CT-based radiomics features for the differential diagnosis of nodular goiter and papillary thyroid carcinoma: an analysis employing propensity score matching

Abstract

Purpose: This study aims to evaluate the effectiveness of CT-based radiomics features in discriminating between nodular goiter (NG) and papillary thyroid carcinoma (PTC).

Methods: A retrospective cohort comprising 228 patients with nodular goiter (NG) and 227 patients with papillary thyroid carcinoma (PTC) diagnosed between January 2018 and December 2022 was consecutively enrolled. Propensity score matching (PSM) was applied to align patients with NG and PTC. A total of 851 radiomics features were extracted from CT images acquired during the arterial phase for each individual. Feature selection was carried out utilizing the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm to generate the radiomics score (Rad-score). Subsequently, the Rad-score was incorporated into a multivariate logistic regression analysis to construct a radiomics nomogram for visual representation.

Results: Following PSM implementation, 101 patients diagnosed with NG were matched with an equivalent number of patients diagnosed with PTC. The developed radiomics score exhibited excellent predictive performance in distinguishing between NG and PTC, with high values of AUC, sensitivity, and specificity in both the training cohort (AUC = 0.823, accuracy = 0.759, sensitivity = 0.794, specificity = 0.740) and validation cohort (AUC = 0.904, accuracy = 0.820, sensitivity = 0.758, specificity = 0.964).

Conclusion: The utilization of CT-based radiomics analysis following PMS offers a quantitative and data-driven approach to enhance the accuracy of distinguishing between nodular goiter (NG) and papillary thyroid carcinoma (PTC).

Keywords: computed tomography; nodular goiter; papillary thyroid carcinoma; propensity score matching; radiomics.

Figure 1

Flow diagram showing the selection of the study population.

Figure 2

The workflow of CT-based radiomics includes: Image acquisition; Segmentation; Feature extraction; Feature selection; Development of a Radiomics Nomogram.

Figure 3

Propensity scores of the baseline characteristics before and after matching. Distribution of propensity scores before (A, B) and after matching (C, D).

Figure 4

Radiomic feature selection was conducted using the parametric method known as the least absolute shrinkage and selection operator (LASSO). (A) Tuning parameter (λ) selection in the LASSO model was performed through 5-fold cross-validation based on minimum criteria. (B) The LASSO coefficient profiles of the radiomics features were analyzed, highlighting six resulting features with nonzero coefficients in the plot.

Figure 5

The radiomics nomogram was developed based on the radiomics score in the training cohort.

Figure 6

The AUC of the radiomics nomogram in the training cohort (A) and validation cohort (B).

Figure 7

Calibration curve of the radiomics nomogram. (A) Calibration curve of the nomogram in the training cohort showed a nonsignificant statistic (p = 0.782) in the Hosmer-Lemeshow test; (B) Calibration curve of the nomogram in the validation cohort displayed a nonsignificant statistic (p = 0.710) in the Hosmer-Lemeshow test.

Figure 8

Decision curve of the radiomics nomogram in the training cohort (A) and validation cohort (B). The decision curve demonstrated that if the threshold probability is within the range of 20% to 80%, the application of radiomics nomogram to differentiate NG from PTC adds more benefit than treating all or none of the patients.