基于解剖先验的U-Net模型在脑MRI基础模型竞赛中夺冠。
From 100,000+ images to winning the first brain MRI foundation model challenges: Sharing lessons and models
- 用U-Net结合解剖与神经影像领域知识构建模型。
- 训练速度比同类模型快10到100倍，体积小10倍。
- 适合医疗图像分析、小模型部署及快速训练场景。
开发医学图像分析的基础模型对于克服放射科任务的独特挑战至关重要。2025年MICCAI会议上首次举办了针对3D脑部MRI的两项基础模型挑战赛：SSL3D与FOMO25。我们的方案在两个赛道均排名第一。该方法基于U-Net卷积神经网络架构，融合了解剖先验和神经影像领域知识。值得注意的是，相比基于Transformer的竞争模型，我们的模型训练速度快1至2个数量级，体积缩小了10倍。相关模型已公开：https://github.com/jbanusco/BrainFM4Challenges。
原文摘要 · Abstract (English)
Developing Foundation Models for medical image analysis is essential to overcome the unique challenges of radiological tasks. The first challenges of this kind for 3D brain MRI, SSL3D and FOMO25, were held at MICCAI 2025. Our solution ranked first in tracks of both contests. It relies on a U-Net CNN architecture combined with strategies leveraging anatomical priors and neuroimaging domain knowledge. Notably, our models trained 1-2 orders of magnitude faster and were 10 times smaller than competing transformer-based approaches. Models are available here: https://github.com/jbanusco/BrainFM4Challenges.
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。