Generalized inverse optimization with application to radiation therapy

广义逆优化在放射治疗中的应用

• 批准号: RGPIN-2015-05180
• 负责人: Chan, Timothy
• 金额: $ 2.04万
• 依托单位: University of Toronto
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=636811
• 关键词: Generalized; inverse; optimization; application; radiation

This research program will develop new tools in the field of optimization and demonstrate the application of those tools to pioneer a new paradigm in radiation therapy treatment planning. Radiation therapy is one of the primary ways to treat cancer. The current treatment planning process is complex and inefficient, typically relying on manual trial-and-error effort to produce a treatment plan. The challenge stems from the difficulty in determining appropriate parameters in the planning software that will result in an acceptable treatment.In this research program, we will develop new inverse optimization methods that can analyze historical treatments and reverse-engineer appropriate treatment parameters. Then, machine learning methods will be developed to predict these treatment parameters from an individual’s anatomy. Our new knowledge-based treatment planning framework, built on a foundation of optimization and machine learning, will be able to simultaneously improve standardization of the treatment planning process without sacrificing personalization of the treatments.

这项研究计划将在优化领域开发新的工具，并展示这些工具的应用，以开创放射治疗治疗计划的新范式。放射治疗是治疗癌症的主要方法之一。目前的治疗计划过程复杂且效率低下，通常依靠人工反复试验来制定治疗计划。挑战来自于在计划软件中确定适当的参数以产生可接受的治疗的困难。在这个研究计划中，我们将开发新的逆优化方法，它可以分析历史治疗并反向工程适当的治疗参数。然后，将开发机器学习方法，根据个人的解剖预测这些治疗参数。我们新的基于知识的治疗计划框架建立在优化和机器学习的基础上，将能够同时提高治疗计划过程的标准化，而不会牺牲治疗的个性化。