Multi-Center Academic-Industrial Partnership for Personalized Al-Enabled High Count PET

个性化 Al 启用高计数 PET 的多中心学术-工业合作伙伴关系

• 批准号: 10682066
• 负责人: RAMSEY D. BADAWI
• 金额: $ 66.97万
• 依托单位: YALE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-05-05 至 2028-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10682066
• 关键词: Adoption; Bilateral; California; Clinic; Clinical; Clinical Data; Clinical Investigator; Computer software; Data; Data Set; Diagnosis; Diagnostic; Dose; Environment; Evaluation; Feedback; Generations; Healthcare; Human; Hybrids; Image; Injections; Investigation; Label; Lesion; Liver; Mathematics; Modeling; Noise; Organ; Patients; Performance; Physicians; Positron-Emission Tomography; Procedures; Production; Provider; Research; Research Personnel; Scanning; Services; Site; Structure; System; Techniques; Testing; Time; Training; Translating; Translations; University Hospitals; Validation; Vendor; Visual; X-Ray Computed Tomography; artificial intelligence algorithm; clinical decision-making; clinical imaging; clinical practice; deep learning; deep learning model; diagnostic accuracy; experience; imaging modality; improved; industry partner; learning network; learning strategy; real world application; reconstruction; virtual; virtual model

Abstract High image noise degrades the diagnostic efficacy and quantitative accuracy of PET, as noise could easily results in overestimation of SUV and cause false positive lesion detections in diagnosis. High image noise also decreases the confidence of clinical decision making, leading to additional unnecessary follow-ups through other imaging modalities and invasive procedure. Deep learning-based noise reduction has shown promises for PET imaging. However, existing approaches only focus on converting low-count image (e.g. acquired through low- dose injection or shorter scan time) to standard-count image in typical clinical scans. However, for both low- count and the vast majority of routinely acquired clinical PET images with normal dose and scan time, there is no approach to convert such clinical images to high-count images to further reduce the image noise, mainly due to the challenge of obtaining high-count PET images as training labels. Another challenge in the real-world application is to match the training data with the testing data, in terms of noise level, noise structure, reconstruction parameters, scanner model, etc. Such matching is particularly challenging in a multi-center multi- scanner setting. In this Academic-Industrial Partnership R01 project, we formed an ideal partnership between Visage Imaging, a leading PACS company, and three leading academic centers (Yale, MGH, UC Davis) to develop, evaluate, deploy, and translate robust deep learning methods to generate virtual-high-count PET images in a highly personalized manner by taking into account the noise level of each organ in each patient, as well as associated non-imaging patient information. The academic sites have access to a large number of high- count data that are acquired either through long dynamic scans (at least 90 minutes) or by the ultra-sensitive long axial field-of-view (FOV) Explorer scanner. The developed product would be deep learning networks that can convert any clinical PET images data from all major vendors (Siemens, GE, United Imaging Healthcare (UIH)) into virtual-high-count ultra-low noise images. Since Yale, MGH, and UC Davis are all serviced by Visage Imaging, the developed deep learning technique can be seamlessly translated into Visage PACS research/clinical servers for validation and evaluation, beta testing and user feedback, and ultimate translation and regulatory filings. In Aim 1, we will develop deep learning models for virtual-high-count PET generation. In Aim 2, we will evaluate and deploy the models into Visage research PACS server and evaluate virtual-high-count PET in clinical environments. In Aim 3, we will integrate the developed virtual-high-count PET deep learning models into the clinical production PACS server and generate regulatory documents and supporting data for FDA 510(k).

抽象的 高图像噪声降低了PET的诊断功效和定量准确性，因为噪声很容易 导致高估SUV并在诊断中导致假阳性病变检测。高图像噪音也 降低了临床决策的信心，从而导致其他不必要的随访 成像方式和侵入性程序。基于深度学习的降噪表明了宠物的承诺 成像。但是，现有方法仅着眼于转换低计数图像（例如，通过低 - 获得 注射剂量或较短的扫描时间）至典型的临床扫描中标准计数图像。但是，对于两个低 - 计数和绝大多数常规获取的临床宠物图像正常剂量和扫描时间，有 没有方法可以将此类临床图像转换为高计数图像以进一步降低图像噪声，主要是由于 挑战以培训标签获得高计宠物图像。现实世界中的另一个挑战 应用程序将训练数据与测试数据匹配，以噪声水平，噪声结构， 重建参数，扫描仪模型等。在多中心多中心 扫描仪设置。在这个学术工业合作伙伴R01项目中，我们在 VISAGE IMAGING，一家领先的PACS公司和三个领先的学术中心（耶鲁大学，MGH，加州大学戴维斯分校） 开发，评估，部署和翻译强大的深度学习方法来生成虚拟高计宠物 通过考虑每个患者中每个器官的噪声水平，以高度个性化的方式图像 以及相关的非成像患者信息。学术网站可以访问大量高级 计算通过长时间动态扫描（至少90分钟）或通过超敏感的数据获取的数据 长轴向视野（FOV）Explorer扫描仪。开发的产品将是深度学习网络 可以转换所有主要供应商（西门子，GE，United Imaging Healthcare）的任何临床PET图像数据 （UIH））中的虚拟高点超低噪声图像。由于耶鲁大学，MGH和加州大学戴维斯分校都通过VISAGE服务 成像，开发的深度学习技术可以无缝地翻译成Visage PACS 用于验证和评估，Beta测试和用户反馈以及最终翻译的研究/临床服务器 和监管文件。在AIM 1中，我们将开发用于虚拟高量宠物生成的深度学习模型。在 AIM 2，我们将评估并将模型部署到VISAGE Research PACS服务器并评估虚拟最高计数 在临床环境中的宠物。在AIM 3中，我们将整合发达的虚拟高计宠物深度学习 模型进入临床生产PACS服务器并生成监管文档并支持数据 FDA 510（k）。