Development of COVID-19 Imaging Tools with Artificial Intelligence

利用人工智能开发 COVID-19 成像工具

• 批准号: 10487067
• 负责人: Bradford J Wood
• 金额: $ 23.23万
• 依托单位: DIVISION OF BASIC SCIENCES - NCI
• 依托单位国家: 美国
• 资助国家: 美国
• 起止时间: 至
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10487067
• 关键词: 3D Print; Artificial Intelligence; Bacterial Pneumonia; Biological Markers; COVID-19; COVID-19 detection; COVID-19 pneumonia; Chest; Child; Classification; Clinical; Clinical Research; Clinical Trials; Combined Modality Therapy; Communicable Diseases; Communities; Contact Tracing; Critical Care; Data; Data Aggregation; Data Set; Development; Devices; Disease; Disease Outbreaks; Drug Combinations; Extramural Activities; Family suidae; Goals; Image; Imaging Device; Immunology; Industry; Influenza; Influenza A Virus, H1N1 Subtype; Journals; Laboratories; Learning; Lung; Malignant Neoplasms; Medical Imaging; Medical center; Metadata; Methodology; Modeling; National Institute of Allergy and Infectious Disease; Outcome; Outcome Measure; Output; Pathway interactions; Performance; Pharmaceutical Preparations; Publishing; Research; Resource Allocation; Signal Transduction; Source; Standardization; Supportive care; Techniques; Testing; The Cancer Imaging Archive; Therapeutic; Thoracic Radiography; Training; Translating; United States National Institutes of Health; Validation; Ventilator; Viral Pneumonia; Virus Shedding; Work; X-Ray Computed Tomography; air filtration; base; chest computed tomography; clinically relevant; coronavirus disease; crosslink; cytokine; deep learning; disease phenotype; drug discovery; fungal pneumonia; image processing; imaging biomarker; industry partner; influenza pneumonia; large datasets; member; model building; nonhuman primate; outcome prediction; pandemic disease; point of care; pre-clinical; preclinical study; predictive modeling; radiologist; response; success; tool; web site

Public data posting of CT scans on public NCI TCIA websites were made. AI deep learning models were made alongside of multiple industry partners, to educate on the serial temporal dynamics of COVID-19. . AI deep learning models were built and publicly posted on a partner's pipeline for research purposes that could automatically segment COVID-19 opacities and classify COVID-19 on an initial point of care CT scan, built on multi-national outbreak training data. Model output was % likelihood COVID on chest CT scans. NIH CC and NCI were among the first to gather multi-national data and develop freeware public AI solutions based on COVID CTs for both academic and commercial developer use. A data challenge was also done for public use alongside of MICCAI and Children's National Medical Center. A uniform and validated imaging biomarker solution for use for a clinical trial setting could expedite the pathway towards drug discovery and early validation or response signals. The NIH team is working with commercial and academic partners to assess quantification tools for COVID metrics. NIH models can detect COVID-19 and differentiate from H1N1 influenza, fungal, or bacterial pneumonias as well as cancer, normal lungs, and other entities with high performance. Ongoing work will attempt to identify and flag CT cases for immediate radiologist review, thus flagging and encouraging isolation, PCR testing, and contact tracing for high suspicion and or asymptomatic cases. Other models predict the later need for critical care therapies based upon an initial CT scan or chest x-ray at the initial point of care. The ability to standardize the quantification of CT responses would enable critical cross-platform comparisons among drug combinations and therapeutic approaches, which is vital, given the necessity for combination therapies across classes of drugs in supportive therapy pathways. It has also been shown that pre-symptomatic CT AI can track disease in a predictable fashion, and that this disease dynamic curve is recapitulated in a non-human primate model of COVID-19. Prior work with extramural partners has demonstrated that federated learning can overcome shortcomings in unbalanced source data for imaging AI, and that the application of a specific federated learning technique can overcome the gap, thus showing that the data does not need to be shared in order to build quality AI models from medical imaging. The chest X-ray AI predictive model using federated learning will soon be published in a high-impact journal. BACKGROUND / SIGNIFICANCE: CT image processing and deep learning models provide quantifiable metrics to serve as a noninvasive biomarker for pulmonary involvement. Correlation with a variety of clinically relevant metadata may enable the use of CT AI during outbreaks to identify CT biomarker features for standardized quantification in clinical trials for COVID-19. This effort cross links with numerous campus efforts, including preclinical NIAID efforts and clinical validation trials for image processing for classification and characterization in COVID-19. A multi-national dataset in COVID-19 is being collected and curated to build public models for COVID-19 classification and quantification and has verified that asymptomatic viral shedding may co-exist in the presence of a positive CT scan with analysis of thousands of CT scans from 4 nations. GOALS: Facilitate validation of a standardized tool for establishment of public deep learning models for quantification and standard response criteria metrics for characterization of COVID-19 clinical trials. HYPOTHESIS: CT imaging data aggregation and artificial intelligence will inform and expedite clinical and preclinical studies of COVID-19. SPECIFIC AIMS: Develop, validate, and translate tools for automated and standardized CT assessment and quantification of COVID-19 disease with deep learning methodologies for use during clinical trials. CC/NCI team members also deployed a 3D-printed miniature ventilator in swine (now commercialized) as well as a disposable isolation bag device with in-line air filtration. CT AI models were licensed to industry.

CT 扫描的公开数据已发布在 NCI TCIA 公共网站上。 AI 深度学习模型是与多个行业合作伙伴共同开发的，旨在了解 COVID-19 的序列时间动态。 。出于研究目的，建立了 AI 深度学习模型并在合作伙伴的管道上公开发布，该模型可以根据多国疫情爆发训练数据，在初始护理点 CT 扫描上自动分割 COVID-19 不透明区域并对 COVID-19 进行分类。模型输出为胸部 CT 扫描中出现新冠肺炎的可能性百分比。 NIH CC 和 NCI 是最早收集跨国数据并开发基于新冠病毒 CT 的免费软件公共人工智能解决方案的机构之一，供学术和商业开发人员使用。还与 MICCAI 和儿童国家医疗中心一起开展了供公众使用的数据挑战。用于临床试验环境的统一且经过验证的成像生物标志物解决方案可以加快药物发现和早期验证或响应信号的进程。美国国立卫生研究院 (NIH) 团队正在与商业和学术合作伙伴合作，评估新冠肺炎指标的量化工具。 NIH 模型可以检测 COVID-19，并以高性能区分 H1N1 流感、真菌或细菌性肺炎以及癌症、正常肺部和其他实体。正在进行的工作将尝试识别和标记 CT 病例，以供放射科医生立即审查，从而标记和鼓励对高度怀疑和/​​或无症状病例进行隔离、PCR 检测和接触者追踪。其他模型根据初始护理点的初始 CT 扫描或胸部 X 光检查来预测稍后需要重症护理治疗。标准化 CT 反应量化的能力将使药物组合和治疗方法之间进行关键的跨平台比较，这一点至关重要，因为在支持治疗途径中需要跨类别药物进行联合治疗。研究还表明，症状前 CT AI 可以以可预测的方式追踪疾病，并且这种疾病动态曲线在 COVID-19 的非人类灵长类动物模型中得到了重现。此前与外部合作伙伴的合作已经证明，联邦学习可以克服成像人工智能源数据不平衡的缺点，并且特定联邦学习技术的应用可以克服这一差距，从而表明不需要共享数据即可从医学成像构建高质量的人工智能模型。使用联邦学习的胸部 X 射线 AI 预测模型即将在高影响力期刊上发表。背景/意义：CT 图像处理和深度学习模型提供了可量化的指标，可作为肺部受累的无创生物标志物。与各种临床相关元数据的关联可以在疫情爆发期间使用 CT AI 来识别 CT 生物标志物特征，以便在 COVID-19 临床试验中进行标准化量化。这项工作与校园内的众多工作相互联系，包括 NIAID 的临床前工作和针对 COVID-19 分类和表征的图像处理的临床验证试验。正在收集和整理 COVID-19 的多国数据集，以构建用于 COVID-19 分类和量化的公共模型，并通过对数千个 CT 扫描的分析，证实无症状病毒排泄可能在 CT 扫描呈阳性的情况下共存来自 4 个国家的扫描。目标：促进标准化工具的验证，以建立用于量化的公共深度学习模型和用于表征 COVID-19 临床试验的标准响应标准指标。假设：CT 成像数据聚合和人工智能将为 COVID-19 的临床和临床前研究提供信息并加快其速度。具体目标：开发、验证和翻译用于自动化和标准化 CT 评估和量化 COVID-19 疾病的工具，并在临床试验期间使用深度学习方法。 CC/NCI 团队成员还在猪身上部署了 3D 打印微型呼吸机（现已商业化）以及带有在线空气过滤功能的一次性隔离袋装置。 CT AI模型已授权给行业。