Foundation X：通过锁-释放预训练策略整合分类、定位和分割以用于胸部 X 光分析
Foundation X: Integrating Classification, Localization, and Segmentation through Lock-Release Pretraining Strategy for Chest X-ray Analysis
AI总结：
针对胸部 X 光多任务标注异构问题，提出 Foundation X 端到端框架，采用 Lock-Release 预训练与师生学习，在 11 个数据集上提升分类、定位和分割性能。
摘要：
开发鲁棒且通用的深度学习模型，对于提高医学影像中的诊断准确性并指导临床干预至关重要，但这需要大量带标注数据。深度学习的发展促进了许多具有多样化专家级标注的医学数据集的创建。聚合这些数据集可以最大化数据利用，并解决标注数据不足的问题。然而，分类、定位和分割等任务之间专家级标注的异构性，给从这些数据集中学习带来了重大挑战。为此，我们提出 nFoundation X，这是一个端到端框架，利用来自众多公开数据集的多样化专家级标注来训练一个能够执行分类、定位和分割等多项任务的基础模型。为应对标注和任务异构性的挑战，我们提出一种锁-释放（Lock-Release）预训练策略，以增强来自多个数据集的循环学习，并结合学生-教师学习范式，确保模型保留适用于所有任务的通用知识，同时防止对任何单一任务过拟合。为证明 Foundation X 的有效性，我们使用 11 个胸部 X 光数据集训练了一个模型，这些数据集涵盖分类、定位和分割任务的标注。实验结果表明，Foundation X 通过广泛利用标注取得了显著的性能提升，在跨数据集和跨任务学习中表现出色，并进一步提升了器官定位和分割任务的性能。所有代码和预训练模型均可在 https://github.com/jlianglab/Foundation_X 公开获取。
英文摘要：
Developing robust and versatile deep-learning models is essential for enhancing diagnostic accuracy and guiding clinical interventions in medical imaging, but it requires a large amount of annotated data. The advancement of deep learning has facilitated the creation of numerous medical datasets with diverse expert-level annotations. Aggregating these datasets can maximize data utilization and address the inadequacy of labeled data. However, the heterogeneity of expert-level annotations across tasks such as classification, localization, and segmentation presents a significant challenge for learning from these datasets. To this end, we introduce nFoundation X, an end-to-end framework that utilizes diverse expert-level annotations from numerous public datasets to train a foundation model capable of multiple tasks including classification, localization, and segmentation. To address the challenges of annotation and task heterogeneity, we propose a Lock-Release pretraining strategy to enhance the cyclic learning from multiple datasets, combined with the student-teacher learning paradigm, ensuring the model retains general knowledge for all tasks while preventing overfitting to any single task. To demonstrate the effectiveness of Foundation X, we trained a model using 11 chest X-ray datasets, covering annotations for classification, localization, and segmentation tasks. Our experimental results show that Foundation X achieves notable performance gains through extensive annotation utilization, excels in cross-dataset and cross-task learning, and further enhances performance in organ localization and segmentation tasks. All code and pretrained models are publicly accessible at https://github.com/jlianglab/Foundation_X.
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。
