Medical AI systems face catastrophic forgetting when deployed in clinical settings, where models must learn new imaging protocols while retaining prior diagnostic capabilities. This challenge is particularly acute for medical vision-language models that must preserve complex cross-modal alignments between medical images and clinical terminology across diverse imaging modalities. We introduce Prompt- Aware Adaptive Elastic Weight Consolidation (PA-EWC), a novel continual learning approach that addresses catastrophic forgetting through prompt-guided parameter specialization. Our method systematically categorizes model parameters based on their functional roles in processing visual-descriptive, spatial-guided, and medical-semantic information, enabling targeted protection of critical knowledge while allowing adaptation to new clinical requirements. PA-EWC incorporates adaptive Fisher Information computation with gradient stability analysis and develops weighted complexity metrics based on medical terminology density. We evaluate our approach across five medical imaging datasets (Kvasir-SEG, ISIC 2018, CheXlocalize, BUSI, CAMUS) representing diverse modalities including endoscopy, dermoscopy, radiography, and ultrasound. Experimental results demonstrate that PA-EWC reduces catastrophic forgetting by up to 17.58% compared to baseline methods, with performance improvements of 4.30% on chest X-ray pathology localization and 6.06% on polyp segmentation.


翻译:医学人工智能系统在临床部署中面临灾难性遗忘问题,模型需要学习新的成像协议同时保留原有诊断能力。这一挑战对于医学视觉语言模型尤为严峻,因为模型必须跨不同成像模态保持医学影像与临床术语间复杂的跨模态对齐关系。本文提出基于提示感知的自适应弹性权重巩固方法,这是一种通过提示引导参数专业化解决灾难性遗忘的新型持续学习方法。该方法根据模型参数在处理视觉描述、空间引导和医学语义信息中的功能角色进行系统分类,实现对关键知识的针对性保护,同时适应新的临床需求。PA-EWC结合梯度稳定性分析的自适应费舍尔信息计算,并基于医学术语密度构建加权复杂度度量。我们在涵盖内窥镜、皮肤镜、放射摄影和超声等多种模态的五个医学影像数据集(Kvasir-SEG、ISIC 2018、CheXlocalize、BUSI、CAMUS)上评估该方法。实验结果表明,与基线方法相比,PA-EWC将灾难性遗忘降低达17.58%,在胸部X光病理定位任务上性能提升4.30%,在息肉分割任务上提升6.06%。

0
下载
关闭预览

相关内容

Top
微信扫码咨询专知VIP会员