NeuroMosaic：基于解剖学的多模态大语言模型，用于从3D MRI和临床叙事中进行分子感知的胶质瘤推理
NeuroMosaic: Anatomically Grounded Multimodal Large Language Modeling for Molecularly Aware Glioma Reasoning from 3D MRI and Clinical Narratives
浏览论文内容
中文总结 AI 辅助
该研究针对多模态医疗大语言模型在神经肿瘤学中的结构缺陷，提出NeuroMosaic模型，通过多模块架构实现胶质瘤的准确推理，在多个数据集上取得优异性能，验证了解剖学索引路由机制的有效性。
中文摘要 AI 辅助
多模态医疗大语言模型在神经肿瘤学领域仍存在结构缺陷，因为体积证据被压缩为通用视觉令牌，且诊断结论往往缺乏与MRI区域的可审计关联。我们提出NeuroMosaic，这是一种3D多模态语言模型，可将多序列脑MRI转换为解剖学索引的区域令牌，使其与临床叙事和分子概念对齐，并生成证据关联的输出。该架构结合了多分辨率体积令牌化器、神经解剖图路由、分子概念记忆以及选择性风险控制。在四个胶质瘤队列中，NeuroMosaic实现了内部亚型宏F1为0.827，外部宏F1值分别为0.784、0.761和0.742。在UPenn-GBM数据集上，它比最强匹配输入基线提升了3.6个百分点（95%置信区间：1.8至5.4，校正后p=0.0018），IDH、1p/19q和MGMT的AUROC分别为0.918、0.861和0.781。证据指向准确率达到0.703，靶向证据删除使正确答案概率降低0.187，而随机删除仅降低0.046。这些结果确立了解剖学索引路由作为准确、有依据且可校准的体积医疗-语言推理的可测量机制。
英文摘要
Multimodal medical large language models remain structurally weak for neuro-oncology because volumetric evidence is compressed into generic visual tokens and diagnostic conclusions often lack an auditable link to MRI regions. We present NeuroMosaic, a 3D multimodal language model that converts multi-sequence brain MRI into anatomy-indexed regional tokens, aligns them with clinical narrative and molecular concepts, and generates evidence-linked outputs. The architecture combines a multi-resolution volumetric tokenizer, a neuroanatomical graph router, a molecular concept memory, and selective risk control. Across four glioma cohorts, NeuroMosaic achieved an internal subtype macro-F1 of 0.827 and external macro-F1 values of 0.784, 0.761, and 0.742. On UPenn-GBM, it improved over the strongest matched-input baseline by 3.6 percentage points (95% CI: 1.8 to 5.4, adjusted p = 0.0018), with IDH, 1p/19q, and MGMT AUROCs of 0.918, 0.861, and 0.781. Evidence pointing accuracy reached 0.703, and targeted evidence deletion reduced correct-answer probability by 0.187, compared with 0.046 for random deletion. These results establish anatomy-indexed routing as a measurable mechanism for accurate, grounded, and calibrated volumetric medical-language reasoning.
