文献速递消化道肿瘤放疗放疗物理与技术

基于直肠癌新辅助放化疗后MRI的深度学习模型预测病理缓解

Image-based deep learning model for predicting pathological response in rectal cancer using post-chemoradiotherapy magnetic resonance imaging.
PubMed 文献 · Radiother Oncol · 2021-06-15

单中心纳入466例接受术前放化疗后手术的局部进展期直肠癌患者,其中113例(24.3%)为留出测试集,基于放化疗后T2加权轴位MR图像构建两个深度学习模型分别预测pCR(Dworak TRG 4)和GR(TRG 3或4)。测试集显示模型预测pCR的AUC为0.76、准确率85.0%,预测GR的AUC为0.72、准确率71.7%,预测性能优于观察者。

要点

  • 基于放化疗后T2加权轴位MRI的深度学习模型可预测直肠癌pCR,测试集AUC 0.76。
  • 模型预测GR的测试集AUC为0.72,准确率71.7%。
  • 模型预测性能优于资深放射科医生和放射肿瘤科医生。

核心结论

  • 放化疗后T2加权轴位MR图像深度学习模型在预测直肠癌pCR或GR方面表现可接受,且优于人类观察者。

研究设计与样本

  • 单中心收集466例接受术前放化疗后手术切除的局部进展期直肠癌患者,其中113例(24.3%)分配至留出测试集。
  • 基于放化疗后T2加权轴位MR图像分别开发预测pCR和GR的两个深度学习模型。
  • pCR定义为Dworak TRG 4,GR定义为TRG 3或4。
  • 在测试集评估模型性能,并与一名资深放射科医生和一名放射肿瘤科医生比较。

主要发现

  • 测试集预测pCR的AUC、敏感度、特异度、阳性预测值、阴性预测值、准确率分别为0.76、0.30、0.96、0.67、0.87、85.0%。
  • 测试集预测GR的AUC、敏感度、特异度、阳性预测值、阴性预测值、准确率分别为0.72、0.54、0.81、0.60、0.77、71.7%。
  • 深度学习模型预测性能优于观察者。
  • pCR预测中真实标签与模型的一致度为fair(kappa=0.34),GR预测为fair(kappa=0.36)。

关键数值与推荐

  • pCR定义为Dworak TRG 4,GR定义为TRG 3或4。

临床怎么用

  • 可基于放化疗后T2加权轴位MRI用深度学习模型辅助预测直肠癌pCR或GR,作为观察者评估的补充参考。

局限性

  • 研究为单中心设计,外部泛化性未验证。
  • pCR预测敏感度仅0.30,模型与真实标签一致度仅为fair(kappa=0.34)。

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

INTRODUCTION: To develop an image-based deep learning model for predicting pathological response in rectal cancer using post-chemoradiotherapy magnetic resonance (MR) imaging. MATERIALS AND METHODS: A total of 466 patients with locally advanced rectal cancer who received preoperative chemoradiotherapy followed by surgical resection were collected from single center, among whom 113 (24.3%) were allocated to the holdout testing set. Complete response (pCR) was defined as Dworak tumor regression grade (TRG) 4, while good response (GR) was defined as TRG 3 or 4. Based on post-chemoradiotherapy T2-weighted axial MR images, two deep learning models were developed to predict pCR and GR, respectively. The prediction performance of the deep learning models was evaluated in the testing set and was compared to that of a senior radiologist and a radiation oncologist. RESULTS: The deep learning model showed an area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 0.76, 0.30, 0.96, 0.67, 0.87, and 85.0% for predicting pCR and 0.72, 0.54, 0.81, 0.60, 0.77, and 71.7% for predicting GR, respectively. The deep learning model had a superior predictive performance than the observers. Fair agreement between the ground truth and the model was shown for pCR prediction (kappa = 0.34) and GR prediction (kappa = 0.36). CONCLUSIONS: The post-chemoradiotherapy T2-weighted axial MR image-based deep learning model showed acceptable performance in predicting pCR or GR in patients with rectal cancer, compared with human observers.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Jang BS, Lim YJ, Song C, et al. Image-based deep learning model for predicting pathological response in rectal cancer using post-chemoradiotherapy magnetic resonance imaging. Radiother Oncol. 2021. PMID: 34139211. doi:10.1016/j.radonc.2021.06.019

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。