Li Yanong, Liu Hailong, Liu Yawei, Li Jane, Suzuki Hiro Hiromichi, Liu Yaou, Tao Jiang, Qiu Xiaoguang
Department of Radiation Oncology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100070, China.
Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100070, China.
Chin Neurosurg J. 2025 Sep 15;11(1):19. doi: 10.1186/s41016-025-00405-7.
Deep learning (DL) based on MRI of medulloblastoma enables risk stratification, potentially aiding in therapeutic decisions. This study aims to develop DL models that identify four medulloblastoma molecular subgroups and prognostic-related genetic signatures.
This retrospective study enrolled 325 patients for model development and an independent external validation cohort of 124 patients, totaling 449 MB patients from 2 medical institutes. Consecutive patients with newly diagnosed MB at MRI (T1-weighted, T2-weighted, and contrast-enhanced T1-weighted) at two medical institutes between January 2015 and June 2023 were identified. Two-stage sequential DL models were designed-MB-CNN that first identifies wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4. Further, prognostic-related genetic signatures using DL models (MB-CNN_TP53/MYC/Chr11) were developed to predict TP53 mutation, MYC amplification, and chromosome 11 loss status. A hybrid model combining MB-CNN and conventional data (clinical information and MRI features) was compared to a logistic regression model constructed only with conventional data. Four-classification tasks were evaluated with confusion matrices (accuracy) and two-classification tasks with ROC curves (area under the curve (AUC)).
The datasets comprised 449 patients (mean age ± SD at diagnosis, 13.55 years ± 2.33, 249 males). MB-CNN accurately classified MB subgroups in the external test dataset, achieving a median accuracy of 77.50% (range in 76.29% to 78.71%). MB-CNN_TP53/MYC/Chr11 models effectively predicted signatures (AUC of TP53 in SHH: 0.91, MYC amplification in Group 3: 0.87, chromosome 11 loss in Group 4: 0.89). The accuracy of the hybrid model outperformed the logistic regression model (82.20% vs. 59.14%, P = .009) and showed comparable performance to MB-CNN (82.20% vs. 77.50%, P = 0.105).
MRI-based DL models allowed identification of the molecular medulloblastoma subgroups and prognostic-related genetic signatures.
基于髓母细胞瘤磁共振成像（MRI）的深度学习（DL）能够进行风险分层，可能有助于治疗决策。本研究旨在开发能够识别四种髓母细胞瘤分子亚组和预后相关基因特征的DL模型。
这项回顾性研究纳入了325例患者用于模型开发，并设立了一个包含124例患者的独立外部验证队列，共计来自2家医疗机构的449例髓母细胞瘤患者。确定了2015年1月至2023年6月期间两家医疗机构中连续的新发髓母细胞瘤MRI（T1加权、T2加权和对比增强T1加权）患者。设计了两阶段序列DL模型——MB-CNN，其首先识别无翅（WNT）、音猬因子（SHH）、3组和4组。此外，还开发了使用DL模型（MB-CNN_TP53/MYC/Chr11）的预后相关基因特征，以预测TP53突变、MYC扩增和11号染色体缺失状态。将结合MB-CNN和传统数据（临床信息和MRI特征）的混合模型与仅用传统数据构建的逻辑回归模型进行比较。通过混淆矩阵（准确率）评估四类分类任务，通过ROC曲线（曲线下面积（AUC））评估两类分类任务。
数据集包括449例患者（诊断时的平均年龄±标准差，13.55岁±2.33，男性249例）。MB-CNN在外部测试数据集中准确地对髓母细胞瘤亚组进行了分类，中位准确率达到77.50%（范围在76.29%至78.71%之间）。MB-CNN_TP53/MYC/Chr11模型有效地预测了特征（SHH中TP53的AUC为0.91，3组中MYC扩增的AUC为0.87，4组中11号染色体缺失的AUC为0.89）。混合模型的准确率优于逻辑回归模型（82.20%对59.14%，P = 0.009），并且与MB-CNN表现相当（82.20%对77.50%，P = 0.105）。
基于MRI的DL模型能够识别髓母细胞瘤分子亚组和预后相关基因特征。
