针对脑肿瘤影像的复杂性，构建了更鲁棒的医学基础模型，提升罕见分子标记预测能力。
NeuroRAD-FM: A Foundation Model for Neuro-Oncology with Distributionally Robust Training
- 采用分布鲁棒优化，缓解多中心数据偏差与类别不平衡问题
- 在多个机构数据上，罕见突变预测准确率最高提升至0.92，生存预测c-index达0.672
- 适合临床研究者和算法开发者用于精准神经肿瘤学建模
神经肿瘤学因数据异质性和肿瘤复杂性，使基础模型难以跨队列泛化。现有模型对罕见分子标志物预测性能差，影响治疗响应评估。为此，我们开发了一种神经肿瘤专用基础模型，采用分布鲁棒损失函数，在多中心脑肿瘤MRI上预训练自监督骨干网络（BYOL、DINO、MAE、MoCo），并应用分布鲁棒优化（DRO）缓解机构与类别偏差。下游任务包括常见标志物分类（MGMT、IDH1、1p/19q、EGFR）、罕见改变（ATRX、TP53、CDKN2A/2B、TERT）、连续标志物（Ki-67、TP53）及IDH1野生型胶质母细胞瘤的总生存预测，涵盖UCSF、UPenn和CUIMC三所机构数据。结果表明，该方法提升了分子预测精度并减少了机构特异性嵌入差异：在CUIMC，平均平衡准确率从0.744升至0.785，AUC从0.656升至0.676；罕见终点中，CDKN2A/2B准确率0.86→0.92，AUC 0.73→0.92；ATRX AUC 0.69→0.82；Ki-67准确率0.60→0.69。生存预测方面，各机构c-index均提升：CUIMC 0.592→0.597，UPenn 0.647→0.672，UCSF 0.600→0.627。Grad-CAM可视化显示肿瘤及周围区域激活，验证可解释性。整体表明，结合基础模型与分布鲁棒优化可生成更具机构不变性的表征，显著提升常见与罕见标志物预测及生存判别能力，凸显未来需前瞻性验证并融合纵向与干预信号以推动精准神经肿瘤学发展。
原文摘要 · Abstract (English)
Neuro-oncology poses unique challenges for machine learning due to heterogeneous data and tumor complexity, limiting the ability of foundation models (FMs) to generalize across cohorts. Existing FMs also perform poorly in predicting uncommon molecular markers, which are essential for treatment response and risk stratification. To address these gaps, we developed a neuro-oncology specific FM with a distributionally robust loss function, enabling accurate estimation of tumor phenotypes while maintaining cross-institution generalization. We pretrained self-supervised backbones (BYOL, DINO, MAE, MoCo) on multi-institutional brain tumor MRI and applied distributionally robust optimization (DRO) to mitigate site and class imbalance. Downstream tasks included molecular classification of common markers (MGMT, IDH1, 1p/19q, EGFR), uncommon alterations (ATRX, TP53, CDKN2A/2B, TERT), continuous markers (Ki-67, TP53), and overall survival prediction in IDH1 wild-type glioblastoma at UCSF, UPenn, and CUIMC. Our method improved molecular prediction and reduced site-specific embedding differences. At CUIMC, mean balanced accuracy rose from 0.744 to 0.785 and AUC from 0.656 to 0.676, with the largest gains for underrepresented endpoints (CDKN2A/2B accuracy 0.86 to 0.92, AUC 0.73 to 0.92; ATRX AUC 0.69 to 0.82; Ki-67 accuracy 0.60 to 0.69). For survival, c-index improved at all sites: CUIMC 0.592 to 0.597, UPenn 0.647 to 0.672, UCSF 0.600 to 0.627. Grad-CAM highlighted tumor and peri-tumoral regions, confirming interpretability. Overall, coupling FMs with DRO yields more site-invariant representations, improves prediction of common and uncommon markers, and enhances survival discrimination, underscoring the need for prospective validation and integration of longitudinal and interventional signals to advance precision neuro-oncology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。