用3D Swin Transformer结合脑解剖知识，提升脑MRI预训练效果
Domain Aware Multi-Task Pretraining of 3D Swin Transformer for T1-weighted Brain MRI
- 设计融合脑部解剖与形态的多任务自监督学习方法
- 在1.37万例脑MRI上预训练，三项下游任务均超越现有方法
- 适合需要高精度脑影像分析的研究者或医疗AI开发者
医学图像标注数据稀缺是制约医学图像分析模型发展的主要瓶颈。为此，近期研究聚焦于减少标注需求的预训练模型，可通过微调应用于多种下游任务。然而，现有方法多为2D方法的简单3D扩展，不适用于3D医学影像数据。针对此问题，我们提出一种新的领域感知多任务学习策略，用于预训练3D Swin Transformer进行脑磁共振成像（MRI）分析。该方法结合脑部解剖结构与形态特征，并在对比学习框架下引入适配3D影像的标准预训练任务。我们在涵盖多个大型数据库的13,687例大规模脑MRI数据上进行预训练。实验表明，该方法在阿尔茨海默病分类、帕金森病分类及年龄预测三个下游任务中均优于现有监督与自监督方法。消融实验证明了所提预训练任务的有效性。
原文摘要 · Abstract (English)
The scarcity of annotated medical images is a major bottleneck in developing learning models for medical image analysis. Hence, recent studies have focused on pretrained models with fewer annotation requirements that can be fine-tuned for various downstream tasks. However, existing approaches are mainly 3D adaptions of 2D approaches ill-suited for 3D medical imaging data. Motivated by this gap, we propose novel domain-aware multi-task learning tasks to pretrain a 3D Swin Transformer for brain magnetic resonance imaging (MRI). Our method considers the domain knowledge in brain MRI by incorporating brain anatomy and morphology as well as standard pretext tasks adapted for 3D imaging in a contrastive learning setting. We pretrain our model using large-scale brain MRI data of 13,687 samples spanning several large-scale databases. Our method outperforms existing supervised and self-supervised methods in three downstream tasks of Alzheimer's disease classification, Parkinson's disease classification, and age prediction tasks. The ablation study of the proposed pretext tasks shows the effectiveness of our pretext tasks.
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。