Magnetic resonance imaging-based radiomics in predicting the expression of Ki-67, p53, and epidermal growth factor receptor in rectal cancer.

Abstract

Background: The preoperative evaluation of the expression levels of Ki-67, p53, and epidermal growth factor receptor (EGFR) based on magnetic resonance imaging (MRI) of rectal cancer is necessary to facilitate individualized therapy. This study aimed to develop and validate radiomics models for the evaluation of the expression levels of Ki-67, p53, and EGFR of rectal cancer from preoperative MRI.

Methods: In this retrospective study, 124 patients (38 in the test group and 86 in the training group) with rectal cancer who underwent preoperative MRI and postoperative Ki-67, p53 and EGFR assay were included in Longyan First Affiliated Hospital of Fujian Medical University from June 2015 to October 2019. A total of 796 radiomics features were acquired from both diffusion-weighted imaging (DWI) and T2-weighted imaging (T2WI). Least absolute shrinkage and selection operator (LASSO) and the minimum redundancy maximum relevance (mRMR) were used to select the most predictive texture features, and then the radiomics score (Rad-score) models were derived to evaluate Ki-67, p53, and EGFR expression status based on the radiomics signature. The receiver operating characteristic (ROC) was used to assess the model's performance, and the reliability was verified via accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

Results: The Rad-score evaluation of Ki-67 expression status yielded area under the curve (AUC) values of 0.91 [95% confidence interval (CI): 0.87-0.95] and 0.81 (95% CI: 0.66-0.96) in the training and test groups. The evaluation of p53 expression produced AUC values of 0.82 (95% CI: 0.77-0.88) and 0.80 (95% CI: 0.65-0.96). For evaluating EGFR expression status in both training and test groups, the AUC values were 0.86 (95% CI: 0.81-0.91) and 0.76 (95% CI: 0.58-0.93), respectively. While Rad-score of Ki-67 expression status in the training group obtained the top accuracy, sensitivity, specificity, and PPV with values of 0.85, 0.80, 0.92, and 0.93.

Conclusions: Preoperative MRI-based radiomics analysis has the ability to noninvasively assess the postoperative Ki-67, p53, and EGFR of rectal cancer.