While the pace of development of AI has rapidly progressed in recent years, the implementation of safe and effective regulatory frameworks has lagged behind. In particular, the adaptive nature of AI models presents unique challenges to regulators as updating a model can improve its performance but also introduce safety risks. In the US, the Food and Drug Administration (FDA) has been a forerunner in regulating and approving hundreds of AI medical devices. To better understand how AI is updated and its regulatory considerations, we systematically analyze the frequency and nature of updates in FDA-approved AI medical devices. We find that less than 2% of all devices report having been updated by being re-trained on new data. Meanwhile, nearly a quarter of devices report updates in the form of new functionality and marketing claims. As an illustrative case study, we analyze pneumothorax detection models and find that while model performance can degrade by as much as 0.18 AUC when evaluated on new sites, re-training on site-specific data can mitigate this performance drop, recovering up to 0.23 AUC. However, we also observed significant degradation on the original site after re-training using data from new sites, providing insight from one example that challenges the current one-model-fits-all approach to regulatory approvals. Our analysis provides an in-depth look at the current state of FDA-approved AI device updates and insights for future regulatory policies toward model updating and adaptive AI.
Understanding Multilingual Medical ASR Adaptation Through Layer-Wise Analysis
Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)(埃尔朗根-纽伦堡弗里德里希-亚历山大大学);University of Sheffield(谢菲尔德大学);Technical University of Munich (TUM)(慕尼黑工业大学)
QuPID: Quantum Parameter-Efficient Input-Dependent Retrieval Adaptation for Medical RAG
Korea University(高丽大学);Sookmyung Women’s University(淑明女子大学);Virginia Tech(弗吉尼亚理工学院暨州立大学);Seoul National University(首尔大学);Seoul National University Hospital(首尔大学医院)
AutoMiSeg: Automatic Medical Image Segmentation via Test-Time Adaptation of Foundation Models
Carnegie Mellon University(卡内基梅隆大学);Brown University(布朗大学);National Institute of Technology Karnataka(印度卡纳塔克国家理工学院);University of Pittsburgh(匹兹堡大学);University of Alabama at Birmingham(阿拉巴马大学伯明翰分校)
Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis
Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);Beth Israel Deaconess Medical Center(贝斯以色列女执事医疗中心);Nankai University(南开大学);The Hong Kong Polytechnic University(香港理工大学);University of Southern California(南加州大学);China University of Mining and Technology(中国矿业大学);Beijing University of Posts and Telecommunications(北京邮电大学)
Deep-based quality assessment of medical images through domain adaptation
Université d'Orléans(奥尔良大学);Institut National Des Télécommunications et TIC(国家电信与信息通信技术学院)
预测多媒体内容的质量在不同的领域经常需要。在某些应用中,质量指标是至关重要的,具有很高的影响力,并可能影响决策,如医疗多媒体诊断。在本文中,我们专注于这样的应用程序,提出了一个有效的和浅层的模型,用于预测质量的医学图像,而无需参考少量的注释数据。我们的模型基于卷积自注意力,旨在从图像的相关局部特征中对复杂表示进行建模,图像本身在图像上滑动以插值全局质量分数。我们还以无监督和半监督的方式应用领域自适应学习。该模型是通过一个数据集组成的几个图像及其相应的主观评分进行评估。所得到的结果表明,所提出的方法的效率,而且,应用域自适应概括不同的多媒体域的感知质量预测的下游任务的相关性。\footnote{Funded by the TIC-ART project, Regional fund (Region Centre-Val de Loire)}
MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling
Columbia University(哥伦比亚大学);Télécom Paris(巴黎电信学院);Institut Polytechnique de Paris(巴黎综合理工学院);University of Maryland, College Park(马里兰大学帕克分校);University of California, Irvine(加州大学欧文分校);University of Rochester(罗切斯特大学);Universidade Federal de São Paulo(圣保罗联邦大学);Duke University(杜克大学);Emory University(埃默里大学)
Pay Attention to the Atlas: Atlas-Guided Test-Time Adaptation Method for Robust 3D Medical Image Segmentation
School of Computation, Information and Technology, Technical University of Munich(慕尼黑工业大学计算、信息与技术学院);Imperial College London(伦敦帝国学院);HeartFlow, Inc.(哈特弗洛公司);School of Medicine, Klinikum rechts der Isar, Technical University of Munich(慕尼黑工业大学右岸医院医学院);Department of Engineering Science, University of Oxford(牛津大学工程科学系);Department of Computer Science, University of Sheffield(谢菲尔德大学计算机科学系)
Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image Enhancement
Southern University of Science and Technology(南方科技大学);Agency for Science, Technology and Research(新加坡科技研究局);Beijing Information Science and Technology University(北京信息科技大学);University of Science and Technology Beijing(北京科技大学)
Towards Continuous Domain adaptation for Healthcare
GE Global Research(通用电气全球研究中心)
深度学习算法在具有挑战性的医学成像问题上取得了巨大的成功。然而,在部署后,这些算法由于医学图像中的\emph{limited data issues}和\emph{diversity}而容易受到数据分布变化的影响。在本文中,我们提出了\emph{ContextNets},一个通用的记忆增强神经网络框架的语义分割,以实现连续的领域自适应,而无需再培训。与现有的方法,需要访问整个源和目标域的图像,我们的算法可以适应目标域与一些类似的图像。我们的条件推理上的任何新的输入与功能计算支持集的图像(和面具,如果可用)通过上下文嵌入,以实现特定于站点的适应。我们展示了最先进的领域自适应性能的X射线肺分割问题,从三个独立的队列,不同的疾病类型,性别,对比度和强度变化。
Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction
University College London(伦敦大学学院);Atinary Technologies(Atinary科技公司);University of Bremen(不来梅大学);Korea Advanced Institute of Science and Technology(韩国科学技术院);Ajou University School of Medicine(亚洲大学医学院);The Chinese University of Hong Kong(香港中文大学)