arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.07960cs.CVcs.LG
收藏

视觉基础模型是否能增强医学图像分割中的域泛化能力?

Do Vision Foundation Models Enhance Domain Generalization in Medical Image Segmentation?

ETH Zurich(苏黎世联邦理工学院);ETH AI Center(苏黎世联邦理工学院人工智能中心);The LOOP Zürich – Medical Research Center(苏黎世LOOP医学研究中心)

Kerem Cekmeceli, Meva Himmetoglu, Guney I. Tombak, Anna Susmelj, Ertunc Erdil, Ender Konukoglu

AI总结:

该研究针对医学图像分割中的域偏移问题,探究多种视觉基础模型搭配不同参数高效微调技术及新型HQHSAM解码器头的域泛化性能,证实基础模型可提升该任务泛化能力,为后续研究提供基础。

摘要:

当训练数据分布与测试数据分布匹配时,神经网络在许多监督学习任务中能达到当前最优性能。但在域(协变量)偏移情况下,其性能会显著下降——由于不同扫描仪型号和采集协议存在差异,这是医学图像分割中普遍存在的问题。近年来,在大型数据集上训练的基础模型(FMs)因具备适配下游任务的能力,且在自然图像上能实现当前最优性能并展现出色的泛化能力而受到关注,但它们在医学图像分割中的有效性仍未得到充分探究。\n本文研究了DinoV2、SAM、MedSAM和MAE等多种基础模型在采用Ladder、Rein(+LoRA)等参数高效微调(PEFT)技术及解码器头进行微调时的域泛化性能。我们提出了一种新型解码器头架构HQHSAM,它简单整合了HSAM和HQSAM这两种当前最优解码器头的元素,以提升分割性能。\n我们在涵盖多种解剖结构和模态的多个数据集上开展了大量实验,结果表明基础模型(尤其是搭配HQHSAM解码器头时)能提升医学图像分割的域泛化能力。此外,我们还发现PEFT技术的有效性因基础模型的不同而存在差异。这些发现凸显了基础模型在多样化临床场景下提升神经网络医学图像分割域泛化性能的潜力,为未来研究奠定了坚实基础。代码和模型可用于研究目的,获取地址为https://github.com/kerem-cekmeceli/Foundation-Models-for-Medical-Imagery。

英文摘要:

Neural networks achieve state-of-the-art performance in many supervised learning tasks when the training data distribution matches the test data distribution. However, their performance drops significantly under domain (covariate) shift, a prevalent issue in medical image segmentation due to varying acquisition settings across different scanner models and protocols. Recently, foundational models (FMs) trained on large datasets have gained attention for their ability to be adapted for downstream tasks and achieve state-of-the-art performance with excellent generalization capabilities on natural images. However, their effectiveness in medical image segmentation remains underexplored. In this paper, we investigate the domain generalization performance of various FMs, including DinoV2, SAM, MedSAM, and MAE, when fine-tuned using various parameter-efficient fine-tuning (PEFT) techniques such as Ladder and Rein (+LoRA) and decoder heads. We introduce a novel decode head architecture, HQHSAM, which simply integrates elements from two state-of-the-art decoder heads, HSAM and HQSAM, to enhance segmentation performance. Our extensive experiments on multiple datasets, encompassing various anatomies and modalities, reveal that FMs, particularly with the HQHSAM decode head, improve domain generalization for medical image segmentation. Moreover, we found that the effectiveness of PEFT techniques varies across different FMs. These findings underscore the potential of FMs to enhance the domain generalization performance of neural networks in medical image segmentation across diverse clinical settings, providing a solid foundation for future research. Code and models are available for research purposes at \url{https://github.com/kerem-cekmeceli/Foundation-Models-for-Medical-Imagery}.

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。

↑