过去十年中,人工智能(AI)在科学领域的应用激发了多样化的跨学科研究,并在生命科学、天文学和神经科学等领域取得了显著进步。尤其是,AI的集成极大地改变了科学和临床实践,包括疾病诊断、机器人手术和药物发现,通过利用医疗图像和视频等多样化的数据模式,从而提升了整体医疗保健水平。尽管AI在医学领域的潜力不容置疑,但其在医疗保健中的实施面临几个关键障碍,包括需要大量数据集、广泛标注以及专门系统的设计劳动密集型。克服这些挑战对于AI在医疗保健中的有效开发和部署至关重要。
我们提出了创新的方法和框架来解决AI在医学中面临这些挑战,包括(1)在多个医疗中心之间实现安全数据共享,以实现大规模数据收集而不引起隐私问题,(2)强大的深度学习算法,只需要弱标注来减少标注工作量,以及(3)一个单模态、多任务的基础模型,能够适应各种数据模式和医疗任务,从而避免了重复的AI开发。这些基础性进展有望使AI在医学领域成为一个更通用和易于访问的工具,支持研究和临床应用。
代表性论文
Multi-grained Radiology Report Generation with Sentence-level Image-language Contrastive Learning, IEEE Transactions on Medical Imaging 2024
Robust deep learning from incomplete annotation for accurate lung nodule detection, Computers in Biology and Medicine 2024
Disorder-Free Data Are All You Need—Inverse Supervised Learning for Broad-Spectrum Head Disorder Detection, New England Journal of Medicine AI 2024
Pan-mediastinal neoplasm diagnosis via nationwide federated learning: a multicentre cohort study, The Lacent Digital Health 2023
Automatic intracranial abnormality detection and localization in head CT scans by learning from free-text reports, Cell Reports Medicine 2023
Relay Learning: A Physically Secure Framework for Clinical Multi-site Deep Learning, NPJ Digital Medicine 2023
Multi-modal Contrastive-Generative Pre-training for Fine-grained Skin Disease Diagnosis, IEEE International Conference on Bioinformatics and Biomedicine 2023
RATING: Medical knowledge-guided rheumatoid arthritis assessment from multimodal ultrasound images via deep learning, Patterns 2022
A Digital Mask to Safeguard Patient Privacy, Nature Medicine 2022
Deep Learning with Weak Annotation from Diagnosis reports for detection of multiple head disorders: a prospective, multicentre study, The Lancet Digital Health 2022
Toward human intervention-free clinical diagnosis of intracranial aneurysm via deep neural network, Patterns 2021