Related Experiment Video
Updated: Jun 29, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Multimodal ultrasonography evaluation in thyroid nodule characterization: what is the ideal algorithm?
Başak Erdemli Gürsel1, Barış Çağlar2, Rıfat Özpar2
1Department of Radiology, Bursa Uludağ University Faculty of Medicine, Bursa. basakgursel@uludag.edu.tr.
Aims:
The aim of this study is to investigate the diagnostic performances of Ultrasonography (US), Shear-wave Elastography (SWE), and Superb Microvascular Imaging (SMI) findings in the diagnosis of malignant thyroid nodules (MTNs) and to determine the US algorithm with the best diagnostic performance.
Material And Methods:
Eighty-one nodules in 77 patients who had underwent multimodal US with biopsy results, were evaluated. Echogenicity, nodule components, contours, presence and type of calcification, and size were analyzed with US. Nodule stiffness and vascular index (VI) measurements were performed via SWE and SMI. The power of the US algorithm in predicting malignancy was evaluated.
Results:
Hypoechogenicity, irregular contour, aspect ratio (anteroposterior (AP)/transvers diameter) >1, and >43.9 kPa were the characteristicshad significant efficacy in the diagnosis of MTNs. Sensitivity, specificity, and AUC values were respectively 100%, 48.5%, and 0.742 for hypoechogenicity; 80%, 90.1%, and 0.855 for irregular contour; 60%, 71.2%, and 0.656 for aspect ratio >1; 60%, 72.7%, and 0.671 for >43.9 kPa; and 93.3%, 90.9%, and 0.921 for the US algorithm. VI did not show significant efficacy in diagnosis.
Conclusion:
Some B-mode and SWE findings showed sufficient efficacy in differentiating benign and malign nodules on their own. However, diagnostic accuracy increased significantly when the US algorithm was applied.
