Prediction of Follicular Thyroid Neoplasm and Malignancy of Follicular Thyroid Neoplasm Using Multiparametric MRI

Abstract

The study aims to evaluate multiparametric magnetic resonance imaging (MRI) for differentiating Follicular thyroid neoplasm (FTN) from non-FTN and malignant FTN (MFTN) from benign FTN (BFTN). We retrospectively analyzed 702 postoperatively confirmed thyroid nodules, and divided them into training (n = 482) and validation (n = 220) cohorts. The 133 FTNs were further split into BFTN (n = 116) and MFTN (n = 17) groups. Employing univariate and multivariate logistic regression, we identified independent predictors of FTN and MFTN, and subsequently develop a nomogram for FTN and a risk score system (RSS) for MFTN prediction. We assessed performance of nomogram through its discrimination, calibration, and clinical utility. The diagnostic performance of the RSS for MFTN was further compared with the performance of the Thyroid Imaging Reporting and Data System (TIRADS). The nomogram, integrating independent predictors, demonstrated robust discrimination and calibration in differentiating FTN from non-FTN in both training cohort (AUC = 0.947, Hosmer-Lemeshow P = 0.698) and validation cohort (AUC = 0.927, Hosmer-Lemeshow P = 0.088). Key risk factors for differentiating MFTN from BFTN included tumor size, restricted diffusion, and cystic degeneration. The AUC of the RSS for MFTN prediction was 0.902 (95% CI 0.798-0.971), outperforming five TIRADS with a sensitivity of 73.3%, specificity of 95.1%, accuracy of 92.4%, and positive and negative predictive values of 68.8% and 96.1%, respectively, at the optimal cutoff. MRI-based models demonstrate excellent diagnostic performance for preoperative predicting of FTN and MFTN, potentially guiding clinicians in optimizing therapeutic decision-making.

Keywords: Follicular neoplasm; Multiparametric MRI; Nomogram; Preoperative assessment; Thyroid.

Fig. 1

Study design and flowchart. Abbreviations n, number of lesions; n*, number of patients; MRI, Magnetic resonance imaging; FNA, fine needle aspiration; FTN, follicular thyroid neoplasm; non-FTN, non-follicular thyroid neoplasm

Fig. 2

Forest plot of independent predictors for FTN a and MFTN b in multivariate logistic regression analysis

Fig. 3

The nomogram for predicting the probability of FTN based on MRI features. When using the nomogram, draw a vertical line to the corresponding point on the axis for each variable. Then, a total score line displays the summed points for each variable. An individual probability of FTN is obtained by projecting the total score line onto the predicted probability bottom scale

Fig. 4

Performance and clinical utility of the nomogram for the discrimination of FTN and non-FTN. a ROC curve in training cohort (AUC: 0.947, 88% sensitivity and 92.4% specificity at the optimal cutoff value of 0.249); b Calibration curves in training cohort (Hosmer-Lemeshow test, P = 0.698); c Decision curves for the training cohort; d ROC curve in validation cohort (AUC: 0.927, 81.8% sensitivity and 92.5% specificity at the optimal cutoff value of 0.245); e Calibration curves in validation cohort (Hosmer-Lemeshow test, P = 0.088); f Decision curves for the validation cohort. ROC, receiver operating characteristic; AUC, area under the curve; FTN, follicular thyroid neoplasm

Fig. 5

A 39-year-old woman presented with a thyroid follicular adenoma larger than 4 cm in the left lobe. Axial T2-weighted image a shows a heterogeneous mass and the present of hyperintense on T2WI with enhancement (black arrow). Axial DWI b and ADC c images show a hyperintense mass without restricted diffusion. Axial contrast-enhanced MRI (early phase) d shows a hyperintense enhancing mass and irregular fissure that did not enhance (black arrow). Axial contrast-enhanced MRI (delay phase) e shows a relatively homogeneous enhanced lesion with pseudocapsule, and fissure that do not enhanced in the early phase enhanced gradually. Pathological section analysis (HE, ×1) f shows densely distributed small follicles and relatively loose follicular cells (long black arrow, HE, ×40)

Fig. 6

A 43-year-old man presented with a thyroid follicular carcinoma larger than 4 cm in the right lobe. Axial T2-weighted image a shows a heterogeneous mass and the present of hyperintense on T2WI with enhancement (black arrow). Axial DWI b and ADC c images show an area with restricted diffusion within the lesion (high signal on DWI and low signal on ADC, black arrow). Axial contrast-enhanced MRI (early phase) d shows a hyperintense enhancing mass and irregular fissure that did not enhance (black arrow). Axial contrast-enhanced MRI (delay phase) e shows a relatively homogeneous enhanced lesion with pseudocapsule (black arrow); fissure that do not enhanced in the early phase enhanced gradually, and the area of cystic degeneration is seen within the lesion. Pathological section analysis (HE, ×1) f shows densely distributed small follicles and follicular cells (long black arrow, HE, ×40)

Fig. 7

Internal validation of the risk score system (RSS) using the bootstrap sampling. The ROC curve was measured by bootstrapping for 1000 repetitions, and the AUC of the bootstrap stepwise model was showed