Liu Jianpeng, Jiang Shufan, Wu Yanfei, Zou Ruoyao, Bao Yifang, Wang Na, Tu Jiaqi, Xiong Ji, Liu Ying, Li Yuxin
Department of Radiology, Huashan Hospital, Fudan University, Shanghai, People's Republic of China.
Department of Pathology, School of Basic Medical Sciences, Fudan University, Shanghai, People's Republic of China.
Int J Surg. 2025 Jul 1;111(7):4576-4585. doi: 10.1097/JS9.0000000000002488. Epub 2025 May 20.
Glioblastoma (GBM) is a highly aggressive brain tumor with a poor prognosis. This study aimed to construct and validate a radiomics-based machine learning model for predicting overall survival (OS) in isocitrate dehydrogenase-wildtype GBM after maximal safe surgical resection using magnetic resonance imaging.
A total of 582 patients were retrospectively enrolled, comprising 301 in the training cohort, 128 in the internal validation cohort, and 153 in the external validation cohort. Volumes of interest from contrast-enhanced T1-weighted imaging were segmented into three regions: contrast-enhancing tumor, necrotic non-enhancing core, and peritumoral edema using a ResNet-based segmentation network. A total of 4227 radiomic features were extracted and filtered using Least Absolute Shrinkage and Selection Operator-Cox regression to identify signatures. The prognostic model was constructed using the Mime prediction framework, categorizing patients into high- and low-risk groups based on the median OS. Model performance was assessed using the concordance index (CI) and Kaplan-Meier survival analysis. Independent prognostic factors were identified through multivariable Cox regression analysis, and a nomogram was developed for individualized risk assessment.
The Step Cox[backward] + RSF model achieved CIs of 0.89, 0.81, and 0.76 in the training, internal, and external validation cohorts. Log-rank tests demonstrated significant survival differences between high- and low-risk groups across all cohorts ( P < 0.05). Multivariate Cox analysis identified age (hazard ratio [HR]: 1.022; 95% CI: 0.979, 1.009, P < 0.05), Karnofsky Performance Status score (HR: 0.970, 95% CI: 0.960, 0.978, P < 0.05), rad-scores of the necrotic non-enhancing core (HR: 8.164; 95% CI: 2.439, 27.331, P < 0.05), and peritumoral edema (HR: 3.748; 95% CI: 1.212, 11.594, P < 0.05) as independent predictors of OS. A nomogram integrating these predictors provided individualized risk assessment.
This deep learning segmentation-based radiomics model demonstrated robust performance in predicting OS in GBM after maximal safe surgical resection. By incorporating radiomic signatures and advanced machine learning algorithms, it offers a noninvasive tool for personalized prognostic assessment and supports clinical decision-making.
胶质母细胞瘤（GBM）是一种侵袭性很强的脑肿瘤，预后较差。本研究旨在构建并验证一种基于放射组学的机器学习模型，用于预测在最大安全手术切除后，异柠檬酸脱氢酶野生型GBM患者的总生存期（OS），该模型使用磁共振成像。
共回顾性纳入582例患者，其中训练队列301例，内部验证队列128例，外部验证队列153例。使用基于ResNet的分割网络，将对比增强T1加权成像的感兴趣体积分割为三个区域：对比增强肿瘤、坏死无增强核心和瘤周水肿。共提取4227个放射组学特征，并使用最小绝对收缩和选择算子- Cox回归进行筛选，以识别特征。使用Mime预测框架构建预后模型，根据OS中位数将患者分为高风险和低风险组。使用一致性指数（CI）和Kaplan-Meier生存分析评估模型性能。通过多变量Cox回归分析确定独立预后因素，并绘制列线图进行个体化风险评估。
在训练、内部和外部验证队列中，逐步Cox[向后] + RSF模型的CI分别为0.89、0.81和0.76。对数秩检验显示，所有队列中高风险组和低风险组之间存在显著的生存差异（P < 0.05）。多变量Cox分析确定年龄（风险比[HR]：1.022；95% CI：0.979，1.009，P < 0.05）、卡诺夫斯基功能状态评分（HR：0.970，95% CI：0.960，0.978，P < 0.05）、坏死无增强核心的放射学评分（HR：8.164；95% CI：2.439，27.331，P < 0.05）和瘤周水肿（HR：3.748；95% CI：1.212，11.594，P < 0.05）为OS的独立预测因素。整合这些预测因素的列线图提供了个体化风险评估。
这种基于深度学习分割的放射组学模型在预测最大安全手术切除后GBM患者的OS方面表现出强大的性能。通过纳入放射组学特征和先进的机器学习算法，它提供了一种用于个性化预后评估的非侵入性工具，并支持临床决策。
