Radiomics Based on T2-Weighted Imaging and Apparent Diffusion Coefficient Images for Preoperative Evaluation of Lymph Node Metastasis in Rectal Cancer Patients

Abstract

Purpose: To develop and validate a radiomics nomogram based on T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) features for the preoperative prediction of lymph node (LN) metastasis in rectal cancer patients.

Materials and methods: One hundred and sixty-two patients with rectal cancer confirmed by pathology were retrospectively analyzed, who underwent T2WI and DWI sequences. The data sets were divided into training (n = 97) and validation (n = 65) cohorts. For each case, a total of 2,752 radiomic features were extracted from T2WI, and ADC images derived from diffusion-weighted imaging. A two-sample t-test was used for prefiltering. The least absolute shrinkage selection operator method was used for feature selection. Three radiomics scores (rad-scores) (rad-score 1 for T2WI, rad-score 2 for ADC, and rad-score 3 for the combination of both) were calculated using the support vector machine classifier. Multivariable logistic regression analysis was then used to construct a radiomics nomogram combining rad-score 3 and independent risk factors. The performances of three rad-scores and the nomogram were evaluated using the area under the receiver operating characteristic curve (AUC). Decision curve analysis (DCA) was used to assess the clinical usefulness of the radiomics nomogram.

Results: The AUCs of the rad-score 1 and rad-score 2 were 0.805, 0.749 and 0.828, 0.770 in the training and validation cohorts, respectively. The rad-score 3 achieved an AUC of 0.879 in the training cohort and an AUC of 0.822 in the validation cohort. The radiomics nomogram, incorporating the rad-score 3, age, and LN size, showed good discrimination with the AUC of 0.937 for the training cohort and 0.884 for the validation cohort. DCA confirmed that the radiomics nomogram had clinical utility.

Conclusions: The radiomics nomogram, incorporating rad-score based on features from the T2WI and ADC images, and clinical factors, has favorable predictive performance for preoperative prediction of LN metastasis in patients with rectal cancer.

Keywords: lymph node metastasis; machine learning; magnetic resonance imaging; radiomics; rectal cancer.

Figure 1

The framework for the radiomics workflow.

Figure 2

Dot diagram of the three rad-scores in each cohort. Dot diagram of rad-score 1 in the training (A) and validation (D) cohorts. Dot diagram of rad-score 2 in the training (B) and validation (E) cohorts. Dot diagram of rad-score 3 in the training (C) and validation (F) cohorts.

Figure 3

Comparisons of the ROC curves for the clinical model and three rad-scores in each cohort. (A) The ROC curves for the clinical model and three rad-scores in the training cohort. (B) The ROC curves for the clinical model and three rad-scores in the validation cohort.

Figure 4

Radiomics nomogram incorporating the rad-score 3, age, and the LN size.

Figure 5

The ROC curves for radiomics nomogram in each cohort. (A) The ROC curve for radiomics nomogram in the training cohort. (B) The ROC curve for radiomics nomogram in the validation cohort.

Figure 6

Calibration curves of radiomics nomogram in each cohort. (A) The calibration curve of radiomics nomogram in the training cohort. (B) The calibration curve of radiomics nomogram in the validation cohort. The x-axis represented the predicted LN metastasis risk. The y-axis represented the actual LN metastasis rate. The diagonal blue line represented a perfect prediction by an ideal model. The red line represented the performance of the radiomics nomogram, of which a closer fit to the diagonal blue line represented a better prediction.

Figure 7

DCA for radiomics nomogram in the validation cohort. The y-axis indicated the net benefit. The red line, blue line, and horizontal black line represented the net benefit of the radiomics nomogram, treat-all strategy, and treat-none strategy, respectively.