结合深度学习与影像组学在食管癌容积旋转调强放疗患者治疗前放射性食管炎预测中的应用
本研究回顾性纳入两中心273例接受容积旋转调强放疗的食管癌患者,提取CT与放疗剂量分布图像的影像组学、剂量组学和深度学习特征构建预测≥2级放射性食管炎的模型。联合模型DLD+剂量组学+临床因素在训练组、内部验证组和外部验证组的AUC分别为0.913、0.821和0.805。
要点
- 联合DLD、剂量组学特征与临床因素的模型预测≥2级放射性食管炎的外部验证AUC为0.805。
- 单独影像组学特征XGBoost模型内部与外部验证AUC分别为0.703和0.694。
- 单独剂量组学特征XGBoost模型内部与外部验证AUC分别为0.801和0.729。
核心结论
- 尽管剂量本身不是预测准确性的决定因素,但多种特征提取方法的组合是提高放射性食管炎预测准确性的一个因素。
- 将DLD与剂量组学特征结合在食管癌VMAT患者治疗前放射性食管炎预测中具有前景。
研究设计与样本
- 回顾性纳入两中心273例接受容积旋转调强放疗的食管癌患者,分为训练组152例、内部验证组66例和外部验证组55例。
- 从CT和放疗剂量分布图像中提取并筛选影像组学特征、剂量组学特征以及卷积神经网络深度学习特征以预测放射性食管炎。
- 采用受试者工作特征曲线下面积(AUC)评估和比较模型性能。
主要发现
- 共筛选出5个影像组学特征和10个剂量组学特征。
- XGBoost模型使用影像组学特征在内部和外部验证组的AUC分别为0.703和0.694,使用剂量组学特征分别为0.801和0.729。
- ResNet34模型对基于影像组学的DL模型(DLR)和基于剂量分布的DL模型(DLD)在内部和外部验证组的AUC分别为0.642和0.657、0.762和0.737。
- DLD+剂量组学+临床因素联合模型在训练组、内部验证组和外部验证组的AUC分别为0.913、0.821和0.805。
关键数值与推荐
- 预测目标为≥2级放射性食管炎。
- XGBoost使用影像组学特征内部验证AUC 0.703、外部验证AUC 0.694;使用剂量组学特征内部验证AUC 0.801、外部验证AUC 0.729。
- ResNet34的DLR模型内部验证AUC 0.642、外部验证AUC 0.657;DLD模型内部验证AUC 0.762、外部验证AUC 0.737。
- 联合模型DLD+剂量组学+临床因素训练组AUC 0.913、内部验证AUC 0.821、外部验证AUC 0.805。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: To develop a combined radiomics and deep learning (DL) model in predicting radiation esophagitis (RE) of a grade ≥ 2 for patients with esophageal cancer (EC) underwent volumetric modulated arc therapy (VMAT) based on computed tomography (CT) and radiation dose (RD) distribution images. MATERIALS AND METHODS: A total of 273 EC patients underwent VMAT were retrospectively reviewed and enrolled from two centers and divided into training (n = 152), internal validation (n = 66), and external validation (n = 55) cohorts, respectively. Radiomic and dosiomic features along with DL features using convolutional neural networks were extracted and screened from CT and RD images to predict RE. The performance of these models was evaluated and compared using the area under curve (AUC) of the receiver operating characteristic curves (ROC). RESULTS: There were 5 and 10 radiomic and dosiomic features were screened, respectively. XGBoost achieved a best AUC of 0.703, 0.694 and 0.801, 0.729 with radiomic and dosiomic features in the internal and external validation cohorts, respectively. ResNet34 achieved a best prediction AUC of 0.642, 0.657 and 0.762, 0.737 for radiomics based DL model (DLR) and RD based DL model (DLD) in the internal and external validation cohorts, respectively. Combined model of DLD + Dosiomics + clinical factors achieved a best AUC of 0.913, 0.821 and 0.805 in the training, internal, and external validation cohorts, respectively. CONCLUSION: Although the dose was not responsible for the prediction accuracy, the combination of various feature extraction methods was a factor in improving the RE prediction accuracy. Combining DLD with dosiomic features was promising in the pretreatment prediction of RE for EC patients underwent VMAT.
引用
- Xie C, Yu X, Tan N, et al. Combined deep learning and radiomics in pretreatment radiation esophagitis prediction for patients with esophageal cancer underwent volumetric modulated arc therapy. Radiother Oncol. 2024. PMID: 39013503. doi:10.1016/j.radonc.2024.110438
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。