Comparison of computed tomography features between follicular neoplasm and nodular hyperplasia

Differential Diagnosis of Malignant Thyroid Calcification Nodule Based on Computed Tomography Image Texture

Purpose: Calcification nodules in thyroid can be found in thyroid disease. Current clinical computed tomography systems can be used to detect calcification nodules. Our aim is to identify the nature of thyroid calcification nodule based on plain CT images. Method: Sixty-three patients (36 benign and 27 malignant nodules) found thyroid calcification nodules were retrospectively analyzed, together with computed tomography images and pathology finding. The regions of interest (ROI) of 6464 pixels containing calcification nodules were manually delineated by radiologists in CT plain images. We extracted thirty-one texture features from each ROI. And nineteen texture features were picked up after feature optimization by logistic regression analysis. All the texture features were normalized to [0, 1]. Four classification algorithms, including ensemble learning, support vector machine, K-nearest neighbor, decision tree, were used as classification algorithms to identity the benign and malignant nodule. Accuracy, PPV, NPV, SEN, and AUC were calculated to evaluate the performance of different classifiers. Results: Nineteen texture features were selected after feature optimization by logistic regression analysis (P <0.05). Both Ensemble Learning and Support Vector Machine achieved the highest accuracy of 97.1%. The PPV, NPV, SEN, and SPC are 96.9%, 97.4%, 98.4%, and 95.0%, respectively. The AUC was 1. Conclusion: Texture features extracted from calcification nodules could be used as biomarkers to identify benign or malignant thyroid calcification.

Could both intrinsic and extrinsic iodine be successfully suppressed on virtual non-contrast CT images for detecting thyroid calcification?

PURPOSE

Although virtual non-contrast (VNC) successfully removes iodinated contrast, uncertainty exists regarding the feasibility of VNC to suppress iodine for detecting thyroid calcification. Therefore, we evaluated whether both intrinsic and extrinsic iodine attenuation were suppressed on VNC images.

MATERIAL AND METHODS

We enrolled 128 patients (male: female 17:111; age 48.0 ± 10.4 years) who underwent dual-layer dual-energy CT (DL-DECT) examination before their thyroid cancer surgeries. Two additional sets of VNC (VNCu, VNCc) images were retrospectively generated from their true unenhanced (TUE) and true contrast-enhanced (TCE) series. We compared CT attenuation values measured on the VNCu and VNCc images by drawing identical regions of interest encompassing thyroid parenchyma, then subjectively determined the concordance of calcification.

RESULTS

Although CT attenuation discrepancies between the VNCu and VNCc were significant (2.0 ± 5.7HU, p < 0.001),61.7%, 89.1%, and 100.0% of all measurements were < 5HU, < 10HU, and < 15HU. Based on Bland-Altman analysis, the limits of agreement were - 9.2HU and 13.2HU, whereas the proportional differences were small for VNC images generated from both TUE and TCE images. There was no discordance between two VNC image sets in detecting thyroid calcification.

CONCLUSIONS

VNC technique could be a feasible method to suppress both intrinsic and extrinsically administered iodine for detecting thyroid calcification.