文献速递腹部技术与安全MR

深度学习与亚区域影像组学融合提高局部进展期直肠癌新辅助放化疗病理完全缓解预测

Integration of Deep Learning and Sub-regional Radiomics Improves the Prediction of Pathological Complete Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer Patients.
PubMed 文献 · Acad Radiol · 2025-01-13

这项回顾性研究纳入三家独立医院的768例局部进展期直肠癌患者,基于治疗前盆腔T2加权MRI提取影像组学、亚区域影像组学和深度学习特征,构建SRADL联合模型预测病理完全缓解;训练队列AUC 0.925,外部测试1 AUC 0.915、测试2 AUC 0.902,优于其他单模态模型。

要点

  • SRADL联合模型在训练队列AUC 0.925、测试1 AUC 0.915、测试2 AUC 0.902,优于其他单模态模型。
  • 以最优阈值0.486分组,三个队列中预测pCR组生存均长于预测非pCR组。
  • 模型基于治疗前盆腔T2加权MRI,采用K-means将肿瘤分为亚区域后提取特征。

核心结论

  • 整合深度学习与亚区域影像组学特征的SRADL模型在预测局部进展期直肠癌新辅助放化疗病理完全缓解方面表现出较高准确性和稳健性,作者认为其有望成为个性化管理的工具。

研究设计与样本

  • 回顾性研究,从三家独立医院纳入768例接受新辅助放化疗后行根治性手术的合格参与者,采集治疗前盆腔MRI T2加权图像用于标注和特征提取。

关键影像表现/征象

  • 采用K-means方法将肿瘤分割为亚区域。
  • 分别用Pyradiomics和3D ResNet50提取影像组学特征和深度学习特征。
  • 在训练队列中用机器学习算法基于影像组学、亚区域影像组学和深度学习特征构建预测模型,并在外部测试中验证。

诊断标准与关键数值

  • SRADL模型预测pCR的AUC在训练队列为0.925(95%CI 0.894至0.948),测试1为0.915(95%CI 0.869至0.949),测试2为0.902(95%CI 0.846至0.945)。
  • 采用最优阈值0.486进行分组,预测pCR组在三个队列中生存均长于预测非pCR组。
  • SRADL模型优于其他单模态预测模型。

临床应用与阅片要点

  • 基于治疗前盆腔T2加权MRI,可提取肿瘤亚区域影像组学与深度学习特征构建SRADL模型辅助预测pCR。
  • 模型评估采用AUC、决策曲线分析和Kaplan-Meier生存分析。

局限性

  • 原文未报告局限性。

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)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: The precise prediction of response to neoadjuvant chemoradiotherapy is crucial for tailoring perioperative treatment in patients diagnosed with locally advanced rectal cancer (LARC). This retrospective study aims to develop and validate a model that integrates deep learning and sub-regional radiomics from MRI imaging to predict pathological complete response (pCR) in patients with LARC.

MATERIALS AND METHODS: We retrospectively enrolled 768 eligible participants from three independent hospitals who had received neoadjuvant chemoradiotherapy followed by radical surgery. Pretreatment pelvic MRI scans (T2-weighted), were collected for annotation and feature extraction. The K-means approach was used to segment the tumor into sub-regions. Radiomics and deep learning features were extracted by the Pyradiomics and 3D ResNet50, respectively. The predictive models were developed using the radiomics, sub-regional radiomics, and deep learning features with the machine learning algorithm in training cohort, and then validated in the external tests. The models' performance was assessed using various metrics, including the area under the curve (AUC), decision curve analysis, Kaplan-Meier survival analysis.

RESULTS: We constructed a combined model, named SRADL, which includes deep learning with sub-regional radiomics signatures, enabling precise prediction of pCR in LARC patients. SRADL had satisfactory performance for the prediction of pCR in the training cohort (AUC 0.925 [95% CI 0.894 to 0.948]), and in test 1 (AUC 0.915 [95% CI 0.869 to 0.949]) and in test 2 (AUC 0.902 [95% CI 0.846 to 0.945]). By employing optimal threshold of 0.486, the predicted pCR group had longer survival compared to predicted non-pCR group across three cohorts. SRADL also outperformed other single-modality prediction models.

CONCLUSION: The novel SRADL, which integrates deep learning with sub-regional signatures, showed high accuracy and robustness in predicting pCR to neoadjuvant chemoradiotherapy using pretreatment MRI images, making it a promising tool for the personalized management of LARC.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Wu X, Wang J, Chen C, et al. Integration of Deep Learning and Sub-regional Radiomics Improves the Prediction of Pathological Complete Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer Patients. Acad Radiol. 2025. PMID: 39809603. doi:10.1016/j.acra.2024.12.049

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。