生成式人工智能与基础模型在放射学中的应用、机遇与潜在挑战
本综述探讨基础模型(FMs)与生成式AI在放射学中的演进角色。FMs利用自注意力机制处理多模态多尺度数据,经迁移学习、微调、提示工程、少样本与零样本学习适配小样本标注的医学影像任务,并可生成合成影像以缓解标注不足。FMs在多种影像模态中显示出提高诊断准确性与优化工作流的潜力,但临床整合受限于可解释性不足、潜在偏倚、隐私、监管、高算力成本及域偏移,需开发者、医疗提供者与监管机构协同应对。
要点
- 基础模型可经迁移学习、微调、提示工程、少样本与零样本学习适配小样本标注的医学影像任务。
- 生成式AI可创建合成医学影像,帮助缓解标注数据不足的限制。
- FMs在放射学多种成像模态中显示出提高诊断准确性和优化工作流的潜力。
核心结论
- 基础模型与生成式AI在放射学中具有提高诊断准确性和优化工作流的潜力,但临床整合仍面临可解释性有限、潜在偏倚、隐私、监管、高算力成本及训练数据与真实临床环境间域偏移等挑战,需技术开发者、医疗提供者与监管机构协同努力以实现负责任部署。
研究设计与样本
- 综述,检索范围与纳入文献原文未报告。
局限性
- 临床整合仍因可解释性有限、潜在偏倚、隐私顾虑、监管约束、高算力成本以及训练数据与真实临床环境之间的域偏移等问题而具有挑战性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Foundation models (FMs) represent a transformative advancement in artificial intelligence (AI), with growing applications in medical imaging. These models leverage self-attention mechanisms and are capable of processing multimodal data, such as images, text, audio, and video, across multiple scales. Although FMs require large datasets for initial training, they can be adapted to specific medical imaging tasks using smaller labeled datasets through techniques such as transfer learning, fine-tuning, prompt engineering, few-shot learning, and zero-shot learning, making them especially valuable in data-scarce settings. Many FMs also incorporate generative AI capabilities that support the creation of synthetic medical images to further address annotation limitations. Current applications span various imaging modalities in radiology, where FMs have shown potential to improve diagnostic accuracy and streamline workflows. However, clinical integration remains challenging due to issues such as limited interpretability, potential bias, privacy concerns, regulatory constraints, high computational costs, and domain shifts between training data and real-world clinical environments. Addressing these barriers will require coordinated efforts among technical developers, health care providers, and regulatory bodies. This review explores the evolving role of FMs and generative AI in radiology, highlighting recent research advances, clinical applications, and the key challenges that must be addressed for responsible deployment.
引用
- Tavakoli N, Shakeri Z, Gowda V, et al. Generative AI and Foundation Models in Radiology: Applications, Opportunities, and Potential Challenges. Radiology. 2025. PMID: 41251552. doi:10.1148/radiol.242961
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。