Value of Contrast-Enhanced Ultrasound in Mummified Thyroid Nodules

Chen, Sijie; Tang, Kui; Gong, Yi; Ye, Fei; Liao, Liyan; Li, Xiaodu; Zhang, Qi; Xu, Yan; Zhang, Rongsen; Niu, Chengcheng

doi:10.3389/fendo.2022.850698

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, some hypoechoic Hashimoto nodules with blurred margins can be classified as C-TIRADS 4 ( 8 ). and mummified nodules with internal necrotic components may also exhibit marked hypoechogenicity ( 9 ). Distinguishing these from malignant nodules poses challenges, leading to the low specificity of 2D-US and warranting fine needle aspiration (FNA), an invasive procedure ( 2 ).…”

Section: Introductionmentioning

confidence: 99%

Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames

Chen,

Zhang,

Zhu

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

ObjectivesTo apply machine learning to extract radiomics features from thyroid two-dimensional ultrasound (2D-US) combined with contrast-enhanced ultrasound (CEUS) images to classify and predict benign and malignant thyroid nodules, classified according to the Chinese version of the thyroid imaging reporting and data system (C-TIRADS) as category 4.Materials and methodsThis retrospective study included 313 pathologically diagnosed thyroid nodules (203 malignant and 110 benign). Two 2D-US images and five CEUS key frames (“2nd second after the arrival time” frame, “time to peak” frame, “2nd second after peak” frame, “first-flash” frame, and “second-flash” frame) were selected to manually label the region of interest using the “Labelme” tool. A total of 7 images of each nodule and their annotates were imported into the Darwin Research Platform for radiomics analysis. The datasets were randomly split into training and test cohorts in a 9:1 ratio. Six classifiers, namely, support vector machine, logistic regression, decision tree, random forest (RF), gradient boosting decision tree and extreme gradient boosting, were used to construct and test the models. Performance was evaluated using a receiver operating characteristic curve analysis. The area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy (ACC), and F1-score were calculated. One junior radiologist and one senior radiologist reviewed the 2D-US image and CEUS videos of each nodule and made a diagnosis. We then compared their AUC and ACC with those of our best model.ResultsThe AUC of the diagnosis of US, CEUS and US combined CEUS by junior radiologist and senior radiologist were 0.755, 0.750, 0.784, 0.800, 0.873, 0.890, respectively. The RF classifier performed better than the other five, with an AUC of 1 for the training cohort and 0.94 (95% confidence interval 0.88–1) for the test cohort. The sensitivity, specificity, accuracy, PPV, NPV, and F1-score of the RF model in the test cohort were 0.82, 0.93, 0.90, 0.85, 0.92, and 0.84, respectively. The RF model with 2D-US combined with CEUS key frames achieved equivalent performance as the senior radiologist (AUC: 0.94 vs. 0.92, P = 0.798; ACC: 0.90 vs. 0.92) and outperformed the junior radiologist (AUC: 0.94 vs. 0.80, P = 0.039, ACC: 0.90 vs. 0.81) in the test cohort.ConclusionsOur model, based on 2D-US and CEUS key frames radiomics features, had good diagnostic efficacy for thyroid nodules, which are classified as C-TIRADS 4. It shows promising potential in assisting less experienced junior radiologists.

show abstract

Section: Introductionmentioning

confidence: 99%

Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames

Chen,

Zhang,

Zhu

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…Previous studies found that it was difficult to differentiate the microvasculature within lesions using color Doppler flow imaging (CDFI) and power Doppler imaging (PDI) ( 15 ). Although contrast-enhanced US (CEUS) can be used to distinguish MTNs and PTCs, it is relatively invasive and the contrast agents may cause allergic reactions ( 16 ). Superb microvascular imaging (SMI) is an innovative microvascular US imaging technique that can separate low-speed flow signals from motion artifacts by multidimensional filtering ( 17 ).…”

Section: Introductionmentioning

confidence: 99%

Diagnostic performance of ACR-TIRADS combined with superb microvascular imaging for differential diagnosis of mummified thyroid nodules and papillary thyroid carcinomas

Tian,

Liang,

Lin

et al. 2024

Endocrine Connections

View full text Add to dashboard Cite

Objective: To investigate the ability of superb microvascular imaging (SMI) to improve the differential diagnosis of mummified thyroid nodules (MTNs) and papillary thyroid carcinomas (PTCs) using the 2017 American College of Radiology Thyroid Imaging Reporting and Data System (ACR-TIRADS). Materials and methods: We enrolled 110 cases of MTNs and 110 cases of PTCs confirmed by fine-needle aspiration (FNA) or surgery. Conventional ultrasound (US) and SMI were analyzed for all nodules. Thyroid nodules were initially categorized by ACR-TIRADS and ACR-TIRADS combined with SMI (SMI-TIRADS). We compared the diagnostic performances of ACR-TIRADS and SMI-TIRADS by receiver operating characteristic curve, sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV). Results: US-detected margin, shape, and echogenic foci differed between MTNs and PTCs (P<0.05). The SMI blood-flow grade was greater in PTCs compared with MTNs (c2=158.78, P<0.05). There was no significant difference in ACR-TIRADS indicators between MTNs and PTCs (c2=1.585, P=0.453); reclassification by SMI-TIRADS showed significant differences between the groups (c2=129.521, P<0.001). The area under the curve was lower for ACR-TIRADS compared with SMI-TIRADS (0.517 vs 0.887, P<0.05). SMI-TIRADS had higher diagnostic value for distinguishing MTNs and PTCs than ACR-TIRADS (sensitivity: 91.82% vs 74.55%, P<0.05; specificity: 84.55% vs 21.82%, P<0.05; accuracy: 88.18% vs 48.18%, P<0.05; PPV: 85.59% vs 48.81%, P<0.05; NPV: 91.18% vs 46.15%, P<0.05). Conclusion: The detection of micrangium and large vessels in thyroid nodules by SMI resulted in high diagnostic specificity and sensitivity. ACR-TIRADS combined with SMI could effectively distinguish between MTNs and PTCs, to avoid unnecessary FNA or surgery.

show abstract

Deep learning to assist composition classification and thyroid solid nodule diagnosis: a multicenter diagnostic study

Chen,

Jiang,

Yao

et al. 2023

Eur Radiol

View full text Add to dashboard Cite

Value of Contrast-Enhanced Ultrasound in Mummified Thyroid Nodules

Cited by 3 publications

References 19 publications

Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames

Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames

Diagnostic performance of ACR-TIRADS combined with superb microvascular imaging for differential diagnosis of mummified thyroid nodules and papillary thyroid carcinomas

Deep learning to assist composition classification and thyroid solid nodule diagnosis: a multicenter diagnostic study

Contact Info

Product

Resources

About