Automatic Organ Segmentation Tool for Radiation Treatment Planning of Cancers

用于癌症放射治疗计划的自动器官分割工具

• 批准号: 10081752
• 负责人: Xue Feng
• 金额: $ 100万
• 依托单位: CARINA MEDICAL, LLC
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-05-01 至 2022-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10081752
• 关键词: 3-Dimensional; Address; Adopted; Adoption; Algorithms; American; Area; Artificial Intelligence; Atlases; Attention; Body Regions; Body part; Cancer Patient; Chest; Clinical; Clinical Research; Computer Vision Systems; Computer software; Consumption; Data; Development; Digital Imaging and Communications in Medicine; Dose; Early Diagnosis; Environment; Healthcare; Heterogeneity; Hour; Human; Image; Intraobserver Variability; Label; Malignant Neoplasms; Manuals; Measures; Medical; Medicine; Methods; Modality; Modeling; Online Systems; Organ; Outcome; Patient-Focused Outcomes; Performance; Phase; Process; Protocols documentation; Radiation Dose Unit; Radiation therapy; Risk; Scanning; Site; Slice; Survival Rate; Techniques; Testing; Time; Toxic effect; Treatment Cost; Update; X-Ray Computed Tomography; algorithm development; automated segmentation; base; cancer radiation therapy; cancer therapy; clinical heterogeneity; cloud based; commercialization; convolutional neural network; cost; deep learning; deep learning algorithm; dosimetry; healthcare community; imaging modality; improved; innovation; learning strategy; life-long learning; millimeter; novel; phase 1 study; prototype; satisfaction; segmentation algorithm; simulation; software development; success; tool; treatment planning; usability; user-friendly; validation studies

ABSTRACT As early detection and better treatment have increased cancer patient survival rates, the importance of protecting normal organs during radiation treatment is drawing more attention, which is critical in reducing long term toxicity of cancers. To avoid excessively high radiation doses to organs-at-risk (OARs), OARs need to be correctly segmented from simulation computed tomography (CT) scans during radiation treatment planning to get an accurate dose distribution. Despite tremendous effort in developing semi- or fully-automatic segmentation solutions, current automated segmentation software, mostly using the atlas-based methods, has not yet reached the level of accuracy and robustness required for clinical usage. Therefore, in current practice, significant manual efforts are still required in the OAR segmentation process. Manual contouring suffers from inter- and intra-observer variability, as well as institutional variability where different sites adopt distinct contouring atlases and labeling criteria, thus leading to inaccuracy and variability in OAR segmentation. When OARs are very close to the treatment target, segmentation errors as small as a few millimeters can have a statistically significant impact on dosimetry distribution and outcome. In addition, it is also costly and time consuming as it can take 1-2 hours of a clinicians’ time to segment major thoracic organs due to the large number of axial slices required. In summary, an accurate and fast process for segmenting OARs in treatment planning using CT scans is needed for improving patient outcomes and reducing the cost of radiation therapy of cancers. In recent years, the rapid development of deep learning methods has revolutionized many computer-vision areas and the adoption of deep learning in medical applications has shown great success. Based on a deep-learning-based algorithm we developed that achieved better-than-human performance and ranked 1st in 2017 American Association of Physicist in Medicine Thoracic Auto-segmentation Challenge, an automatic OAR segmentation product will be developed in this project with the three aims: 1) further improve the performance and robustness of OAR segmentation algorithms, focusing on addressing the heterogeneity issue of different clinical environments; 2) further enrich the functionalities and enhance usability of the cloud- based software product; and 3) perform clinical validation study on the algorithm performance and software usability at collaborating sites. With this product, the segmentation accuracy can be improved, leading to more robust treatment plans in protecting normal organs and improved long term patient outcome. The time and cost of radiation treatment planning can be greatly reduced, contributing to a more affordable cancer treatment and reduced healthcare burden.

摘要 由于早期发现和更好的治疗提高了癌症患者的存活率， 在放射治疗中保护正常器官引起了更多的关注，这是减少长时间的关键 癌症的长期毒性。为了避免对危险器官(桨)的过高辐射剂量，桨需要 在放射治疗计划期间从模拟计算机断层扫描中正确分割到 得到准确的剂量分布。尽管在开发半自动或全自动汽车方面付出了巨大的努力 分割解决方案，当前的自动分割软件，主要使用基于图谱的方法，具有 尚未达到临床使用所需的准确性和稳健性水平。因此，在目前的实践中， 在OAR分割过程中，仍然需要大量的人工工作。手工绘制轮廓会受到 观察员之间和内部的可变性，以及不同地点采用不同的 等高线地图集和标注标准，从而导致桨叶分割的不准确性和可变性。什么时候 桨离治疗目标很近，小到几毫米的分割误差都可以有 对剂量学分布和结果有统计学意义的影响。此外，这也是昂贵的和时间 消耗，因为临床医生可能需要1-2小时的时间来分割主要的胸部器官，因为 所需的轴向切片数。总之，在治疗过程中，一种准确而快速的划桨过程 需要计划使用CT扫描来改善患者结果并降低放射治疗的成本 癌症。近年来，深度学习方法的快速发展使许多人发生了革命性的变化 在计算机视觉领域，深度学习在医学中的应用已经显示出巨大的成功。 基于我们开发的基于深度学习的算法，该算法取得了比人类更好的性能 在2017年美国物理学家协会医学自动分割挑战赛中排名第一 本项目将开发自动划桨产品，主要有三个目标：1)进一步完善 OAR分割算法的性能和稳健性，侧重于解决异构性 不同临床环境的问题；2)进一步丰富云的功能，增强云的可用性- 3)对算法性能和软件进行了临床验证研究 协作站点的可用性。有了这款产品，可以提高分割精度，导致更多 在保护正常器官和改善长期患者预后方面制定强有力的治疗计划。时间和成本 的放射治疗计划可以大大减少，有助于更负担得起的癌症治疗和 减轻了医疗负担。