用于引入未见医学成像模态的可转移低秩卷积基

中文摘要 AI 辅助

部署一个日后必须适应其从未见过的模态的医学成像模型是一个反复出现的实际问题：重新训练共享表示成本高昂，且会破坏已投入使用的模态的性能。我们在严格的留一域出协议下研究这个“引入”问题，其中卷积骨干在源模态（肾脏CT和脑部MRI）上预训练，永久冻结，然后要求其适应未见模态（胸部X光）。在此协议下我们有三个发现。首先，当骨干从未观察过目标目标模态时，决策层参数高效微调是不够的：线性探针和全连接的LoRA都远远达不到要求，而卷积LoRA能恢复大部分可实现的准确率，表明适应必须触及卷积特征。其次，核心的是，在源模态上学习的低秩卷积“基”是可转移的：冻结该基并仅训练其向上投影，使用仅0.78%的全微调参数就能引入未见模态，准确率比相同大小的随机基高6.11个百分点，而等效的决策层基则没有可靠的转移。第三，基于适配器的引入使源模态准确率完全不变（Δ = 0.00个百分点），而全微调只有通过灾难性地降低源模态才能达到最高目标准确率。在冻结骨干特征上的马氏距离分数在严格的源保留阈值下能高灵敏度地检测未见模态，为何时需要引入提供了实际触发条件。所有结果均在三个种子上报告，并带有配对的自助置信区间。

英文摘要

Deploying a medical imaging model that must later accommodate a modality it has never seen is a recurring practical problem: retraining the shared representation is expensive and destroys performance on the modalities already in service. We study this \emph{onboarding} problem under a strict leave-one-domain-out protocol, in which a convolutional backbone is pre-trained on source modalities (Kidney CT and Brain MRI), frozen permanently, and then required to accommodate an unseen modality (Chest X-ray). Under this protocol we establish three findings. First, decision-layer parameter-efficient fine-tuning is insufficient when the backbone has never observed the target modality: a linear probe and fully-connected LoRA both fall well short, whereas convolutional LoRA recovers most of the achievable accuracy, showing that adaptation must reach the convolutional features. Second, and centrally, the low-rank convolutional \emph{basis} learned on the source modalities \emph{transfers}: freezing that basis and training only its up-projections onboards the unseen modality using just $0.78\%$ of full fine-tuning's parameters, at an accuracy $6.11$ percentage points above a random basis of identical size, while an equivalent decision-layer basis exhibits no reliable transfer. Third, adapter-based onboarding leaves source-modality accuracy exactly unchanged ($Δ= 0.00$ pp), whereas full fine-tuning reaches the highest target accuracy only by catastrophically degrading the source modalities. A Mahalanobis score on frozen backbone features detects the unseen modality with high sensitivity at a strict source-retention threshold, providing a practical trigger for when onboarding is required. All results are reported over three seeds with paired bootstrap confidence intervals.

发表机构

• Bangladesh University of Engineering and Technology (BUET)（孟加拉国工程技术大学）
• Osaka Metropolitan University（大阪都市大学）
• Chittagong University of Engineering and Technology (CUET)（吉大港工程技术大学）
• Kochi University of Technology（高知工科大学）

机构由 AI 辅助整理，请以论文原文为准。