arXiv 2304.108802024-05-28cs.CV

Med-Tuning：一种用于医学体积分割的新型参数高效微调框架

Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation

School of Automation and Electrical Engineering, University of Science and Technology Beijing（北京科技大学自动化与电气工程学院）；Center for Research in Computer Vision, University of Central Florida（中佛罗里达大学计算机视觉研究中心）；School of Computer Science, University of Birmingham（伯明翰大学计算机学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）

Jiachen Shen, Wenxuan Wang, Chen Chen, Jianbo Jiao, Jing Liu, Yan Zhang, Shanshan Song, Jiangyun Li

备注：: Accepted by MIDL 2024

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出Med-Tuning框架和Med-Adapter模块，通过少量参数微调预训练模型，在医学体积分割任务上实现优于全量微调的性能，参数减少达4倍。

摘要：

“预训练后微调（FT）”范式被广泛采用，以提升基于深度学习方法的医学体积分割模型的性能。然而，传统的全量微调会带来高昂的计算和内存成本。因此，以既有效又参数高效的方式对预训练模型进行微调，以应用于医学体积分割任务，变得越来越重要。在本文中，我们引入了一个名为Med-Tuning的新框架，以实现医学体积分割任务的参数高效微调（PET），并设计了一个名为Med-Adapter的高效即插即用模块，用于任务特定的特征提取。通过少量微调参数，我们的框架增强了在自然图像上预训练的2D基线模型在分割任务上的精度。在三个基准数据集（CT和MRI模态）上的大量实验表明，我们的方法在体积分割任务上取得了优于以往PET方法的结果。与全量微调相比，Med-Tuning将微调模型参数减少了最多4倍，同时分割性能甚至更优。我们的项目网页位于\url{https://rubics-xuan.github.io/Med-Tuning/}。

英文摘要：

The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boost the model performance of deep learning-based methods for medical volumetric segmentation. However, conventional full FT incurs high computational and memory costs. Thus, it is of increasing importance to fine-tune pre-trained models for medical volumetric segmentation tasks in a both effective and parameter-efficient manner. In this paper, we introduce a new framework named Med-Tuning to realize parameter-efficient tuning (PET) for medical volumetric segmentation task and an efficient plug-and-play module named Med-Adapter for task-specific feature extraction. With a small number of tuned parameters, our framework enhances the 2D baselines's precision on segmentation tasks, which are pre-trained on natural images. Extensive experiments on three benchmark datasets (CT and MRI modalities) show that our method achieves better results than previous PET methods on volumetric segmentation tasks. Compared to full FT, Med-Tuning reduces the fine-tuned model parameters by up to 4x, with even better segmentation performance. Our project webpage is at \url{https://rubics-xuan.github.io/Med-Tuning/}.

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。