Insights into Imaging (Jun 2024)

Multiparametric MRI-based radiomic model for predicting lymph node metastasis after neoadjuvant chemoradiotherapy in locally advanced rectal cancer

  • Qiurong Wei,
  • Ling Chen,
  • Xiaoyan Hou,
  • Yunying Lin,
  • Renlong Xie,
  • Xiayu Yu,
  • Hanliang Zhang,
  • Zhibo Wen,
  • Yuankui Wu,
  • Xian Liu,
  • Weicui Chen

DOI
https://doi.org/10.1186/s13244-024-01726-4
Journal volume & issue
Vol. 15, no. 1
pp. 1 – 14

Abstract

Read online

Abstract Objectives To construct and validate multiparametric MR-based radiomic models based on primary tumors for predicting lymph node metastasis (LNM) following neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC) patients. Methods A total of 150 LARC patients from two independent centers were enrolled. The training cohort comprised 100 patients from center A. Fifty patients from center B were included in the external validation cohort. Radiomic features were extracted from the manually segmented volume of interests of the primary tumor before and after nCRT. Feature selection was performed using multivariate logistic regression analysis. The clinical risk factors were selected via the least absolute shrinkage and selection operator method. The radiologist’s assessment of LNM was performed. Eight models were constructed using random forest classifiers, including four single-sequence models, three combined-sequence models, and a clinical model. The models’ discriminative performance was assessed via receiver operating characteristic curve analysis quantified by the area under the curve (AUC). Results The AUCs of the radiologist’s assessment, the clinical model, and the single-sequence models ranged from 0.556 to 0.756 in the external validation cohort. Among the single-sequence models, modelpost_DWI exhibited superior predictive power, with an AUC of 0.756 in the external validation set. In combined-sequence models, modelpre_T2_DWI_post had the best diagnostic performance in predicting LNM after nCRT, with a significantly higher AUC (0.831) than those of the clinical model, modelpre_T2_DWI, and the single-sequence models (all p < 0.05). Conclusions A multiparametric model that incorporates MR radiomic features before and after nCRT is optimal for predicting LNM after nCRT in LARC. Critical relevance statement This study enrolled 150 LARC patients from two independent centers and constructed multiparametric MR-based radiomic models based on primary tumors for predicting LNM following nCRT, which aims to guide therapeutic decisions and predict prognosis for LARC patients. Key Points The biological characteristics of primary tumors and metastatic LNs are similar in rectal cancer. Radiomics features and clinical data before and after nCRT provide complementary tumor information. Preoperative prediction of LN status after nCRT contributes to clinical decision-making. Graphical Abstract

Keywords