Adversarially Based Virtual CT Workflow for Evaluation of AI in Medical Imaging

基于对抗性的虚拟 CT 工作流程，用于评估医学影像中的人工智能

• 批准号: 10592427
• 负责人: Xun Jia
• 金额: $ 61.56万
• 依托单位: RENSSELAER POLYTECHNIC INSTITUTE
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-04-01 至 2025-12-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10592427
• 关键词: Acceleration; Address; Agreement; Anatomy; Artificial Intelligence; Authorization documentation; Big Data; Bypass; Catalogs; Chest; Classification; Clinical; Code; Communities; Computer software; Data; Data Set; Detection; Development; Diagnostic; Disease; Effectiveness; Elements; Ensure; Evaluation; Evaluation Methodology; Feedback; Future; Generations; Goals; Head; Human; Image; Image Analysis; Individual; Industrialization; Infrastructure; Internet; Label; Learning; Machine Learning; Mainstreaming; Marketing; Masks; Medical; Medical Device; Medical Imaging; Medicine; Methods; Modeling; Nature; Pathologic; Pathway Analysis; Patients; Performance; Play; Population; Positioning Attribute; Publishing; Regulation; Research; Research Personnel; Retrieval; Role; Running; Safety; Sampling; Science; Semantics; System; Techniques; Testing; Texas; Training; Translations; Universities; Validation; Vendor; Work; X-Ray Computed Tomography; algorithmic bias; authority; clinical application; clinical predictors; clinical translation; clinically relevant; deep learning; deep neural network; empowerment; federated learning; image processing; image reconstruction; imaging modality; improved; innovation; interest; learning strategy; low dose computed tomography; lung cancer screening; novel strategies; patient privacy; prototype; radiomics; reconstruction; simulation; tomography; tool; virtual; virtual patient; web site

Adversarially Based Virtual CT Workflow for Evaluation of AI in Medical Imaging ABSTRACT Over the past several years, artificial intelligence (AI) and machine learning (ML), especially deep learning (DL), has been the most prominent direction of tomographic research, commercial development, clinical translation, and FDA evaluation. Recently, it has become widely recognized that deep neural networks often have generalizability issues and are vulnerable to adversarial attacks, deliberate or unintentional. This critical challenge must be addressed to optimize the performance of deep neural networks in medical applications. In January this year, FDA published an action plan for furthering the oversight for AI/DL-based software as medical devices (SaMDs). One major action underlined in the plan is “regulatory science methods related to algorithm bias and robustness”. The significance of ensuring the safety and effectiveness of AI/DL-based SaMDs cannot be overestimated since AI is expected to play a critical role in the future of medicine. In this context, the overall goal of this academic-FDA partnership R01 project is to generate diverse training and challenging testing datasets of low-dose CT (LDCT) scans, prototype a virtual CT workflow, and establish an evaluation methodology for AI-based imaging products to support FDA marketing authorization. The technical innovation lies in cutting-edge DL methods empowered by (a) adversarial learning to generate anatomically and pathologically representative features in the human chest; (b) adversarial attacking to probe the virtual CT workflow in individual steps and its entirety; and (c) systematic evaluation methods to better characterize and predict the clinical performance of AI-based imaging products. In contrast to other CT simulation pipelines, our Adversarially Based CT (ABC) platform relies on adversarial learning to ensure diversity and realism of the simulated data and images and improve the generalizability of deep networks, and utilizes adversarial samples to probe the ABC workflow to address the robustness of deep networks. The overarching hypothesis is that adversarial learning and attacking methods are powerful to deliver high- quality datasets for AI-based imaging research and performance evaluation. The specific aims are: (1) diverse patient modeling (SBU), (2) virtual CT scanning (UTSW), (3) deep CT imaging (RPI), (4) virtual workflow validation (FDA), and (5) ABC system dissemination (RPI-SBU-UTSW-FDA). In this project, generative adversarial learning will play an instrumental role in generating features of clinical semantics. Also, adversarial samples will be produced in both sinogram and image domains. In these complementary ways, AI-based imaging products can be efficiently evaluated for not only accuracy but also generalizability and robustness. Upon completion, our ABC workflow/platform will be made publicly available and readily extendable to other imaging modalities and other diseases. This ABC system will be shared through the FDA’s Catalog of Regulatory Science Tools, and uniquely well positioned to greatly facilitate the development, assessment and translation of emerging AI-based imaging products.

基于对抗的虚拟CT工作流，用于评估医学成像中的AI 抽象的 在过去的几年中，人工智能（AI）和机器学习（ML），尤其是深度学习（DL）， 一直是层析成像研究，商业发展，临床翻译的最突出的方向， 和FDA评估。最近，它已被广泛认识到深度神经网络经常有 概括性问题，容易受到对抗性攻击，故意或无意的。这个批评 必须应对挑战以优化医疗应用中深神经网络的性能。 今年1月，FDA发布了一项行动计划，以推动基于AI/DL的软件的监督为 医疗设备（SAMDS）。该计划中强调的一项重大行动是“与 算法偏见和鲁棒性”。确保基于AI/DL的安全性和有效性的重要性 由于预计AI在医学的未来中会发挥关键作用，因此不能高估SAMD。在这个 背景下，该学术FDA合作伙伴R01项目的总体目标是生成潜水员培训和 低剂量CT（LDCT）扫描的测试数据集，原型虚拟CT工作流程并建立一个 基于AI的成像产品的评估方法支持FDA营销授权。技术 创新在于由（a）对抗性学习赋予的尖端DL方法 并在病理上代表人胸部的特征； （b）对抗攻击以探测虚拟CT 单个步骤及其整体的工作流程； （c）更好地表征和 预测基于AI的成像产品的临床性能。与其他CT模拟管道相反，我们 基于对抗的CT（ABC）平台依赖于对抗性学习，以确保多样性和现实主义 模拟数据和图像并改善深网的普遍性，并利用对抗样本 探测ABC工作流程以解决深网的鲁棒性。 总体假设是，对抗性学习和攻击方法具有强大的功能 用于基于AI的成像研究和性能评估的质量数据集。具体目的是：（1）潜水员 患者建模（SBU），（2）虚拟CT扫描（UTSW），（3）深CT成像（RPI），（4）虚拟工作流程 验证（FDA）和（5）ABC系统传播（RPI-SBU-UTSW-FDA）。在这个项目中，生成 对抗性学习将在产生临床语义的特征方面发挥工具作用。另外，对抗性 样品将在正式和图像域中产生。以这些完整的方式，基于AI 成像产物不仅可以有效地评估精度，而且可以概括性和鲁棒性进行评估。 完成后，我们的ABC工作流程/平台将公开可用，并易于扩展到其他 成像方式和其他疾病。该ABC系统将通过FDA的目录共享 监管科学工具，并具有良好的位置，可以极大地支持开发，评估和 基于AI的成像产品的翻译。