BrainFM可统一处理多种脑影像任务，不依赖具体成像模态。
A Modality-agnostic Multi-task Foundation Model for Human Brain Imaging
- 采用渐进式生成与真实-合成混合训练，提升模型对图像差异的鲁棒性。
- 在11个公开数据集上验证，5大任务性能稳定，跨模态泛化能力强。
- 适合临床医生和研究者快速部署，无需针对每种扫描协议重新训练。
近年来基于学习的方法在校准医学影像（如计算机断层扫描CT）中取得显著进展，但在未校准模态（特别是磁共振成像MRI）上表现不佳，其性能高度受对比度、分辨率和方向差异影响。这限制了其在多样临床协议中的广泛应用。本文提出BrainFM，一种面向人类脑影像的模态无关多任务视觉基础模型。通过“轻度到严重”个体内生成与“真实-合成”混合训练策略，BrainFM能有效应对图像外观差异（如模态、对比度、形变、分辨率、伪影），并直接应用于五大核心脑影像任务：CT及T1w/T2w/FLAIR MRI图像合成、解剖分割、头皮到皮层距离估计、偏置场估计与配准。我们在11个公共数据集上评估了BrainFM的效能，结果表明其在所有任务和输入模态下均具强鲁棒性与有效性。代码已开源。
原文摘要 · Abstract (English)
Recent learning-based approaches have made astonishing advances in calibrated medical imaging like computerized tomography (CT), yet they struggle to generalize in uncalibrated modalities -- notably magnetic resonance (MR) imaging, where performance is highly sensitive to the differences in MR contrast, resolution, and orientation. This prevents broad applicability to diverse real-world clinical protocols. Here we introduce BrainFM, a modality-agnostic, multi-task vision foundation model for human brain imaging. With the proposed "mild-to-severe" intra-subject generation and "real-synth" mix-up training strategy, BrainFM is resilient to the appearance of acquired images (e.g., modality, contrast, deformation, resolution, artifacts), and can be directly applied to five fundamental brain imaging tasks, including image synthesis for CT and T1w/T2w/FLAIR MRI, anatomy segmentation, scalp-to-cortical distance, bias field estimation, and registration. We evaluate the efficacy of BrainFM on eleven public datasets, and demonstrate its robustness and effectiveness across all tasks and input modalities. Code is available at https://github.com/jhuldr/BrainFM.
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。