Prognostic Analysis of 131I Efficacy After Papillary Thyroid Carcinoma Surgery Based on CT Radiomics

Abstract

Objective: To develop and validate a radiomics-clinical combined model combining preoperative computed tomography (CT) and clinical data from patients with papillary thyroid carcinoma (PTC) to predict the efficacy of initial postoperative 131I treatment.

Methods: A total of 181 patients with PTC who received total thyroidectomy and initial 131I treatment were divided into training and testing sets (7:3 ratio). Univariate analysis and multivariate logistic regression were used to screen clinical factors affecting the therapeutic response to 131I treatment and construct a clinical model. Radiomics features extracted from preoperative CT images of PTCs were dimensionally reduced through recursive feature elimination and least absolute shrinkage and selection operator. Logistic regression was used to establish a radiomics model, and a radiomics-clinical combined model was developed by integrating the clinical model. The area under the curve (AUC), sensitivity, and specificity were used to evaluate the prediction performance of each model.

Results: Multivariate analysis revealed that pre-131I treatment serum thyroglobulin was an independent clinical risk factor affecting the efficacy of initial 131I treatment (P = .002), and the AUC, sensitivity, and specificity for predicting the efficacy of initial 131I treatment were 0.895, 0.899, and 0.816, respectively. After dimensionality reduction, 14 key CT radiomics features of PTCs were included. The established radiomics model predicted the efficacy of 131I treatment in the training and testing sets with AUCs of 0.825 and 0.809, sensitivities of 0.828 and 0.636, and specificities of 0.745 and 0.944, respectively. The combined model improved the AUC, sensitivity, and specificity in both sets.

Conclusion: The preoperative CT-based radiomics model can effectively predict the efficacy of initial postoperative 131I treatment in patients with intermediate- or high-risk PTC, and the radiomics-clinical combined model exhibits better predictive performance.

Keywords: Iodine-131; papillary thyroid carcinoma; predictive model; radiomics; treatment outcome.

Figure 1.

The flowchart of patient selection.

Figure 2.

Segmentation schematic diagram of papillary thyroid carcinoma primary lesion.

Figure 3.

Screening of useful features using the LASSO regression. (A) Hyperparameter lambda in LASSO regression radiomics feature screening. The x-axis represents lambda values and the y-axis represents MSE. (B) Changes in the LASSO regression model radiomics feature coefficients. The coefficient on the x-axis represents the lambda value and the y-axis represents the radiomics feature coefficient. Abbreviations: LASSO, least absolute shrinkage and selection operator; MSE, mean square error.

Figure 4.

Receiver operating characteristic curves of the radiomics model and combined model in the training and testing sets. (A) Training set; (B) testing set. Abbreviations: RCCM, radiomics-clinical combined model; RM, radiomics model.

Figure 5.

Calibration curves of the radiomics model and combined model for predicting the initial ¹³¹I therapeutic response. (A) Training set; (B) testing set. Abbreviations: HL, Hosmer–Lemeshow test; RCCM, radiomics-clinical combined model; RM, radiomics model.

Figure 6.

Clinical decision curve analysis for the 3 models in the training and testing sets. (A) Training set; (B) testing set. The x-axis represents the threshold probability, and the y-axis represents the net benefit. Abbreviations: RCCM, radiomics-clinical combined model; RM, radiomics model; sTg, serum thyroglobulin (ie, clinical model).

Figure 7.

Nomogram for predicting the initial ¹³¹I therapeutic response.