School of Biomedical Engineering, Anhui Medical University, Hefei, 230032, China.
Hefei Cancer Hospital, Chinese Academy of Sciences, Hefei, 230031, P.R. China.
BMC Med Imaging. 2024 Nov 18;24(1):313. doi: 10.1186/s12880-024-01473-4.
Esophageal fistula (EF), a rare and potentially fatal complication, can be better managed with predictive models for personalized treatment plans in esophageal cancers. We aim to develop a clinical-deep learning radiomics model for effectively predicting the occurrence of EF.
The study involved esophageal cancer patients undergoing radiotherapy or chemoradiotherapy. Arterial phase enhanced CT images were used to extract handcrafted and deep learning radiomic features. Along with clinical information, a 3-step feature selection method (statistical tests, Least Absolute Shrinkage and Selection Operator, and Recursive Feature Elimination) was used to identify five feature sets in training cohort for constructing random forest EF prediction models. Model performance was compared and validated in both retrospective and prospective test cohorts.
One hundred seventy five patients (122 in training and 53 in test cohort)were retrospectively collected from April 2018 to June 2022. An additional 27 patients were enrolled as a prospective test cohort from June 2022 to December 2023. Post-selection in the training cohort, five feature sets were used for model construction: clinical, handcrafted radiomic, deep learning radiomic, clinical-handcrafted radiomic, and clinical-deep learning radiomic. The clinical-deep learning radiomic model excelled with AUC of 0.89 (95% Confidence Interval: 0.83-0.95) in the training cohort, 0.81 (0.65-0.94) in the test cohort, and 0.85 (0.71-0.97) in the prospective test cohort. Brier-score and calibration curve analyses validated its predictive ability.
The clinical-deep learning radiomic model can effectively predict EF in patients with advanced esophageal cancer undergoing radiotherapy or chemoradiotherapy.
食管瘘（EF）是一种罕见且可能致命的并发症，可以通过预测模型为食管癌患者制定个性化治疗方案来更好地管理。我们旨在开发一种临床深度学习放射组学模型，以有效预测 EF 的发生。
本研究纳入了接受放疗或放化疗的食管癌患者。使用动脉期增强 CT 图像提取手工和深度学习放射组学特征。结合临床信息，采用 3 步特征选择方法（统计检验、最小绝对收缩和选择算子、递归特征消除），在训练队列中识别出 5 个特征集，用于构建随机森林 EF 预测模型。在回顾性和前瞻性测试队列中比较和验证模型性能。
从 2018 年 4 月至 2022 年 6 月，回顾性收集了 175 例患者（训练组 122 例，测试组 53 例）。从 2022 年 6 月至 2023 年 12 月，额外纳入了 27 例患者作为前瞻性测试队列。在训练队列中进行选择后，使用了 5 个特征集进行模型构建：临床、手工放射组学、深度学习放射组学、临床-手工放射组学和临床-深度学习放射组学。临床-深度学习放射组学模型在训练队列中的 AUC 为 0.89（95%置信区间：0.83-0.95），在测试队列中为 0.81（0.65-0.94），在前瞻性测试队列中为 0.85（0.71-0.97）。Brier 评分和校准曲线分析验证了其预测能力。
临床深度学习放射组学模型可有效预测接受放疗或放化疗的晚期食管癌患者 EF 的发生。
