Artificial Intelligence Driven Automatic Treatment Planning of Stereotactic Radiosurgery for the Management of Multiple Brain Metastases

项目摘要/摘要 脑转移瘤(BMS)是一种危及生命的疾病，发生在高达40%的癌症患者中。约40%的 BM患者有多个(≥4)骨髓基质(MBMS)。全脑放射治疗(WBRT)长期以来一直是 MBMS患者的护理标准显示出明显的神经认知功能障碍。立体定向 放射外科(SRS)改善了肿瘤控制，减少了对认知功能的负面影响 WBRT。然而，历史上它只为患有&lt；4BMS的患者保留。最近，几项临床试验 报告了强有力的证据支持MBMS患者的SRS。国家综合癌症网络 因此，指导方针不再限制SR的BMS数量。然而，MBMS中较大的黑石数量 患者大大增加了治疗计划的复杂性。传统的人工提前计划 对于MBMS来说，手动确定计划参数变得繁琐且不切实际。现代逆向规划 方法可以通过求解由多个 为各种临床或实际考虑而设计的目标，而这些目标中的优先事项 影响生成的计划质量。医生对特定病人的偏好很难量化，而且 准确地传达给计划者，特别是对于MBMS患者，因为数量、大小和位置不同 BMS的成员。因此，最好的医生偏好计划通常是通过广泛的反复试验优先实现的 调整以及规划者和医生之间的几轮互动。因此，计划时间可以 耗时长达数小时，计划质量可能不是最优的，并且可能会有很大差异，这是由于 医生和规划师的技能和医生与规划师的沟通和合作，导致恶化 临床结果。受到人工智能(AI)最近的巨大进步的启发，尤其是深刻的 强化学习(DRL)和深度逆强化学习(DIRL)在智能决策中的应用 在计算机视觉和机器人技术的基础上，我们提出开发一种人工智能驱动的SRS自动治疗系统 有效管理MBMS的计划系统(Assistant-MBMS)，学习人级智能 来自人类专家的治疗计划。我们设想该系统具有两个深度神经网络：DNN-R，即 充当人工智能医生，预测医生对每个患者的偏好，并充当DNN-P 作为人工智能规划者，调整优先事项，以实现医生满意的计划。我们将追求两个具体的目标 目标。目标1.系统原型开发：我们将收集人类专家规划者的优先级调整行动和 通过基于交错DIRL的奖励函数学习和基于DRL的策略学习来开发DNN-R和DNN-P。 目标2.系统改进和端到端评估：我们将进行前瞻性研究，以改进我们的 系统基于人类专家对生成的人工智能计划的进一步微调操作，然后评估 我们的系统的可行性、有效性和效率。完成后，援助-MBMS将提供高质量和 有效的SRS治疗计划，使MBMS患者受益，特别是资源有限地区的患者。

Project Summary/Abstract Brain metastases (BMs) are a life-threatening disease, occurring in up to 40% of cancer patients. About 40% of BM patients have multiple (≥4) BMs (mBMs). Whole brain radiotherapy (WBRT), which has long been the standard of care for mBMs patients, has shown pronounced impairment of neurocognitive functions. Stereotactic radiosurgery (SRS) has improved tumor control and reduced negative effect on cognition function, compared to WBRT. However, it has been historically reserved only for patients with <4 BMs. Recently, several clinical trials reported strong evidence to support SRS for mBMs patients. National Comprehensive Cancer Network guidelines hence no longer restrict the number of BMs for SRS. However, the larger BM number in mBMs patients substantially increases the complexity of treatment planning. Conventional manual forward planning to manually determine plan parameters becomes cumbersome and impractical for mBMs. Modern inverse planning methods can determine plan parameters by solving an optimization problem that is composed of multiple objectives designed for various clinical or practical considerations, while the priorities among these objectives affect the resulting plan quality. The physician’s preferences for a particular patient can hardly be quantified and precisely conveyed to the planner, especially for mBMs patients due to the varying number, size, and locations of BMs. Hence, the best physician-preferred plan is often achieved through extensive trial-and-error priority tuning and several rounds of interactions between the planner and physician. Consequently, planning time can take up to hours, and plan quality may be suboptimal and can vary significantly, due to the varying levels of physician and planner’s skills and physician-planner communication and cooperation, leading to deteriorated clinical outcome. Inspired by the recent colossal advancements of artificial intelligence (AI), particularly deep reinforcement learning (DRL) and deep inverse reinforcement learning (DIRL), on intelligent decision-making in computer visions and robotics, we propose to develop an artificial intelligence driven automatic SRS treatment planning system for effective management of mBMs (Aid-mBMs), learning a human-level intelligence on treatment planning from human experts. We envision the system to have two deep neural networks: DNN-R that acts as an AI-physician to predict the physician’s preferences for each individual patient, and DNN-P that acts as an AI-planner to tune the priorities to achieve a plan of physician’s satisfaction. We will pursue two specific aims. Aim 1. System prototype development: We will collect human expert planners’ priority-tuning actions and develop DNN-R and DNN-P via interleaved DIRL-based reward function learning and DRL-based policy learning. Aim 2. System improvement and end-to-end evaluation: We will perform a prospective study to improve our system based on human expert’s further fine-tuning actions on the generated AI plans, and then evaluate the feasibility, effectiveness, and efficiency of our system. Upon completion, Aid-mBMs will provide high-quality and efficient SRS treatment planning to benefit mBMs patients, especially those in resource-limited regions.