如何训练你的 CheXDragon：训练胸部X射线模型以迁移到新任务和医疗系统
How to Train Your CheXDragon: Training Chest X-Ray Models for Transfer to Novel Tasks and Healthcare Systems
AI总结：
本研究系统比较了监督与自监督预训练策略，发现多模态自监督学习在迁移到新医疗系统和任务时性能显著优于单模态，并验证了DAPT和LP-FT等适应策略的额外增益。
摘要：
自监督学习（SSL）使得机器学习模型的标签高效训练成为可能。这对于医学影像等领域至关重要，因为在这些领域中，标签的获取成本高昂且耗时。然而，将模型迁移到不同医疗系统或新任务的最有效的监督或自监督策略尚不明确。在本工作中，我们使用医学图像（胸部X射线）和文本（放射学报告）的多模态数据集，系统地实验了多种监督和自监督预训练策略。随后，我们在来自两个外部机构、包含多样化任务集的数据上评估了这些策略的性能。此外，我们实验了不同的迁移学习策略，以有效地将这些预训练模型适应到新任务和医疗系统。我们的实证结果表明，多模态自监督学习在新医疗系统和任务上的性能显著优于单模态自监督学习，与完全监督预训练的模型相当。我们进一步展示了通过多模态领域自适应预训练（DAPT）、线性探测后微调（LP-FT）以及两者结合的方法，对模型进行进一步适应新数据集和任务后所带来的额外性能提升。我们为那些并非所有上述方法都可行的场景提供了替代模型的建议。我们的结果为改善医学图像解释模型在新医疗系统和新任务上的泛化能力提供了指导。
英文摘要：
Self-supervised learning (SSL) enables label efficient training for machine learning models. This is essential for domains such as medical imaging, where labels are costly and time-consuming to curate. However, the most effective supervised or SSL strategy for transferring models to different healthcare systems or novel tasks is not well understood. In this work, we systematically experiment with a variety of supervised and self-supervised pretraining strategies using multimodal datasets of medical images (chest X-rays) and text (radiology reports). We then evaluate their performance on data from two external institutions with diverse sets of tasks. In addition, we experiment with different transfer learning strategies to effectively adapt these pretrained models to new tasks and healthcare systems. Our empirical results suggest that multimodal SSL gives substantial gains over unimodal SSL in performance across new healthcare systems and tasks, comparable to models pretrained with full supervision. We demonstrate additional performance gains with models further adapted to the new dataset and task, using multimodal domain-adaptive pretraining (DAPT), linear probing then finetuning (LP-FT), and both methods combined. We offer suggestions for alternative models to use in scenarios where not all of these additions are feasible. Our results provide guidance for improving the generalization of medical image interpretation models to new healthcare systems and novel tasks.
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。
