Virtual Biopsy with Tissue-level Accuracy in Glioma

神经胶质瘤中具有组织水平精度的虚拟活检

• 批准号: 10393035
• 负责人: Joseph A Maldjian
• 金额: $ 59.55万
• 依托单位: UT SOUTHWESTERN MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-04-15 至 2026-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10393035
• 关键词: 19q; Algorithms; Applications Grants; Artificial Intelligence; Automation; Biology; Biomedical Engineering; Biopsy; Brain; Brain Neoplasms; Classification; Clinical; Computerized Medical Record; Craniotomy; Data; Data Set; Databases; Digital Imaging and Communications in Medicine; Excision; Glioma; Goals; Human; Hyperacusis; Image; Institution; Knowledge; MGMT gene; Magnetic Resonance Imaging; Manuals; Medical center; Methods; Methylation; Molecular; Molecular Analysis; Morphologic artifacts; Motion; Neurosurgical Procedures; Noise; Operative Surgical Procedures; Patient Care; Patient-Focused Outcomes; Patients; Performance; Predictive Value; Procedures; Process; Prognosis; Prospective cohort; Reporting; Research Project Grants; Resources; Risk; Sample Size; Sensitivity and Specificity; T2 weighted imaging; Testing; The Cancer Genome Atlas; The Cancer Imaging Archive; Time; Tissue Sample; Tissues; Training; Tumor Tissue; United States National Institutes of Health; Validation; Work; base; clinical decision-making; clinical implementation; clinical translation; contrast imaging; cost; deep learning; deep learning algorithm; experience; improved; large datasets; learning classifier; learning strategy; molecular marker; motion sensitivity; mutational status; novel; prospective; response; surgical risk; tool; tumor; virtual biopsy

Project Summary This is a Bioengineering Research Grant (BRG) proposal in response to PAR-19-158 to further develop and validate a non-invasive panel of the most critical glioma molecular markers (IDH, 1p/19q, MGMT) using standard clinical MRI T2-weighted images and deep learning, and extend the performance to tissue-level accuracies. Currently, the only reliable way of obtaining molecular marker status is through direct tissue sampling of the tumor, requiring either a craniotomy and stereotactic biopsy or a large open surgical resection. Noninvasive determination of molecular markers with tissue-level accuracy would be transformational in the management of gliomas, reducing or eliminating the risks and costs associated with a neurosurgical procedure, accelerating the time to definitive treatment, improving patient experience and ultimately patient outcomes and survival time. Artificial intelligence such as deep learning has emerged as a powerful method for classification of imaging data that can exceed human performance. Preliminary work using our novel voxel-wise classification-segmentation approach with the NIH/NCI TCIA glioma database has outperformed any prior noninvasive methods for determination of IDH, 1p/19q, and MGMT methylation, achieving accuracies of 97%, 93%, and 95%, respectively. The approach however, needs to be validated beyond the TCIA and accuracies need to be extended in order to achieve tissue level performance. This will be accomplished by using our top-performing voxel-wise classification framework, leveraging marker-specific targeted sample sizes, and gaining a final boost from deep-learning artifact correction networks. In Aim 1 we will curate a database of over 2000 gliomas including 500 subjects from our institution, 1200 subjects from our external collaborators, and over 300 subjects from the TCIA. We will train our voxel-wise deep learning classifiers to determine molecular status based on clinical T2-weighted MR images with target accuracies of 97%. In Aim 2 we will rigorously evaluate the motion and noise sensitivity of the networks and create an artifact correction network with the goals of 1) recovering accuracies in the setting of large amounts of motion/noise and 2) further boosting accuracy to tissue-level performance even in the absence of visible artifact. In Aim 3 we will deploy a complete end-to-end clinical workflow and evaluate real-world live performance of the AI tool on 300 prospectively acquired brain tumor cases and 300 subjects from our external collaborators. The AI tool will be made available for deployment at other medical centers. The developed framework can also be extended to additional markers in a straightforward fashion. In summary, this BRG proposal will further develop, refine and validate a non-invasive MRI-based method for determining the most critical glioma molecular markers rivaling tissue-level accuracies to significantly reduce and in many cases eliminate the need for stereotactic biopsy.

项目概要 这是响应 PAR-19-158 的生物工程研究补助金 (BRG) 提案，旨在进一步开发和 使用标准验证最关键的神经胶质瘤分子标记（IDH、1p/19q、MGMT）的非侵入性面板 临床 MRI T2 加权图像和深度学习，并将性能扩展到组织级精度。 目前，获得分子标记状态的唯一可靠方法是通过直接组织取样 肿瘤，需要开颅手术和立体定向活检或大的开放手术切除。无创 以组织水平准确度确定分子标记将给疾病管理带来变革 神经胶质瘤，减少或消除与神经外科手术相关的风险和成本，加速 确定治疗的时间，改善患者体验，最终改善患者的治疗结果和生存时间。 深度学习等人工智能已成为图像数据分类的强大方法 可以超越人类的表现。使用我们新颖的体素分类分割的初步工作 NIH/NCI TCIA 神经胶质瘤数据库的方法优于任何先前的非侵入性方法 测定 IDH、1p/19q 和 MGMT 甲基化，准确度达到 97%、93% 和 95%， 分别。然而，该方法需要在 TCIA 之外进行验证，并且需要提高准确性 扩展以达到组织水平的性能。这将通过使用我们性能最佳的 体素分类框架，利用特定于标记的目标样本量，并获得最终的提升 来自深度学习伪影校正网络。 在目标 1 中，我们将建立一个包含 2000 多个神经胶质瘤的数据库，其中包括我们机构的 500 名受试者、1200 名受试者 来自我们的外部合作者以及来自 TCIA 的 300 多个受试者。我们将训练我们的体素深度学习 分类器根据临床 T2 加权 MR 图像确定分子状态，目标精度为 97%。在目标 2 中，我们将严格评估网络的运动和噪声敏感性并创建一个工件 校正网络，其目标是 1）恢复大量运动/噪声设置中的精度和 2）即使在没有可见伪影的情况下，也能进一步提高组织水平性能的准确性。在目标 3 中，我们将 部署完整的端到端临床工作流程并评估 AI 工具在 300 上的实际实时性能 从我们的外部合作者处前瞻性获得脑肿瘤病例和 300 名受试者。人工智能工具将是 可供部署在其他医疗中心。所开发的框架还可以扩展到 以简单的方式添加额外的标记。综上所述，本次BRG提案将进一步发展、完善和完善。 验证一种基于 MRI 的非侵入性方法，用于确定最关键的神经胶质瘤分子标记物 组织水平的准确性可显着减少甚至在许多情况下消除立体定向活检的需要。