通过主动学习与选择性半监督微调适配医学视觉基础模型以用于体积医学图像分割
Adapting Medical Vision Foundation Models for Volumetric Medical Image Segmentation via Active Learning and Selective Semi-supervised Fine-tuning
AI总结：
针对医学视觉基础模型高效适配目标域分割任务的需求，提出主动无源域适配方法，结合新型主动学习样本查询策略与选择性半监督微调，以最小样本预算实现体积医学图像分割性能提升。
摘要：
医学视觉基础模型（Med-VFMs）凭借从大量未标注图像的自监督预训练中习得的知识，具备出色的医学图像解读能力。为提升其在自适应下游任务（尤其是分割任务）上的性能，现有方法通常随机选取少量目标域样本进行微调，但目前缺乏探索如何高效适配Med-VFMs以在目标域上实现最优性能的研究，因此亟需设计一种通过选取高信息量样本微调Med-VFMs、最大化其目标域适配性能的高效方法。\n为实现这一目标，我们提出主动无源域适配（Active Source-Free Domain Adaptation, ASFDA）方法，可高效将Med-VFMs适配至目标域以完成体积医学图像分割任务。该ASFDA方法采用一种新型主动学习（Active Learning, AL）方法，在无需访问源域预训练样本的前提下，从目标域中选取信息量最高的样本用于微调Med-VFMs，从而以最小的选取预算实现性能最大化。在该AL方法中，我们设计了主动测试时样本查询策略，通过两个查询指标从目标域选取样本，分别是多样化知识散度（Diversified Knowledge Divergence, DKD）和解剖结构分割难度（Anatomical Segmentation Difficulty, ASD）。其中DKD用于衡量源域-目标域的知识差距与域内多样性，它利用预训练知识引导选取目标域中与源域差异大、语义多样性高的样本；ASD通过自适应测量前景区域的预测熵，评估解剖结构的分割难度。此外，我们的ASFDA方法采用选择性半监督微调策略，通过从未查询样本中识别高可靠性样本，提升微调的性能与效率。
英文摘要：
Medical Vision Foundation Models (Med-VFMs) have superior capabilities of interpreting medical images due to the knowledge learned from self-supervised pre-training with extensive unannotated images. To improve their performance on adaptive downstream evaluations, especially segmentation, a few samples from target domains are selected randomly for fine-tuning them. However, there lacks works to explore the way of adapting Med-VFMs to achieve the optimal performance on target domains efficiently. Thus, it is highly demanded to design an efficient way of fine-tuning Med-VFMs by selecting informative samples to maximize their adaptation performance on target domains. To achieve this, we propose an Active Source-Free Domain Adaptation (ASFDA) method to efficiently adapt Med-VFMs to target domains for volumetric medical image segmentation. This ASFDA employs a novel Active Learning (AL) method to select the most informative samples from target domains for fine-tuning Med-VFMs without the access to source pre-training samples, thus maximizing their performance with the minimal selection budget. In this AL method, we design an Active Test Time Sample Query strategy to select samples from the target domains via two query metrics, including Diversified Knowledge Divergence (DKD) and Anatomical Segmentation Difficulty (ASD). DKD is designed to measure the source-target knowledge gap and intra-domain diversity. It utilizes the knowledge of pre-training to guide the querying of source-dissimilar and semantic-diverse samples from the target domains. ASD is designed to evaluate the difficulty in segmentation of anatomical structures by measuring predictive entropy from foreground regions adaptively. Additionally, our ASFDA method employs a Selective Semi-supervised Fine-tuning to improve the performance and efficiency of fine-tuning by identifying samples with high reliability from unqueried ones.
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。
