Diagnostic Performance of Ultrasound Strain Elastography in Transverse and Longitudinal Views in Predicting Malignant Thyroid Nodules

Application of ultrasound elastography and radiomic for predicting central cervical lymph node metastasis in papillary thyroid microcarcinoma

Objective

This study aims to combine ultrasound (US) elastography (USE) and radiomic to predict central cervical lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC).

Methods

A total of 204 patients with 204 thyroid nodules who were confirmed with PTMC and treated in our hospital were enrolled and randomly assigned to the training set (n = 142) and the validation set (n = 62). US features, USE (gender, shape, echogenic foci, thyroid imaging reporting and data system (TIRADS) category, and elasticity score), and radiomic signature were employed to build three models. A nomogram was plotted for the combined model, and decision curve analysis was applied for clinical use.

Results

The combined model (USE and radiomic) showed optimal diagnostic performance in both training (AUC = 0.868) and validation sets (AUC = 0.857), outperforming other models.

Conclusion

The combined model based on USE and radiomic showed a superior performance in the prediction of CLNM of patients with PTMC, covering the shortage of low specificity of conventional US in detecting CLNM.

Development and Validation of a Nomogram Based on Multimodality Ultrasonography Images for Differentiating Malignant from Benign American College of Radiology Thyroid Imaging, Reporting and Data System (TI-RADS) 3-5 Thyroid Nodules

OBJECTIVE

The aim of the work described here was to develop and validate a predictive nomogram based on combined image features of gray-scale ultrasonography (US), elastosonography (ES) and contrast-enhanced US (CEUS) to differentiate malignant from benign American College of Radiology Thyroid Imaging, Reporting and Data System (ACR TI-RADS) 3-5 thyroid nodules.

METHODS

Among 2767 thyroid nodules scanned by CEUS in Xijing Hospital between April 2014 and November 2018, 669 nodules classified as ACR TI-RADS 3-5 were included, with confirmed diagnosis and ES examination. Four hundred fifty-five nodules were set as a training cohort and 214 as a validation cohort. Images were categorized as gray-scale US ACR TI-RADS 3, TI-RADS 4 and TI-RADS 5; ES patterns of ES-1 and ES-2; and CEUS patterns of either heterogeneous hypo-enhancement, concentric hypo-enhancement, homogeneous hyper-/iso-enhancement, no perfusion, hypo-enhancement with sharp margin, island-like enhancement or ring-like enhancement. On the basis of multivariate logistic regression analysis, a predictive nomogram model was developed and validated by receiver operating characteristic curve analysis.

RESULTS

In the training cohort, ACR TI-RADS 4 and 5, ES-2, heterogeneous hypo-enhancement, concentric hypo-enhancement and homogeneous hyper-/iso-enhancement were selected as predictors of malignancy by univariate logistic regression analysis. A predictive nomogram (combining indices of ACR TI-RADS, ES and CEUS) indicated excellent predictive ability for differentiating malignant from benign lesions in the training cohort: area under the receiver operating characteristic curve (AUC) = 0.93, 95% confidence interval (CI): 0.90-0.95. The prediction nomogram model was determined to have a sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 0.84, 0.88, 0.91 and 0.81. In the validation cohort, the AUC of the prediction nomogram model was significantly higher than those of the single modalities (p < 0.005) . The AUCs of the validation cohort were 0.93 (95% CI: 0.89-0.96) and 0.93 (95% CI: 0.89-0.97), respectively, for senior and junior radiologists. The prediction nomogram model has a sensitivity, specificity, PPV and NPV of 0.86, 0.87, 0.87 and 0.86.

CONCLUSION

A predictive nomogram model combining ACR TI-RADS, ES and CEUS exhibited potential clinical utility in differentiating malignant from benign ACR TI-RADS 3-5 thyroid nodules.

Real-time reliable semantic segmentation of thyroid nodules in ultrasound images

Objective.Low efficiency in medical image segmentation is a common issue that limits computer-aided diagnosis development. Due to the varying positions and sizes of nodules, it is not easy to accurately segment ultrasound images. This study aims to propose a segmentation model that maintains high efficiency while improving accuracy.Approach. We propose a novel layer that integrates the advantages of dense connectivity, dilated convolution, and factorized filters to maintain excellent efficiency while improving accuracy. Dense connectivity optimizes feature reuse, dilated convolution redesigns layers, and factorized convolution improves efficiency. Moreover, we propose a loss function optimization method from a pixel perspective to increase the network's accuracy further.Main results.Experiments on the Thyroid dataset show that our method achieves 81.70% intersection-over-union (IoU), 90.50% true positive rate (TPR), and 0.25% false positive rate (FPR). In terms of accuracy, our method outperforms the state-of-the-art methods, with twice faster inference and nearly 400 times fewer parameters. Meanwhile, in a test on an External Thyroid dataset, our method achieves 77.03% IoU, 82.10% TPR, and 0.16% FPR, demonstrating our proposed model's robustness.Significance.We propose a real-time semantic segmentation architecture for thyroid nodule segmentation in ultrasound images called fully convolution dense dilated network (FCDDN). Our method runs fast with a few parameters and is suitable for medical devices requiring real-time segmentation.

Diagnostic performance of artificial intelligence-based computer-aided diagnosis system in longitudinal and transverse ultrasonic views for differentiating thyroid nodules

OBJECTIVE

To evaluate the diagnostic performance of different ultrasound sections of thyroid nodule (TN) using computer-aided diagnosis system based on artificial intelligence (AI-CADS) in predicting thyroid malignancy.

MATERIALS AND METHODS

This is a retrospective study. From January 2019 to July 2019, patients with preoperative thyroid ultrasound data and postoperative pathological results were enrolled, which were divided into two groups: lower risk group (ACR TI-RADS 1, 2 and 3) and higher risk group (ACR TI-RADS 4 and 5). The malignant risk scores (MRS) of TNs were obtained from longitudinal and transverse sections using AI-CADS. The diagnostic performance of AI-CADS and the consistency of each US characteristic were evaluated between these sections. The receiver operating characteristic (ROC) curve and the Cohen κ-statistic were performed.

RESULTS

A total of 203 patients (45.61 ± 11.59 years, 163 female) with 221 TNs were enrolled. The area under the ROC curve (AUC) of criterion 3 [0.86 (95%CI: 0.80~0.91)] was lower than criterion 1 [0.94 (95%CI: 0.90~ 0.99)], 2 [0.93 (95%CI: 0.89~0.97)] and 4 [0.94 (95%CI: 0.90, 0.99)] significantly (P<0.001, P=0.01, P<0.001, respectively). In the higher risk group, the MRS of transverse section was higher than longitudinal section (P<0.001), and the agreement of extrathyroidal extension and shape was moderate and fair (κ =0.48, 0.31 respectively). The diagnostic agreement of other ultrasonic features was substantial or almost perfect (κ >0.60).

CONCLUSION

The diagnostic performance of computer-aided diagnosis system based on artificial intelligence (AI-CADS) in longitudinal and transverse ultrasonic views for differentiating thyroid nodules (TN) was different, which was higher in the transverse section. It was more dependent on the section for the AI-CADS diagnosis of suspected malignant TNs.

US-Elastography With Different Techniques for Thyroid Nodule Characterization: Systematic Review and Meta-analysis

Background

Thyroid nodules are frequent in adult population and thyroid cancer incidence has increased dramatically over the past three decades. The aim of this systematic review and meta-analysis was to evaluate the US-Elastosonography (USE) diagnostic performance in assessing the thyroid nodules malignancy risk.

Methods

PubMed and Embase databases were searched from January 2011 to July 2021. We extracted data from selected studies and calculated the overall diagnostic accuracy of qualitative USE, semi-quantitative USE and quantitative USE. Summary receiver operating characteristic (ROC) curve was elaborated to show the results. All statistical tests were performed using Metadisc and Medcal software package.

Results

Finally 72 studies with 13,505 patients and 14,015 thyroid nodules (33% malignant) undergoing elastography were included. The pooled sensitivity, specificity and AUC were 84%, 81%, and 0.89 respectively for qualitative USE; 83%, 80%, and 0.93 for semi-quantitative USE and 78%, 81% and 0.87, for quantitative USE. The qualitative and semiquantitative USE present very similar diagnostic accuracy values and both better than the quantitative USE.

Conclusions

USE is a useful imaging tool for thyroid nodule characterization. In accordance with recent guidelines and meta-analyses, the USE could be used daily in thyroid nodule malignancy risk stratification.

Systematic Review Registration

PROSPERO: CRD42021279257.

Impact of imaging cross-section on visualization of thyroid microvessels using ultrasound: Pilot study

Non-invasive, contrast-free microvascular imaging of human thyroids can be potentially beneficial in reducing the large number of benign biopsies of suspicious nodules. However, motion incurred by thyroid due to its proximity to the pulsating carotid artery significantly impacts the visualization of blood flow in small vessels. Singular value based spatiotemporal clutter filtering (SVD-STF) improves the performance of tissue rejection in the presence of motion. However, despite effective clutter filtering, motion in thyroid imaging can impact coherent integration of the Doppler ensemble and degrade the visualization of the underlying vasculature. Recently studies have demonstrated that motion correction using 2D normalized cross-correlation based speckle tracking can address this issue, however, only in-plane motion can be tracked and corrected. Given the natural anatomical orientation of the rigid trachea, thyroid and the pulsating carotid artery, we hypothesize that imaging of thyroid microvessels may be more reliable in the longitudinal view than in the transverse. Specifically, distal presence of rigid trachea can limit out-of-plane motion in the longitudinal view. We tested this hypothesis on 48 acquisitions obtained from 24 thyroid patients having at least one suspicious nodule. In each patient, ultrasound images of the thyroid were acquired in both longitudinal and transverse views. Compounded plane-wave imaging was used to acquire the ultrasound images at high frame-rate, which is important for contrast-free small vessel blood flow imaging. Thyroid motion was tracked using 2D normalized cross-correlation based speckle tracking. Tissue clutter was rejected using singular value decomposition based spatiotemporal clutter filtering. The clutter-filtered Doppler ensemble was motion corrected prior to slow-time power Doppler integration. Signal-to-noise and contrast-to-noise ratios were computed to assess the improvement in quality of the power Doppler images. Out-of-plane motion was detected by estimating normalized ensemble cross-correlation coefficient. The results demonstrated that motion associated with the thyroid due to the carotid artery was primarily in the lateral direction, which could be estimated and corrected using 2D speckle tracking. However, the motion in the transverse view displayed increased speckle decorrelation. The average ensemble cross-correlation coefficient of the thyroid ultrasound images were significantly higher (p < 0.05) in the longitudinal view than in the transverse view. The largest improvement in SNR and CNR of the estimated PD images upon motion correction was observed in the longitudinal view (12.95 ± 3.76 dB and 16.48 ± 4.6 dB) than in the transverse view (3.72 ± 0.894 dB and 6.217 ± 1.689 dB). These preliminary results show that motion encountered by the thyroid due to carotid pulsations can be effectively tracked and corrected in the longitudinal view relative to transverse, which is important for reliably visualizing the underlying blood flow.