Wahid Kareem A, Sahin Onur, Kundu Suprateek, Lin Diana, Alanis Anthony, Tehami Salik, Kamel Serageldin, Duke Simon, Sherer Michael V, Rasmussen Mathis, Korreman Stine, Fuentes David, Cislo Michael, Nelms Benjamin E, Christodouleas John P, Murphy James D, Mohamed Abdallah S R, He Renjie, Naser Mohammed A, Gillespie Erin F, Fuller Clifton D
Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX.
Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX.
JCO Clin Cancer Inform. 2024 Jun;8:e2300174. doi: 10.1200/CCI.23.00174.
The quality of radiotherapy auto-segmentation training data, primarily derived from clinician observers, is of utmost importance. However, the factors influencing the quality of clinician-derived segmentations are poorly understood; our study aims to quantify these factors.
Organ at risk (OAR) and tumor-related segmentations provided by radiation oncologists from the Contouring Collaborative for Consensus in Radiation Oncology data set were used. Segmentations were derived from five disease sites: breast, sarcoma, head and neck (H&N), gynecologic (GYN), and GI. Segmentation quality was determined on a structure-by-structure basis by comparing the observer segmentations with an expert-derived consensus, which served as a reference standard benchmark. The Dice similarity coefficient (DSC) was primarily used as a metric for the comparisons. DSC was stratified into binary groups on the basis of structure-specific expert-derived interobserver variability (IOV) cutoffs. Generalized linear mixed-effects models using Bayesian estimation were used to investigate the association between demographic variables and the binarized DSC for each disease site. Variables with a highest density interval excluding zero were considered to substantially affect the outcome measure.
Five hundred seventy-four, 110, 452, 112, and 48 segmentations were used for the breast, sarcoma, H&N, GYN, and GI cases, respectively. The median percentage of segmentations that crossed the expert DSC IOV cutoff when stratified by structure type was 55% and 31% for OARs and tumors, respectively. Regression analysis revealed that the structure being tumor-related had a substantial negative impact on binarized DSC for the breast, sarcoma, H&N, and GI cases. There were no recurring relationships between segmentation quality and demographic variables across the cases, with most variables demonstrating large standard deviations.
Our study highlights substantial uncertainty surrounding conventionally presumed factors influencing segmentation quality relative to benchmarks.
放射治疗自动分割训练数据的质量至关重要，这些数据主要来自临床医生的标注。然而，影响临床医生标注质量的因素尚不清楚；我们的研究旨在量化这些因素。
使用来自放射肿瘤学轮廓共识协作组数据集中放射肿瘤学家提供的危及器官（OAR）和肿瘤相关的分割。分割来自五个疾病部位：乳腺、肉瘤、头颈部（H&N）、妇科（GYN）和胃肠道（GI）。通过将观察者的分割与专家得出的共识进行比较，逐结构确定分割质量，专家共识作为参考标准基准。Dice相似系数（DSC）主要用作比较的指标。根据特定结构的专家得出的观察者间变异性（IOV）临界值，将DSC分层为二元组。使用贝叶斯估计的广义线性混合效应模型来研究人口统计学变量与每个疾病部位的二元化DSC之间的关联。最高密度区间不包括零的变量被认为对结果测量有实质性影响。
分别对乳腺、肉瘤、头颈部、妇科和胃肠道病例使用了574、110、452、112和48个分割。按结构类型分层时，超过专家DSC IOV临界值的分割的中位数百分比，OAR为55%，肿瘤为31%。回归分析显示，对于乳腺、肉瘤、头颈部和胃肠道病例，与肿瘤相关的结构对二元化DSC有实质性负面影响。各病例中分割质量与人口统计学变量之间没有反复出现的关系，大多数变量的标准差都很大。
我们的研究突出了相对于基准而言，围绕传统上假定的影响分割质量的因素存在的重大不确定性。
