Prediction of pathological nodal stage after neoadjuvant chemoradiotherapy by using the interaction between tumor features and lymph node features from pretreatment MRI in rectal cancer

ZHU Haitao; ZHANG Xiaoyan; LI Xiaoting; SHI Yanjie; ZHU Huici; WANG Lin; WU Aiwen; SUN Yingshi

doi:10.19732/j.cnki.2096-6210.2022.02.003

您当前的位置：

首页 >

文章列表页 >

Prediction of pathological nodal stage after neoadjuvant chemoradiotherapy by using the interaction between tumor features and lymph node features from pretreatment MRI in rectal cancer　

更新时间：2025-12-15

- Prediction of pathological nodal stage after neoadjuvant chemoradiotherapy by using the interaction between tumor features and lymph node features from pretreatment MRI in rectal cancer　
- Vol. 31, Issue 2, Pages: 113-120(2022)
- 作者机构：
  
  1. 北京大学肿瘤医院医学影像科,北京,100142
  2. 北京大学肿瘤医院结直肠肿瘤外科,北京,100142
- 作者简介：
- 基金信息：
- DOI：10.19732/j.cnki.2096-6210.2022.02.003
  CLC：
- Published Online：28 April 2022，
  
  Published：28 April 2022
- 稿件说明：
移动端阅览
朱海涛,张晓燕,李晓婷,等. 基线MRI中直肠癌原发灶与淋巴结交互特征预测新辅助治疗后淋巴结状态[J]. 肿瘤影像学, 2022, 31(2): 113-120 https://doi.

org/10.19732/j.cnki.2096-6210.2022.02.003
朱海涛,张晓燕,李晓婷,等. 基线MRI中直肠癌原发灶与淋巴结交互特征预测新辅助治疗后淋巴结状态[J]. 肿瘤影像学, 2022, 31(2): 113-120 https://doi. DOI： 10.19732/j.cnki.2096-6210.2022.02.003.

org/10.19732/j.cnki.2096-6210.2022.02.003 DOI：

摘要

目的：

探索基线直肠癌磁共振成像（magnetic resonance imaging，MRI）图像中原发灶与淋巴结特征的交互作用对于新辅助治疗后淋巴结状态的预测能力。

方法：

回顾并收集229例局部进展期直肠癌的基线MRI数据和淋巴结病理学检查结果。由3名影像科医师在基线直肠癌MRI图像中手动勾画肿瘤原发灶和体积最大淋巴结感兴趣区，并分别提取2个区域各41个影像学特征，并计算两者的交互项41个。参照淋巴结的病理学检查结果计算每一个肿瘤原发灶特征、淋巴结特征以及其交互项的受试者工作特征（receiver operating characteristic，ROC）曲线的曲线下面积（area under curve，AUC）。

结果：

将123个影像学特征按照AUC值降序排列，其前41个特征中有21个属于交互项。灰度共生矩阵对比度特征交互项的AUC为0.727 6，高于单独使用原发灶的对比度特征（AUC=0.555 3，

=0.000 8）或淋巴结的对比度特征（AUC=0.713 9，

=0.038 4）。一阶特征中灰度总和特征交互项预测淋巴结病理学状态的AUC为0.713 5，高于单独使用原发灶的灰度总和特征（AUC=0.567 6，

=0.003 1）或淋巴结的灰度总和特征（AUC=0.690 8，

=0.012 0）。

结论：

相对于单独使用直肠癌MRI图像中的肿瘤原发灶或淋巴结特征，二者的交互项能够更准确地对新辅助治疗后淋巴结病理学状态进行预测。

Abstract

Objective:

To increase the prediction accuracy of pathological nodal stage after neoadjuvant chemoradiotherapyby using the interaction between tumor features and lymph node features from pretreatment magnetic resonance imaging (MRI) data.

Methods:

The MRI data and pathological N-stage of 229 patients with locally advanced rectal cancer were retrospectively collected. And 3 radiologists delineated region of interest on tumor region and lymph node regions. 41 features were extracted from the primary tumor and the largest lymph node respectively. 41 interaction terms were calculated. Receiver operating characteristic(ROC) curve was generated by comparing each of the 123 features with the pathological N-stage. Area under curve (AUC) was calculated.

Results:

After ranking the 123 features with a descending order of AUC value

21 out of the first 41 features belong to the interaction terms. The contract feature in gray level cooccurrence produces AUC=0.727 6 at the interaction term

larger than using the corresponding tumor feature (AUC=0.555 3) or lymph node feature (AUC=0.713 9) alone. The signal sum in first-order features produces AUC=0.713 5 at the interaction term

larger than using the corresponding tumor feature (AUC=0.567 6) or lymph node feature (AUC=0.690 8) alone.

Conclusion:

The interaction between tumor features and lymph node features from pretreatment MRI data performed better than each of them for the prediction of pathological N-stage after neoadjuvant chemoradiotherapy.

关键词

Keywords

references

Views

864

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research progress of quantitative assessment of MRI and radiomics for lymph node metastasis of rectal cancer

Prediction of microsatellite instability in rectal cancer using MRI radiomics models based on multiple machine learning algorithms

Radiomics based on RESOLVE ADC in identification of extramural venous invasion in rectal cancer

Incremental value of morphologic features on high-resolution MRI in the diagnosis of lymph node metastasis of rectal cancer

High resolution T2WI image-based radiomics nomogram for prediction of perineural invasion in rectal cancer

Related Author

XU Meihai

SHEN Wei

Lu LI

Wen BU

Qiaoyu SUN

Wei WANG

Yuwen ZHANG

Haidong JIANG

Related Institution

Department of Radiology, The First Affiliated Hospital of Bengbu Medical University

Department of Radiology, Affiliated Tumor Hospital of Nantong University

Department of Pathology, Affiliated Tumor Hospital of Nantong University

GE Healthcare

河北省沧州中西医结合医院影像中心

AI问答

⁰