Autosegmentation for head and neck Radiotherapy

描述（由申请人提供）：我们提议开发、实施和测试颅内和头颈部癌症患者治疗计划图像中结构自动分割所需的方法。对于先进的放射治疗技术，需要描绘用于脑部放射治疗的关键结构，以确定来自所提议的治疗的剂量是否会损害结构的功能。在放射肿瘤治疗计划过程中采用自动分割计算机模块具有显著提高效率、成本效益以及最终提高接受放射治疗的患者的临床结果的潜力。这样的系统将解决与在治疗计划图像的连续切片上手动描绘正常解剖结构的当前实践相关联的艰巨的劳动和时间密集型挑战。具体而言，我们建议（1）进一步改进、实施和测试我们在本机构开发的用于颅内结构和子结构轮廓勾画的半自动基于图谱的分割算法，以治疗小到中等尺寸的颅内肿瘤患者，（2）开发、实施，并测试基于图谱的分割算法，用于颅内结构和子结构的轮廓绘制，以治疗患有大占位性颅内肿瘤的患者，以及（3）量化在临床环境中由这些方法提供的用户交互时间的减少。

DESCRIPTION (provided by applicant): We propose to develop, implement, and test the methodology required to automate the segmentation of structures in the treatment planning images of patients with intracranial and head- and-neck cancers. Delineating critical structures for radiotherapy of the brain is required for advanced radiotherapy technologies to determine if the dose from the proposed treatment will impair the functionality of the structures. Employing an automatic segmentation computer module in the radiation oncology treatment planning process has the potential to significantly increase the efficiency, cost- effectiveness, and, ultimately, clinical outcome of patients undergoing radiation therapy. Such a system would address the formidable labor- and time-intensive challenges associated with the current practice of manually delineating normal anatomical structures on the serial slices of treatment planning images. Specifically, we propose to (1) further improve, implement, and test the semi-automatic atlas-based segmentation algorithms we have developed at our institution for the contouring of intracranial structures and substructures for the treatment of patients with small to moderate size intracranial tumors, (2) to develop, implement, and test atlas-based segmentation algorithms for the contouring of intracranial structures and substructures for the treatment of patients with large space-occupying intracranial tumors, and (3) to quantify the reduction in user-interaction time afforded by these methods in the clinical setting.