MAFM^3：面向多模态医疗AI的基础模型模块化适配框架
MAFM^3: Modular Adaptation of Foundation Models for Multi-Modal Medical AI
AI总结：
针对医学影像领域数据稀缺导致全场景预训练困难的问题，本文提出MAFM^3模块化适配框架，通过轻量组件让单个基础模型灵活适配多任务多模态，实验验证其可有效提升任务性能。
摘要：
基础模型在大规模数据集上训练以捕捉领域的通用规律，但在医学影像领域，数据稀缺问题使得针对每个领域、模态或任务开展预训练都极具挑战。本文没有为不同场景构建独立模型，而是提出MAFM^3（面向多模态医疗AI的基础模型模块化适配框架），该框架可通过轻量级模块化组件，让单个基础模型拓展适配至不同领域、任务和模态。这些组件相当于专门的技能集，系统可在推理阶段根据输入类型或临床目标灵活激活对应能力。与传统适配方法孤立处理每个新任务或新模态不同，MAFM^3提供了统一可拓展的框架，可实现高效的多任务、多模态适配。实验层面，本文将最初为分类任务训练的胸部CT基础模型适配为预后预测和分割模块以验证方法有效性，结果显示两个任务的性能均得到提升；此外，在引入PET扫描数据后，MAFM^3的Dice得分相较对应基线提升了5%。上述结果表明，配备模块化组件的基础模型并非天然受限于初始训练范围，可演进为适用于医学影像的多任务、多模态系统。本工作的代码实现可访问https://github.com/Areeb2735/CTscan_prognosis_VLM获取。
英文摘要：
Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every domain, modality, or task challenging. Instead of building separate models, we propose MAFM^3 (Modular Adaptation of Foundation Models for Multi-Modal Medical AI), a framework that enables a single foundation model to expand into diverse domains, tasks, and modalities through lightweight modular components. These components serve as specialized skill sets that allow the system to flexibly activate the appropriate capability at the inference time, depending on the input type or clinical objective. Unlike conventional adaptation methods that treat each new task or modality in isolation, MAFM^3 provides a unified and expandable framework for efficient multitask and multimodality adaptation. Empirically, we validate our approach by adapting a chest CT foundation model initially trained for classification into prognosis and segmentation modules. Our results show improved performance on both tasks. Furthermore, by incorporating PET scans, MAFM^3 achieved an improvement in the Dice score 5% compared to the respective baselines. These findings establish that foundation models, when equipped with modular components, are not inherently constrained to their initial training scope but can evolve into multitask, multimodality systems for medical imaging. The code implementation of this work can be found at https://github.com/Areeb2735/CTscan_prognosis_VLM
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
