Automatic quality assessment of rigid registration of ultrasound images for radiotherapy

放射治疗超声图像刚性配准的自动质量评估

• 批准号: 488025-2015
• 负责人: Rivaz, Hassan
• 金额: $ 1.82万
• 依托单位: Concordia University
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2015
• 资助国家: 加拿大
• 起止时间: 2015-01-01 至 2016-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=586137
• 关键词: Automatic; quality; assessment; rigid; registration

The goal of radiotherapy (RT) is to maximize radiation dose to the tumour while minimizing dose to healthy tissues. The emergence of stereotactic body radiotherapy (SBRT) promises to shorten treatment time from a few weeks to a few days, which is especially significant in remote and rural areas where long commutes are required to attend an RT session. Many organs, such as prostate, liver, lungs and breast, can move substantially during RT due to factors such as breathing, digestion, bladder filling, etc. Therefore, accurate continuous localization of the target is of particular importance in SBRT. Ultrasound is a safe and real-time imaging modality and is commonly used for imaging of soft tissue. It is also significantly less expensive than magnetic resonance (MR) and computed tomography (CT). Tissue tracking with ultrasound can be performed with what is known as image registration in the medical imaging community, which is an active field of research. The tracking information can be used to compensate for motion during treatment. Since the tracking is done automatically, it is important to develop quality assessment (QA) techniques to reduce the chance of missing the target. We propose to develop novel image processing and machine learning techniques that will automatically perform QA of the registration outcome, so that the RT can be temporarily suspended until high quality tracking is restored. Elekta is a world leader in development of advanced RT solutions with strong research and development presence in Canada. The tools developed here may eventually enable more efficient RT methods that significantly shorten the treatment time from daily visits to RT centers from 3-5 weeks to just few days. This is particularly important for individuals who reside in remote areas of Canada, where patients have to be relocated for a long time to receive RT treatment. Furthermore, ultrasound is significantly less expensive and faster compared to MR and CT, and a reliable ultrasound-based tracking system leads to substantial saving for our healthcare system.

放疗（RT）的目的是最大化肿瘤的辐射剂量，同时最大程度地减少剂量 组织。立体定向身体放疗（SBRT）的出现有望从一个缩短治疗时间 几周到几天，这在长途通勤的偏远和农村地区尤其重要 需要参加RT会议。许多器官，例如前列腺，肝脏，肺部和乳房，都可以大大移动 由于呼吸，消化，膀胱填充等因素，在RT期间。因此，准确的连续 目标的定位在SBRT中特别重要。超声是一种安全且实时的成像 模态，通常用于成像软组织。它也比磁性便宜得多 共振（MR）和计算机断层扫描（CT）。可以使用超声跟踪进行超声跟踪 被称为医学成像社区中的图像注册，这是一个积极的研究领域。这 跟踪信息可用于补偿治疗过程中的运动。由于跟踪完成了 自动开发质量评估（QA）技术以减少失踪的机会很重要 目标。我们建议开发新颖的图像处理和机器学习技术 自动执行注册结果的质量检查，以便将RT暂时悬挂直至高 质量跟踪已恢复。 Elekta是具有强大的高级RT解决方案发展的世界领导者 加拿大的研发存在。这里开发的工具最终可能会提高效率 从每天访问到RT中心从3-5周到仅缩短治疗时间的RT方法 几天。这对于居住在加拿大偏远地区的个人（患者）尤其重要 必须长时间搬迁才能接受RT治疗。此外，超声显着少得多 与MR和CT相比，昂贵且更快，基于可靠的超声跟踪系统导致 为我们的医疗保健系统节省大量。