融合影像、病理与报告三模态信息，提升脑瘤亚型分类准确率。
DS@GT ARC at MEDIQA-CORE-Task-1 2026: Trimodal Model Fusion with Task-Specific Gates for Brain Tumor Subtype Classification
- 设计三模态融合架构，通过任务专用门控机制整合多源数据。
- 在全模态条件下达到0.801的平均宏F1，优于基线0.796。
- 适合医疗多模态分析与精准诊断研究者参考。
脑瘤诊断是时间敏感的临床过程，患者可能需数周等待最终病理报告。这一问题推动了从多模态输入自动分类肿瘤亚型系统的发展。本文介绍DS@GT ARC团队在ImageCLEFmed MEDIQA-CORE 2026任务1（脑瘤亚型分类）中的工作。该任务评估三种胶质瘤分类问题：一级分子类型、低级别（LGG）与高级别（HGG）区分、以及WHO分级。我们结合预提取的MRI（NeuroVFM）、组织病理学（Prov-GigaPath）嵌入向量与自由文本放射科报告。团队探索了两种三模态融合架构、两种报告编码器（RadBERT与Llama-3.1-8B-Instruct），并引入生物学启发的后处理阶段。在全模态条件下，模型取得0.801的平均宏F1，超过主办方基线0.796，排名第二（代码通过验证）。在缺失模态的条件下评估显示，该优势高度依赖病理模态的存在；当模态缺失时，系统性能低于基线。代码已开源：https://github.com/dsgt-arc/imageclef-mediqacore-2026。
原文摘要 · Abstract (English)
Brain tumor diagnosis is a time-sensitive process in which patients may wait weeks for a finalized pathology report. This problem motivates automated systems that classify tumor subtype from multimodal inputs. This paper details the DS@GT ARC team's work for ImageCLEFmed MEDIQA-CORE 2026 Task~1, Brain Tumor Subtype Classification. The task evaluates three glioma classification problems: Level-1 Molecular Type, LGG vs HGG, and WHO Grade. We combine pre-extracted MRI (NeuroVFM) and histopathology (Prov-GigaPath) embeddings with free-text radiology reports. Our team explored two trimodal fusion architectures, two report encoders (RadBERT and Llama-3.1-8B-Instruct), and a biologically motivated post-processing stage. We achieve a mean macro-F1 of 0.801 under the Fully Multimodal condition, exceeding the organizers' baseline of 0.796 and ranking second among the teams whose code passed verification. Additional evaluation across modality-dropping conditions shows that this advantage depends heavily on the availability of the histopathology modality, and that our system falls behind the baseline when modalities are missing. Our code is available on GitHub at https://github.com/dsgt-arc/imageclef-mediqacore-2026.
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。