Zhang Hongbo, Zhou Beibei, Zhang Hanwen, Zhang Yuze, Ouyang Ying, Su Ruru, Tang Xumei, Lei Yi, Huang Biao
Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
Department of Radiology, The Seventh Af.liated Hospital, Sun Yat-Sen University, Shenzhen, China.
Neurooncol Adv. 2025 Apr 28;7(1):vdaf079. doi: 10.1093/noajnl/vdaf079. eCollection 2025 Jan-Dec.
Gliomas, the most prevalent type of primary brain tumors, require precise molecular characterization for effective diagnosis and treatment. Despite advancements in radiomics, simultaneous prediction of key molecular markers, such as isocitrate dehydrogenase () mutation, co-deletion, and telomerase reverse transcriptase () promoter mutation, along with prognosis, remains challenging. We aimed to develop and validate a deep learning (DL) model capable of simultaneously predicting key genetic molecular markers and prognosis in gliomas.
We conducted a retrospective analysis of 457 adult-type diffuse gliomas (193 training cohorts; 162 and 102 cases in SZS and The Cancer Genome Atlas (TCGA) validation cohorts, respectively). We developed MultiCubeNet, a multisequence, multiscale, multitask DL framework designed to predict mutation, co-deletion, promoter mutation, and prognosis. Model performance was benchmarked against conventional radiomics pipelines and neuroradiologist annotations. Classification accuracy was evaluated by the area under the receiver operating characteristic curve (AUC), with prognostic performance quantified using Harrell's concordance index (C-index).
The median age of the patients was 49 years, and 266 were men (58.2%). The model demonstrated high efficiency in the training set, achieving AUCs of 0.966 for mutation, 0.961 for co-deletion, and 0.851 for promoter mutation. In the external test set (SZS), the model maintained strong performance with AUCs of 0.877, 0.730, and 0.705 for mutation, co-deletion, and promoter mutation, respectively. The performance in TCGA cohort was less optimal, with AUCs below 0.8. The framework consistently matched or exceeded both radiomics pipelines and neuroradiologists in molecular marker identification. Survival analysis revealed significant prognostic stratification across all cohorts (C-index: 0.706-0.866).
MultiCubeNet, a multitask DL model leveraging multisequence and multiscale magnetic resonance imaging, demonstrated strong performance in predicting key molecular markers and prognosis in gliomas, thereby supporting personalized treatment approaches.
胶质瘤是最常见的原发性脑肿瘤类型，需要精确的分子特征来进行有效的诊断和治疗。尽管放射组学取得了进展，但同时预测关键分子标志物，如异柠檬酸脱氢酶（IDH）突变、1p/19q共缺失和端粒酶逆转录酶（TERT）启动子突变以及预后，仍然具有挑战性。我们旨在开发并验证一种能够同时预测胶质瘤关键遗传分子标志物和预后的深度学习（DL）模型。
我们对457例成人型弥漫性胶质瘤进行了回顾性分析（193例为训练队列；SZS验证队列和癌症基因组图谱（TCGA）验证队列分别有162例和102例）。我们开发了MultiCubeNet，这是一种多序列、多尺度、多任务的DL框架，旨在预测IDH突变、1p/19q共缺失、TERT启动子突变和预后。模型性能以传统放射组学流程和神经放射科医生的注释为基准进行评估。通过受试者操作特征曲线（AUC）下的面积评估分类准确性，使用Harrell一致性指数（C指数）量化预后性能。
患者的中位年龄为49岁，男性266例（58.2%）。该模型在训练集中表现出高效率，IDH突变的AUC为0.966，1p/19q共缺失为0.961，TERT启动子突变为0.851。在外部测试集（SZS）中，该模型保持了较强的性能，IDH突变、1p/19q共缺失和TERT启动子突变的AUC分别为0.877、0.730和0.705。在TCGA队列中的性能不太理想，AUC低于0.8。在分子标志物识别方面，该框架始终与放射组学流程和神经放射科医生的表现相当或更优。生存分析显示所有队列中均有显著的预后分层（C指数：0.706 - 0.866）。
MultiCubeNet是一种利用多序列和多尺度磁共振成像的多任务DL模型，在预测胶质瘤关键分子标志物和预后方面表现出强大性能，从而支持个性化治疗方法。
