Reducing cardiac toxicity with deep learning and MRI-guided radiation therapy

通过深度学习和 MRI 引导放射治疗减少心脏毒性

• 批准号: 10473755
• 负责人: Carri Kaye Glide-Hurst
• 金额: $ 53.13万
• 依托单位: UNIVERSITY OF WISCONSIN-MADISON
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-08-23 至 2026-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10473755
• 关键词: Acute; Acute Coronary Event; Aftercare; Angiography; Atlases; Attention; Benchmarking; Biological Markers; Blood; Breast Lymphoma; Cancer Intervention; Cancer Patient; Cancer Survivor; Cardiac; Cardiac Volume; Cardiology; Cardiotoxicity; Chest; Clinical; Clinical Trials; Complex; Congestive Heart Failure; Coronary; Coronary Arteriosclerosis; Coronary artery; Coupled; Coupling; Data; Dose; Echocardiography; Emerging Technologies; Esophageal Lymphoma; Evaluation; Exhibits; Future; Generations; Goals; Heart; Heart Atrium; Hour; Image; Incidence; Lead; Life Expectancy; Linear Accelerator Radiotherapy Systems; Link; Longterm Follow-up; Lung; Lymphoma; Magnetic Resonance Imaging; Malignant Childhood Neoplasm; Malignant Neoplasms; Malignant neoplasm of esophagus; Malignant neoplasm of lung; Malignant neoplasm of thorax; Manuals; Meta-Analysis; Methods; Modality; Modeling; Modification; Morbidity - disease rate; Motion; Non-Small-Cell Lung Carcinoma; Oncology; Organ; Outcome; Patients; Pericardial effusion; Public Health; Quality of life; Radiation; Radiation Dose Unit; Radiation Therapy Oncology Group; Radiation Tolerance; Radiation therapy; Radiology Specialty; Randomized Clinical Trials; Research; Risk; Roentgen Rays; Safety; Scanning; Techniques; Technology; Therapeutic; Translations; Treatment-Related Cancer; Uncertainty; United States National Institutes of Health; Validation; X-Ray Computed Tomography; base; cancer complication; cancer therapy; cardiac magnetic resonance imaging; clinical efficacy; clinical practice; comorbidity; computer science; cone-beam computed tomography; deep learning; experience; generative adversarial network; heart function; image guided; image guided radiation therapy; image processing; imaging approach; improved; improved outcome; innovation; malignant breast neoplasm; minimally invasive; multi-task learning; multidisciplinary; multimodality; new technology; novel; pericardial sac; prospective; radiation delivery; respiratory; response; side effect; simulation; soft tissue; standard of care; treatment planning; tumor; volunteer

Cardiac toxicity is a devastating complication of cancer treatment and occurs during, shortly after, or even many years after treatment. Long-term follow up of patients undergoing thoracic radiation, such as lymphoma, lung, and esophageal cancers, has shown that in particular, radiation therapy (RT) can lead to major radiation-induced cardiac toxicities like congestive heart failure and coronary artery disease. Typically, the standard of care for cardiac dose assessment involves simple heart dose/volume metrics. However, mounting evidence suggests that cardiac substructures contained within the heart are highly radiosensitive and dose to substructures are more strongly associated with overall survival than assessing whole-heart dose/volume metrics. Nevertheless, precise characterization of cardiac substructure dose in routine clinical practice is currently limited because substructures are not visible on CT simulation scans used for RT planning, cardiac MRI are not widely available for cancer patients, and manual delineation is cumbersome, taking 6-10 hours per case. Further, precise localization is complicated by both cardiac and respiratory motion. Our long-term goal is to develop and validate clinically viable novel technologies to localize cardiac substructures for novel cancer therapies and interventions. The rationale for the proposed research is that by developing a robust and efficient clinical framework for cardiac substructure dose assessment, more effective cardiac sparing strategies can be achieved. Our expertise in deep learning coupled with experience in MR-guided RT has laid the groundwork for this paradigm-changing proposal with the long-term goal of optimal cardiac sparing to ultimately reduce radiation- induced cardiac toxicity. To attain the overall objectives, we propose the following specific aims: (i) develop high quality, efficient cardiac substructure segmentation and accurate synthetic CT generation via deep learning, (ii) quantify respiratory and cardiac-induced cardiac substructure motion using a novel 5D-MRI approach and inter-fraction uncertainties to derive margins and planning strategies for robust cardiac sparing, and (iii) evaluate the clinical efficacy of these emerging technologies in a randomized clinical trial for lung cancer evaluating longitudinal changes in cardiac function from MRI, quality of life, echocardiogram, and blood biomarkers between MR-guided adaptive radiation therapy with sparing and standard x-ray based treatment with whole-heart dose metrics. This multi-disciplinary (oncology, cardiology, radiology, and computer science) proposal integrates state of the art technologies while challenging the standard of care of using whole-heart dose evaluations. The research proposed is innovative as it challenges the current, oversimplified classic model of whole-heart dose estimates via several cutting-edge techniques. The research is significant because of its widespread application in other thoracic cancers including lung, breast, lymphoma, esophageal, and future pediatric cancer trials. Ultimately, the overall positive impact is that our pipeline will yield highly effective cardiac substructure sparing to reduce radiation-related cardiac toxicities and maximize therapeutic gains.

心脏毒性是癌症治疗的毁灭性并发症，发生在不久之后，甚至许多 治疗后几年。长期随访接受胸腔辐射的患者，例如淋巴瘤，肺， 食管癌和食管癌特别表明，辐射疗法（RT）可能导致重大辐射诱导 心脏毒性如充血性心力衰竭和冠状动脉疾病。通常，护理标准 心脏剂量评估涉及简单的心脏剂量/体积指标。但是，越来越多的证据表明 心脏内包含的心脏子结构高度放射敏感，并剂量为子结构 与评估全心剂量/体积指标相比，与整体生存更加密切相关。 然而，目前正在常规的临床实践中心脏子结构剂量的精确表征 有限，因为在用于RT规划的CT模拟扫描中不可见子结构，心脏MRI是 癌症患者不广泛使用，手动描述很麻烦，每例案例需要6-10个小时。 此外，心脏和呼吸运动都使精确的定位变得复杂。我们的长期目标是 开发和验证临床上可行的新技术，以定位新型癌症的心脏子结构 治疗和干预措施。拟议研究的理由是，通过开发强大而有效的效率 心脏子结构剂量评估的临床框架，更有效的心脏支撑策略可以是 成就了。我们在深度学习方面的专业知识以及MR指导RT的经验为 这项改变范式的提案具有最佳心脏保留的长期目标，以最终减少辐射 - 诱导心脏毒性。为了实现总体目标，我们提出以下具体目标：（i）发展 高质量，有效的心脏子结构细分和通过深度学习的准确合成CT生成 （ii）使用新型的5D-MRI方法和 划分的不确定性，以得出鲁棒性心脏保留的边缘和计划策略，并且（iii）评估 这些新兴技术的临床功效在一项评估肺癌的随机临床试验中 MRI，生活质量，超声心动图和血液生物标志物的心脏功能的纵向变化 MR引导的自适应放射疗法，并以全心脏剂量进行节省和标准的基于X射线的治疗 指标。这个多学科（肿瘤学，心脏病学，放射学和计算机科学）提案整合了状态 艺术技术的同时，在挑战使用全心剂量评估的护理标准的同时。这 提出的研究具有创新性，因为它挑战了当前的全心剂量经典模型 通过几种尖端技术进行估计。这项研究很重要，因为其广泛应用 在其他胸腔癌中，包括肺，乳腺癌，淋巴瘤，食管和未来的儿科癌症试验。 最终，总体积极的影响是我们的管道将产生高效的心脏子结构 减少与辐射相关的心脏毒性并最大程度地提高治疗性。