To develop and externally validate an automatic Artificial Intelligence (AI) tool for delineating gross tumor volume (GTV) in esophageal squamous cell carcinoma (ESCC) patients, which can assist in the neo-adjuvant or radical radiation therapy treatment planning. In this multi-institutional study, contrast-enhanced CT images from 580 eligible ESCC patients were retrospectively collected. The GTV contours delineated by two experts via consensus were used as ground truth. A three-dimensional deep learning model was developed for GTV contouring in the training cohort and internally and externally validated in three validation cohorts. The AI tool was compared against twelve board-certified experts in 25 patients randomly selected from the external validation cohort to evaluate its assistance in improving contouring performance and reducing variation. Contouring performance was measured using dice similarity coefficient (DSC) and average surface distance (ASD). Additionally, our previously established radiomics model for predicting pathological complete response (pCR) was utilized to compare AI-generated and ground truth contours, in order to assess the potential of the AI contouring tool in radiomics analysis. The AI tool demonstrated good GTV contouring performance in multi-center validation cohorts, with median DSC values of 0.865, 0.876, and 0.866, and median ASD values of 0.939 mm, 0.789 mm, and 0.875 mm, respectively. Furthermore, the AI tool significantly improved contouring performance for half of twelve board-certified experts (DSC values, 0.794-0.835 vs 0.856-0.881, = 0.003-0.048), reduced the intra- and inter-observer variations by 37.4% and 55.2%, respectively, and saved contouring time by 77.6%. In the radiomics analysis, 88.7% of radiomic features from ground truth and AI-generated contours demonstrated stable reproducibility, and similar pCR prediction performance for these contours ( = 0.430) were observed. Our AI contouring tool can improve GTV contouring performance and facilitate radiomics analysis in ESCC patients, which indicated its potential on GTV contouring during radiation therapy treatment planning and radiomics studies.

中文翻译：

---

基于对比增强 CT 图像的食管癌自动大体肿瘤体积轮廓深度学习：一项多机构研究

开发并外部验证一种自动人工智能（AI）工具，用于描绘食管鳞状细胞癌（ESCC）患者的大体肿瘤体积（GTV），这可以协助新辅助或根治性放射治疗的治疗计划。在这项多机构研究中，回顾性收集了 580 名符合条件的 ESCC 患者的对比增强 CT 图像。两位专家通过协商一致描绘的 GTV 轮廓被用作地面实况。为训练队列中的 GTV 轮廓开发了三维深度学习模型，并在三个验证队列中进行了内部和外部验证。该人工智能工具与从外部验证队列中随机选出的 25 名患者的 12 名委员会认证专家进行了比较，以评估其在改善轮廓表现和减少变异方面的帮助。使用骰子相似系数 (DSC) 和平均表面距离 (ASD) 来测量轮廓性能。此外，我们之前建立的用于预测病理完全反应（pCR）的放射组学模型被用来比较人工智能生成的轮廓和地面真实轮廓，以评估人工智能轮廓工具在放射组学分析中的潜力。AI 工具在多中心验证队列中表现出良好的 GTV 轮廓表现，中位 DSC 值分别为 0.865、0.876 和 0.866，中位 ASD 值分别为 0.939 mm、0.789 mm 和 0.875 mm。此外，人工智能工具显着提高了 12 名委员会认证专家中的一半的轮廓绘制性能（DSC 值，0.794-0.835 vs 0.856-0.881，= 0.003-0.048），将观察者内部和观察者之间的差异减少了 37.4% 和 55.2%分别，并节省了 77.6% 的轮廓时间。在放射组学分析中，来自地面实况和 AI 生成轮廓的 88.7% 放射组学特征表现出稳定的再现性，并且观察到这些轮廓的类似 pCR 预测性能 (= 0.430)。我们的人工智能轮廓工具可以提高 GTV 轮廓性能并促进 ESCC 患者的放射组学分析，这表明了其在放射治疗计划和放射组学研究中 GTV 轮廓的潜力。