Terparia Samsara, Mir Romaana, Tsang Yat, Clark Catharine H, Patel Rushil
Radiotherapy Physics, Mount Vernon Cancer Centre, Northwood, UK.
NIHR Radiotherapy Trials Quality Assurance Group, Mount Vernon Cancer Centre, Northwood, UK.
Phys Imaging Radiat Oncol. 2020 Dec 1;16:149-155. doi: 10.1016/j.phro.2020.10.008. eCollection 2020 Oct.
Peer-review of Target Volume (TV) and Organ at Risk (OAR) contours in radiotherapy planning are typically conducted visually; this can be time consuming and subject to interobserver variation. This study investigated automatic evaluation of contouring using conformity indices and supervised machine learning.
A total of 393 contours from 253 Stereotactic Ablative Body Radiotherapy (SABR) benchmark cases (adrenal gland, liver, pelvic lymph node and spine), delineated by 132 clinicians from 25 centres, were visually evaluated for conformity against gold standard contours. Contours were scored as "pass" or "fail" on visual peer review and six Conformity Indices (CIs) were applied. CI values were mapped to pass/fail scores for each contour and used to train supervised machine learning models. A 5-fold cross validation method was employed to determine the predictive accuracies of each model.
The stomach structure produced models with the highest predictive accuracy overall (96% using Support Vector Machine and Ensemble models), whilst the liver GTV produced models with the lowest predictive accuracy (76% using Logistic Regression). Predictive accuracies across all models ranged from 68-96% (68-87% for TV and 71-96% for OARs).
Although a final visual review by an experienced clinician is still required, the automatic contour evaluation method could reduce the time for benchmark case reviews by identifying gross contouring errors. This method could be successfully implemented to support departmental training and the continuous assessment of outlining for clinical staff in the peer-review process, to reduce interobserver variability in contouring and improve interpretation of radiological anatomy.
放射治疗计划中靶区（TV）和危及器官（OAR）轮廓的同行评审通常采用视觉方式进行；这可能耗时且存在观察者间差异。本研究调查了使用适形指数和监督式机器学习对轮廓进行自动评估。
来自25个中心的132名临床医生勾勒出了253例立体定向体部放射治疗（SABR）基准病例（肾上腺、肝脏、盆腔淋巴结和脊柱）的总共393个轮廓，对这些轮廓与金标准轮廓的符合度进行了视觉评估。在视觉同行评审中，轮廓被评为“通过”或“未通过”，并应用了六个适形指数（CI）。将CI值映射到每个轮廓的通过/未通过分数，并用于训练监督式机器学习模型。采用五折交叉验证方法来确定每个模型的预测准确性。
总体而言，胃部结构产生的模型预测准确性最高（支持向量机和集成模型为96%），而肝脏大体肿瘤体积（GTV）产生的模型预测准确性最低（逻辑回归为76%）。所有模型的预测准确性范围为68 - 96%（靶区为68 - 87%，危及器官为71 - 96%）。
尽管仍需要经验丰富的临床医生进行最终的视觉审查，但自动轮廓评估方法可以通过识别明显的轮廓勾画错误来减少基准病例审查的时间。该方法可以成功实施，以支持部门培训和在同行评审过程中对临床工作人员轮廓勾画的持续评估，减少轮廓勾画中的观察者间变异性，并改善对放射解剖结构的解读。
