Characteristics of malignant thyroid lesions on [18F] fluorodeoxyglucose (FDG)-Positron emission tomography (PET)/Computed tomography (CT)

Abstract

Objectives: To determine the imaging variables that can best differentiate malignant from benign thyroid lesions incidentally found on F-18 FDG PET/CT scans.

Methods: All F-18 FDG PET/CT studies starting from 2011 to end of 2016 were reviewed for incidental thyroid lesions or metabolic abnormalities. Only patients who were found to have FNAB or histopathology were included. Patients with known thyroid malignancy were excluded. Patients were analyzed for age, sex, SUVmax, non-enhanced CT tissue density in mean Hounsfield units (HU), uptake pattern (focal or diffuse) and gland morphology (MNG or diffuse). A control group of 15 patients with normal thyroid glands were used to assess the tissue density in HU for normal thyroid tissue. Sensitivity, specificity, PPV, NPV and accuracy to detect malignancy were calculated. Pearson Chi-square test was used to compare categorical variables while unpaired T-test and one way ANOVA test were used to compare means of continuous variables. ROC analysis was used to assess the best cut off points for SUVmax and HU. Regression analysis was used to detect the independent predictors for malignant lesions.

Results: Biopsy was unsatisfactory or indeterminate in 4/48 patients (8%). Only 44 patients (mean age 55.2 ± 14.7; 30 females (68 %)) with unequivocal FNAB or histopathology were included for further analysis. MNG was noted in 17/44 patients (38.6 %). Thyroid malignancy was found in 16/44 (36.4 %), benign thyroid lesions in 28/44 (63.6 %). Thyroid malignancies were 12 papillary, 1 follicular, 1 Hurthle cell neoplasm and 2 lymphoma. Benign lesions were 23 benign follicular or colloid nodules and 5 autoimmune thyroiditis. Focal FDG uptake pattern was more frequently associated with malignant lesions compared to benign lesions (75 % vs. 43 %; p = 0.039). The mean SUVmax and tissue density (HU) were both higher in malignant than benign lesions (8.8 ± 8.3 vs. 3.6 ± 1.9, p = 0.024) and (48.9 ± 12.7 vs. 32.9 ± 17.5, p = 0.003) respectively. The mean HU in the control group with normal thyroid tissue was 90 ± 7.4 significantly higher than in both the benign and malignant lesions (p < 0.001). ROC analysis revealed SUVmax cutoff of >4.7 and HU cutoff of >42 to best differentiate malignant from benign lesions. The sensitivity, specificity, PPV, NPV and accuracy to detect malignancy for SUVmax>4.7 were 68.8 %, 78.6 %, 64.8 %, 81.5 & 75.0 % (p = 0.002), for HU > 42 were 81.3.0 %, 75.0 %, 65.0 %, 87.5 & 77.3 % (p = 0.0003) and for both parameters combined were 87.5 %, 60.7 %, 56.0 %, 89.5 % and accuracy of 70.5 % (p = 0.002) respectively. Only HU > 42 and SUVmax>4.7 were independent predictors for malignancy with odd ratios 8.98 and 4.93 respectively.

Conclusion: A higher tissue density (HU > 42) and SUVmax>4.7 as well as tendency for focal uptake pattern are the most significant characteristics associated with malignant thyroid lesions occasionally detected on PET/CT.

Keywords: F-18 FDG PET/CT; Lesional Hounsfield units (HU); Lesional SUVmax; Thyroid incidentalomas; Thyroid malignancy.

Fig. 1

Flow chart of the included study population.

Fig. 2

Histopathology results for the entire study population. PTC = Papillary Thyroid Carcinoma; FTC = Follicular Thyroid Carcinoma.

Fig. 3

Box and Whisker graph for comparison of tissue density in mean HU between benign lesions, malignant lesions and controls with normal thyroid glands. All data plotted as dots with data connected at their means and error bars representing the 95 % CI.

Fig. 4

Comparison of ROC curves for SUVmax and mean HU as continuous variables (A), as well as SUVmax>4.7, HU > 42 and combined SUVmax>4.7 and HU > 42 as categorical (binary) variables (B). All curves with statistically significant AUC but comparison of AUC between different curves were not statistically significant.