和性别。
  • 最强皮层厚度预测区域包括颞上沟、海马旁回、距状沟周围、三角部及颞中区域。

核心结论

  • 机器学习可基于任何手术或内科干预前的多模态神经影像准确分类胶质母细胞瘤患者的生存期,且未使用症状、治疗、术后结局或肿瘤基因组信息。
  • 结果表明胶质母细胞瘤对大脑结构和功能组织有全局性影响,并可预测生存期。

研究设计与样本

  • 回顾性研究,从华盛顿大学医学中心神经外科脑肿瘤服务招募胶质母细胞瘤患者N=133,平均年龄60.8岁,中位生存期14.1个月,57.9%男性。
  • 所有患者术前完成结构神经影像和静息态功能MRI(RS-fMRI)。
  • 使用人口学、皮层厚度(CT)和静息态功能网络连接(FC)训练深度神经网络,按生存期(<1年、1-2年、>2年)分类。
  • 采用置换特征重要性基于训练模型识别最强生存预测因子。

主要发现

  • 模型在分类生存期(<1年、1-2年、>2年)时,交叉验证与留出法联合准确率为90.6%。
  • 最强人口学预测因子为诊断时年龄和性别。
  • 最强皮层厚度预测因子包括颞上沟、海马旁回、距状沟周围、三角部及颞中区域。
  • 最强功能连接特征主要涉及背侧和腹侧躯体运动、视觉及扣带岛盖网络。

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)。

原文

PURPOSE: Glioblastoma (GBM) is the most common and aggressive malignant glioma, with an overall median survival of less than two years. The ability to predict survival before treatment in GBM patients would lead to improved disease management, clinical trial enrollment, and patient care. METHODS: GBM patients (N = 133, mean age 60.8 years, median survival 14.1 months, 57.9% male) were retrospectively recruited from the neurosurgery brain tumor service at Washington University Medical Center. All patients completed structural neuroimaging and resting state functional MRI (RS-fMRI) before surgery. Demographics, measures of cortical thickness (CT), and resting state functional network connectivity (FC) were used to train a deep neural network to classify patients based on survival (< 1y, 1-2y, >2y). Permutation feature importance identified the strongest predictors of survival based on the trained models. RESULTS: The models achieved a combined cross-validation and hold out accuracy of 90.6% in classifying survival (< 1y, 1-2y, >2y). The strongest demographic predictors were age at diagnosis and sex. The strongest CT predictors of survival included the superior temporal sulcus, parahippocampal gyrus, pericalcarine, pars triangularis, and middle temporal regions. The strongest FC features primarily involved dorsal and inferior somatomotor, visual, and cingulo-opercular networks. CONCLUSION: We demonstrate that machine learning can accurately classify survival in GBM patients based on multimodal neuroimaging before any surgical or medical intervention. These results were achieved without information regarding presentation symptoms, treatments, postsurgical outcomes, or tumor genomic information. Our results suggest GBMs have a global effect on the brain's structural and functional organization, which is predictive of survival.

来源:J Neurooncol,查看原文。版权归原作者所有。

引用

  1. Luckett PH, Olufawo M, Lamichhane B, et al. Predicting survival in glioblastoma with multimodal neuroimaging and machine learning. J Neurooncol. 2023. PMID: 37668941. doi:10.1007/s11060-023-04439-8

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。