Retrospective Validation and Clinical Implementation of Automated Contouring of Organs at Risk in the Head and Neck: A Step Toward Automated Radiation Treatment Planning for Low- and Middle-Income Countries.
Retrospective Validation and Clinical Implementation of Automated Contouring of Organs at Risk in the Head and Neck: A Step Toward Automated Radiation Treatment Planning for Low- and Middle-Income Countries.
复制标题
DOI：
10.1200/jgo.18.00055
复制
发表时间：
2018-07
影响因子：
--
通讯作者：
Yang J
中科院分区：
文献类型：
--
作者：
McCarroll RE;Beadle BM;Balter PA;Burger H;Cardenas CE;Dalvie S;Followill DS;Kisling KD;Mejia M;Naidoo K;Nelson CL;Peterson CB;Vorster K;Wetter J;Zhang L;Court LE;Yang J
我们使用多寰椎可变形图像配准算法评估了头颈癌 (HNC) 患者正常结构的自动轮廓绘制，以更好地为低收入和中等收入国家提供全自动放射治疗计划解决方案，提供定量分析并确定全球范围内的可接受性。由专门的 HNC 放射肿瘤学家对 128 名 HNC 患者的八种正常结构（大脑、脑干、耳蜗、眼睛、肺、下颌骨、腮腺和脊髓）的自动轮廓进行回顾性评分。来自国际合作机构的另外五名放射肿瘤学家对 10 名患者子集的轮廓进行了评估，并评估了医师间的变异性。使用 Dice 相似系数、平均表面距离和 Hausdorff 距离评估自动轮廓与独立医生绘制结构的定量一致性。随后，自动轮廓绘制被应用于临床，并已用于 166 名患者，并且使用相同的指标将轮廓与医生编辑的自动轮廓进行定量比较。回顾起来，87% 的正常结构轮廓被评为可接受用于基于剂量体积直方图的规划，无需编辑。临床实施后，50% 的轮廓未经过编辑以用于治疗计划。与腮腺 (0.92 ± 0.10)、脑干 (0.95 ± 0.09) 和脊髓 (0.92 ± 0.12) 的医生编辑的自动轮廓相比，自动轮廓的平均（±标准差）骰子相似系数表明仅进行了较小的编辑。所有结构的平均表面距离和豪斯多夫距离分别小于 0.15 毫米和 1.8 毫米。根据多个国际中心的回顾性评级和临床整合判断，正常结构的自动轮廓绘制可生成可靠的轮廓，仅需要最少的编辑。自动轮廓对于治疗计划来说是可以接受的，无需进行或最多进行少量编辑，这表明自动轮廓对于临床使用以及自动放射治疗计划算法的持续开发是可行的。
We assessed automated contouring of normal structures for patients with head-and-neck cancer (HNC) using a multiatlas deformable-image-registration algorithm to better provide a fully automated radiation treatment planning solution for low- and middle-income countries, provide quantitative analysis, and determine acceptability worldwide. Autocontours of eight normal structures (brain, brainstem, cochleae, eyes, lungs, mandible, parotid glands, and spinal cord) from 128 patients with HNC were retrospectively scored by a dedicated HNC radiation oncologist. Contours from a 10-patient subset were evaluated by five additional radiation oncologists from international partner institutions, and interphysician variability was assessed. Quantitative agreement of autocontours with independently physician-drawn structures was assessed using the Dice similarity coefficient and mean surface and Hausdorff distances. Automated contouring was then implemented clinically and has been used for 166 patients, and contours were quantitatively compared with the physician-edited autocontours using the same metrics. Retrospectively, 87% of normal structure contours were rated as acceptable for use in dose-volume-histogram–based planning without edit. Upon clinical implementation, 50% of contours were not edited for use in treatment planning. The mean (± standard deviation) Dice similarity coefficient of autocontours compared with physician-edited autocontours for parotid glands (0.92 ± 0.10), brainstem (0.95 ± 0.09), and spinal cord (0.92 ± 0.12) indicate that only minor edits were performed. The average mean surface and Hausdorff distances for all structures were less than 0.15 mm and 1.8 mm, respectively. Automated contouring of normal structures generates reliable contours that require only minimal editing, as judged by retrospective ratings from multiple international centers and clinical integration. Autocontours are acceptable for treatment planning with no or, at most, minor edits, suggesting that automated contouring is feasible for clinical use and in the ongoing development of automated radiation treatment planning algorithms.