Semiautomatic segmentation of glioblastoma for radiotherapy treatment plannin

During the radiation therapy (RT) process, the treatment is planned and simulated with a treatment planning system (TPS). Contouring identifies the Planning Treatment Volume (PTV), that is the physical RT treatment volume. PTV of Glioblastoma (GB) includes, after expansion, Gross Tumor Volume (GTV, the tumor) and Clinical Target Volume (CTV, tumor plus edema). GlioCAD, a Computer-Assisted Detection software for contouring gliomas in MRI/DTI, was used to delineate GTV. The dataset included the images of 21 patients undergoing RT for GB. For each patient, we co-registered CT-planning images and diagnostic MRI (16 T1-gad, 6 T2 Flair, 13 Flair Fat Sat), which were used for GlioCAD training and validation. CAD outlined the tumor with good accuracy, after ruling out in post-processing some false positives. We identified reliable GTVs, suitable for RT requirements. An evolution of GlioCAD will take into account edema for outlining CTV. The method is promising. Together with a further automatic system for the delineation of organs at risk (OAR) in the brain, the procedure may be helpful for standardization of RT-treatment planning.

在放射治疗（radiation therapy, RT）流程中，临床通过治疗计划系统（treatment planning system, TPS）开展治疗方案的规划与模拟。靶区勾画环节需明确计划靶区（Planning Treatment Volume, PTV），即实际执行放射治疗的物理靶体积。胶质母细胞瘤（Glioblastoma, GB）的PTV经扩野处理后，包含大体肿瘤体积（Gross Tumor Volume, GTV，即肿瘤实体）与临床靶区（Clinical Target Volume, CTV，即肿瘤实体联合瘤周水肿）。本研究使用GlioCAD——一款针对磁共振成像/弥散张量成像（MRI/DTI）中胶质瘤靶区勾画的计算机辅助检测软件——来勾勒GTV。本数据集纳入21例接受GB放射治疗的患者影像资料。针对每位患者，研究人员配准了CT计划图像与诊断磁共振成像（含16例钆增强T1加权像、6例T2液体衰减反转恢复序列图像、13例脂肪抑制液体衰减反转恢复序列图像），并将其用于GlioCAD的训练与验证。经后处理排除部分假阳性结果后，该CAD工具可实现高精度的肿瘤轮廓勾画。本研究确定了符合RT要求的可靠GTV数据。后续GlioCAD的迭代版本将纳入瘤周水肿信息，以实现CTV的自动勾画。该方法展现出良好的应用前景。联合一款可自动勾画脑部危及器官（organs at risk, OAR）的后续自动化系统，本流程可为放射治疗计划的标准化提供有力支撑。