Predicting Malignancy of Thyroid Micronodules: Radiomics Analysis Based on Two Types of Ultrasound Elastography Images

RATIONALE AND OBJECTIVES

To develop a multimodal ultrasound radiomics nomogram for accurate classification of thyroid micronodules.

MATERIALS AND METHODS

A retrospective study including 181 thyroid micronodules within 179 patients was conducted. Radiomics features were extracted from strain elastography (SE), shear wave elastography (SWE) and B-mode ultrasound (BMUS) images. Minimum redundancy maximum relevance and least absolute shrinkage and selection operator algorithms were used to select malignancy-related features. BMUS, SE, and SWE radiomics scores (Rad-scores) were then constructed. Multivariable logistic regression was conducted using radiomics signatures along with clinical data, and a nomogram was ultimately established. The calibration, discriminative, and clinical usefulness were considered to evaluate its performance. A clinical prediction model was also built using independent clinical risk factors for comparison.

RESULTS

An aspect ratio ≥ 1, mean elasticity index, BMUS Rad-score, SE Rad-score, and SWE Rad-score were identified as the independent predictors for predicting malignancy of thyroid micronodules by multivariable logistic regression. The radiomics nomogram based on these characteristics showed favorable calibration and discriminative capabilities (AUCs: 0.903 and 0.881 for training and validation cohorts, respectively), all outperforming clinical prediction model (AUCs: 0.791 and 0.626, respectively). The decision curve analysis also confirmed clinical usefulness of the nomogram. The significant improvement of net reclassification index and integrated discriminatory improvement indicated that multimodal ultrasound radiomics signatures might work as new imaging markers for classifying thyroid micronodules.

CONCLUSION

The nomogram combining multimodal ultrasound radiomics features and clinical factors has the potential to be used for accurate diagnosis of thyroid micronodules in the clinic.

Diagnostic value of thyroid micronodules with high b-value diffusion weighted imaging: Comparative study with high-resolution ultrasound

PURPOSE

This study aims to compare the diagnostic performance of two imaging methods for thyroid nodules ≤1.0 cm and reduce unnecessary overdiagnosis.

METHODS

A retrospective study was conducted on 80 patients with pathologically confirmed solitary thyroid micronodules underwent both high-resolution ultrasound (HRUS) and High b-value (2000 s/mm²) diffusion weighted imaging (DWI). Intra- and interobserver agreement (Intraclass correlation coefficient) was followed by Kruskal-Wallis test to detect whether the quantitative apparent diffusion coefficient (ADC) and thyroid nodule subgroups were related. Cohen's kappa analysis was applied to assess the interobserver consistency of DWI and HRUS characteristics. The receiver operating characteristic curves were adopted for evaluating the diagnostic performance of thyroid malignancy. The sensitivity, specificity, and accuracy of the two imaging methods were compared using the McNemar's test and Kappa test.

RESULTS

A total of 80 patients were included, consisting of 43 malignant and 37 benign micronodules. The sensitivity, specificity and accuracy of DWI combined with rADC (ADCmin to ADCn ratio) for the diagnosis of thyroid micronodules were 83.7%, 89.2% and 86.3%, respectively. The area under the curve (AUC) was 0.91 (95% confidence interval [CI]: 0.84-0.97). The sensitivity, specificity and accuracy of HRUS diagnosis were 100%, 62.16% and 82.5%, respectively.

CONCLUSION

High b-value DWI is superior to HRUS for evaluating the diagnostic performance of solid thyroid micronodules. DWI and its ADC quantitative analysis could be added to the evaluation of thyroid micronodules to improve the specificity of diagnosis, reduce overdiagnosis and avoid unnecessary biopsies or surgeries.

The diagnostic value of elastography score and strain index for the evaluation of thyroid micronodules

Background/aim: In the general population, the frequency of thyroid micronodules is increasing, and the prevalence of malignancy is higher for such nodules. Ultrasonography findings of these nodules are neither specific nor sensitive. The aim of this study was to investigate the diagnostic value of elastography in patients with thyroid micronodules. Materials and methods: A total of 224 patients with thyroid micronodules were recruited in this prospective study. All patients underwent a thyroid fine-needle aspiration biopsy. Elastography scores (ESs) and strain indexes (SIs) were measured with real-time ultrasound elastography. Results: Malignant micronodules had higher ES and SI values than those of benign micronodules (P < 0.001). When ES was used to diagnose malignancy, scores of >3 showed sensitivity of 79.4% and specificity of 98.1%. The area under the curve (AUC) for ES was 0.888 (P < 0.001). The optimal SI cutoff value that differentiated benign from malignant micronodules was 3.06 (98% sensitivity; 91% specificity). The AUC for SI was 0.970 (P < 0.001). Conclusions: ES and SI are beneficial markers for detecting malignant thyroid micronodules. We showed that SI is better than ES when assessing the malignancy of thyroid micronodules.

Diagnostic value of elastosonography for thyroid microcarcinoma

OBJECTIVE

To assess the diagnostic value of elastosonography for thyroid microcarcinoma (TMC), particularly with regard to elasticity score (ES) and strain ratio (SR).

METHODS

Conventional ultrasound and elastosonography were performed for 487 thyroid micronodules before surgery. We set the histology as the reference standard. The ES and SR values, as well as their diagnostic threshold and efficiency, were compared and analyzed by the receiver-operating characteristic (ROC) curve. Additional comparisons between TMC patients with and without extracapsular extension were also performed.

RESULTS

Statistically significant differences (P<0.05) in both ES and SR values were detected among the TMC and benign groups. The area under the ROC curve of SR was significantly greater than that of ES (0.956 and 0.844, respectively; P<0.05). Using ES⩾3 and SR⩾3.65 as diagnostic threshold values, the diagnostic sensitivity, specificity, and accuracy of ES for differentiating benign and malignant nodules were 79.9%, 72.3%, and 80.5%, respectively, whereas those of SR were 86.6%, 85.3%, and 89.4%, respectively. The maximum diameter, microcalcification status, aspect ratio, bilateral cervical lymph node metastasis, and SR values of nodules with extracapsular extension (A1 subgroup) were greater than those of nodules without extracapsular extension (A2 subgroup).

CONCLUSIONS

Elasticity imaging technology not only can help differentiate between benign and malignant thyroid micronodules but also allow SR values to provide accurate and objective information on tissue hardness and to predict TMC extracapsular extension or even bilateral cervical lymph node metastasis.