Machine learning accelerated on-line adaptive replanning

机器学习加速在线自适应重新规划

• 批准号: 10370345
• 负责人: Eric S Paulson
• 金额: $ 48.05万
• 依托单位: MEDICAL COLLEGE OF WISCONSIN
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-04-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10370345
• 关键词: 3-Dimensional; Accounting; Address; Adoption; Affect; Air; Anatomy; Clinic; Clinical; Collaborations; Dose Fractionation; Effectiveness; Electron Transport; Future; Generations; Goals; Health Care Costs; Image; Industry; Learning; Length; Location; Lung; Machine Learning; Magnetic Resonance Imaging; Malignant neoplasm of pancreas; Maps; Methodology; Methods; Modality; Normal tissue morphology; Organ; Patients; Physiology; Process; Quality of life; Radiation Oncologist; Radiation therapy; Research Personnel; Shapes; Site; Speed; Surface; Techniques; Testing; Texture; Therapeutic; Time; Toxic effect; Variant; automated segmentation; base; base editing; bone; cancer radiation therapy; cone-beam computed tomography; convolutional neural network; electron density; forging; image guided; image guided radiation therapy; imaging modality; improved; industry partner; innovation; large datasets; neural network algorithm; novel; pancreatic cancer patients; prospective; prospective test; quantitative imaging; routine practice; soft tissue; success; targeted treatment; tool; treatment response; tumor

Abstract. The overall goal of this proposal is to develop and test a novel machine learning (ML) accelerated On-Line Adaptive Replanning (MOLAR) solution for magnetic resonance imaging (MRI) guided radiation therapy (RT) (MRgRT). During the multi-fraction RT process, the location, shape and size of tumors and normal organs vary significantly between the fractions. These interfraction variations are among the major factors that can limit the accuracy of RT targeting. The current standard practice of image-guided RT (IGRT), developed to address the interfraction variations based on cone-beam CT (CBCT), can only correct for translational errors, and thus does not fully account for interfraction changes. To address this issue, researchers recently introduced online adaptive replanning (OLAR) that generates a new plan based on the anatomy of the day and delivers the plan for the fraction. Currently, two main obstacles affect the success of OLAR: (1) the anatomy of the day cannot be delineated accurately based on CBCT, and (2) the time required to perform OLAR is long enough to render it impractical. One way to improve the delineation accuracy is to use MRI versus CT. MRI-guided OLAR is currently being introduced into the clinics to substantially improve RT targeting. However, the bottleneck is still the impractical length of time required to segment the anatomy of the day, which can exceed 30 minutes. Furthermore, available synthetic CT (sCT) generation methods are slow or inaccurate for MRI-guided OLAR. There is no method available to quickly and objective determine when OLAR is necessary. To address these issues, we plan to develop novel techniques in the MOLAR solution. We hypothesize that the MRI-based MOLAR solution will fully account for interfraction changes, thereby substantially improving tumor targeting during RT delivery and the effectiveness of RT. Specifically, we aim to (1) develop practical ML-based solutions to quickly determine the necessity of OLAR and to rapidly generate accurate synthetic CTs; (2) develop ML-based techniques to substantially accelerate segmentation for OLAR using a progressive three-step process; and (3) verify clinical practicality and effectiveness of MOLAR by retrospectively and prospectively applying the MOLAR on MRI sets to test its speed and effectiveness in accounting for interfraction variations. We will develop this novel MOLAR solution by forging unique collaborations between clinical physicists, radiation oncologists and industry developers via an established academic-industry partnership. The successful completion of this project will enable clinicians to routinely practice “image-plan-treat”, which is the optimal solution for MRgRT. This new paradigm will fully account for interfraction variations, improve tumor targeting, reduce normal tissue toxicity, and ultimately encourage clinicians to revise the current doses and/or dose fractionations to increase therapeutic gain, enhance patient quality of life, and/or substantially save on healthcare costs. Our proposed strategy represents a drastic departure from current practice. We firmly believe that this strategy is the future of RT delivery.

抽象的。该提案的总体目标是开发和测试一种新的机器学习（ML）加速 用于磁共振成像（MRI）引导放射的在线自适应重新规划（MOLAR）解决方案 治疗（RT）（MRgRT）。在多分割RT过程中，肿瘤的位置、形状和大小以及 正常器官在级分之间变化显著。这些分数间的变化是其中的主要 这些因素可能限制RT靶向的准确性。当前的图像引导RT（IGRT）标准实践， 基于锥束CT（CBCT）开发的用于解决干涉变化的方法只能校正 平移误差，因此不能完全解释分数间的变化。为了解决这个问题， 研究人员最近推出了在线自适应重新规划（OLAR），它可以根据 一天的解剖和交付部分的计划。目前，有两个主要障碍影响到 OLAR：（1）基于CBCT无法准确描绘当天的解剖结构，（2）所需时间 执行OLAR的时间足够长，使其不切实际。提高描绘精度的一种方法是使用 MRI对比CT。MRI引导的OLAR目前正在引入诊所，以大幅改善RT 面向.然而，瓶颈仍然是分割解剖结构所需的不切实际的时间长度。 一天，可以超过30分钟。此外，可用的合成CT（sCT）生成方法是缓慢的或难以实现的。 对于MRI引导的OLAR不准确。没有方法可以快速客观地确定何时发生OLAR 是必要的.为了解决这些问题，我们计划在MOLAR解决方案中开发新技术。我们 假设基于MRI的MOLAR解决方案将充分考虑级分间变化，从而 实质上改善RT递送期间的肿瘤靶向和RT的有效性。具体而言，我们的目标是 (1)开发实用的基于ML的解决方案，以快速确定OLAR的必要性，并快速生成 准确的合成CT;（2）开发基于ML的技术，以大大加速OLAR的分割 采用渐进式三步法;（3）通过以下方法验证MOLAR的临床实用性和有效性： 回顾性和前瞻性地在MRI设备上应用MOLAR，以测试其在以下方面的速度和有效性： 考虑到馏分间的变化。我们将通过锻造独特的 临床物理学家、放射肿瘤学家和行业开发人员之间的合作， 学术界和工业界的合作。该项目的成功完成将使临床医生能够定期 实践"图像-计划-治疗"，这是MRgRT的最佳解决方案。这一新模式将充分说明 级分间变异，改善肿瘤靶向，降低正常组织毒性，并最终促进 临床医生修改当前剂量和/或剂量分次，以增加治疗增益，增强患者 生活质量，和/或大大节省医疗费用。我们提出的战略是一个激烈的 与现行做法不同。我们坚信，这一战略是RT交付的未来。