Purpose: When autocontouring based on artificial intelligence (AI) is used in the radiotherapy (RT) workflow, the contours are reviewed and eventually adjusted by a radiation oncologist before an RT treatment plan is generated, with the purpose of improving dosimetry and reducing both interobserver variability and time for contouring. The purpose of this study was to evaluate the results of application of a commercial AI-based autocontouring forRT, assessing both geometric accuracies and the influence on optimized dose from automatically generated contours after review by human operator. Materials and Methods: A commercial autocontouring system was applied to a retrospective database of 40 patients, of which 20 were treated with radiotherapy for prostate cancer (PCa) and 20 for head and neck cancer (HNC). Contours resulting fromAIwere compared againstAIcontours reviewed by human operator and human-only contours using Dice similarity coefficient (DSC), Hausdorff distance (HD), and relative volume difference (RVD). Dosimetric indices such asDmean,D0.03cc, and normalized plan quality metrics were used to compare dose distributions from RT plans generated from structure sets contoured by humans assisted byAIagainst plans from manual contours. The reduction in contouring time obtained by using automated tools was also assessed. A Wilcoxon rank sum test was computed to assess the significance of differences. Interobserver variability of the comparison of manual vs. AI-assisted contours was also assessed among two radiation oncologists for PCa. Results: For PCa, AI-assisted segmentation showed good agreement with expert radiation oncologist structures with averageDSCamong patients ≥ 0.7 for all structures, and minimal radiation oncology adjustment of structures (DSCof adjusted versusAIstructures ≥ 0.91). ForHNC, results of comparison between manual andAIcontouring varied considerably e.g., 0.77 for oral cavity and 0.11–0.13 for brachial plexus, but again, adjustment was generally minimal (DSCof adjusted againstAIcontours 0.97 for oral cavity, 0.92–0.93 for brachial plexus). The difference in dose for the target and organs at risk were not statistically significant between human and AI-assisted, with the only exceptions of D0.03ccto the anal canal andDmeanto the brachial plexus. The observed average differences in plan quality for PCa andHNCcases were 8% and 6.7%, respectively. The dose parameter changes due to interobserver variability in PCa were small, with the exception of the anal canal, where large dose variations were observed. The reduction in time required for contouring was 72% for PCa and 84% forHNC. Conclusions: When an autocontouring system is used in combination with human review, the time of the RT workflow is significantly reduced without affecting dose distribution and plan quality.
目的：在放射治疗（RT）工作流程中应用基于人工智能（AI）的自动勾画时，放射肿瘤科医师会在生成RT治疗计划前对勾画结果进行审核并最终调整，旨在改善剂量学、减少观察者间差异并缩短勾画时间。本研究旨在评估商用AI自动勾画系统在RT中的应用效果，从几何精度和人工审核后自动生成轮廓对优化剂量的影响两方面进行评估。材料与方法：将商用自动勾画系统应用于包含40例患者的回顾性数据库，其中20例为前列腺癌（PCa）放疗患者，20例为头颈癌（HNC）放疗患者。通过戴斯相似系数（DSC）、豪斯多夫距离（HD）和相对体积差异（RVD）比较AI生成的轮廓、经人工审核的AI轮廓以及纯人工勾画轮廓。采用平均剂量（Dmean）、0.03立方厘米体积受量（D0.03cc）及标准化计划质量指标等剂量学参数，比较基于AI辅助人工勾画的结构集生成的RT计划与纯手工勾画计划的剂量分布。同时评估使用自动化工具所减少的勾画时间，并采用威尔科克森秩和检验分析差异显著性。在前列腺癌病例中，还评估了两位放射肿瘤科医师进行人工勾画与AI辅助勾画对比的观察者间差异。结果：对于PCa，AI辅助分割与专家勾画结构高度一致，所有结构的患者平均DSC≥0.7，且放射肿瘤科医师对结构的调整极小（调整后结构与AI结构的DSC≥0.91）。对于HNC，人工与AI勾画结果的差异较大（如口腔DSC为0.77，臂丛神经为0.11-0.13），但调整幅度总体仍较小（调整后结构与AI轮廓的DSC：口腔为0.97，臂丛神经为0.92-0.93）。除肛管D0.03cc和臂丛神经Dmean外，人工与AI辅助勾画在靶区和危及器官的剂量差异均无统计学意义。PCa和HNC病例的计划质量平均差异分别为8%和6.7。除观察到肛管存在较大剂量变异外，PCa中因观察者间差异导致的剂量参数变化较小。勾画时间减少幅度为PCa 72%，HNC 84%。结论：当自动勾画系统与人工审核结合使用时，可在不影响剂量分布和计划质量的前提下显著缩短RT工作流程时间。
肿瘤(癌症)患者之家