Prediction of thyroid nodule malignancy using thyroid imaging reporting and data system (TIRADS) and nodule size
Related Experiment Video
Updated: Dec 31, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Azin Shayganfar1, Peyman Hashemi1, Mahsa Masjedi Esfahani1
1Department of Radiology, Isfahan University of Medical Sciences, Isfahan, Iran.
Objectives:
Thyroid imaging reporting and data system (TIRADS) is a combination of ultrasonographic features developed to help physicians in predicting the malignancy risk of thyroid nodules based on sonographic characteristics. Thyroid nodule size is another factor in determining whether a nodule is malignant. The aim of this study was detecting the predictive value of TIRADS and nodule size based on Bethesda classification in prognostication of malignancy.
Methods:
This was a cross-sectional study of 239 patients with thyroid nodules. The patients underwent ultrasonography using TIRADS classification and FNA biopsy based on Bethesda categorization. The results were analyzed using SPSS with the cut off points and predictive values measured.
Results:
TIRADS ≥4 could detect malignant nodules with a sensitivity of 91.67% and specificity of 52.8%. An inverse relationship was observed between nodule size and malignancy risk and cutoff point of 12 mm was found for detecting malignant nodules.
Conclusions:
Thyroid nodules with TIRADS 4 and 5 and diameter lower than 12 mm, are highly suspicious for malignancy and should be considered as indications for fine needle aspiration biopsy.
Advances In Knowledge:
The study suggests TIRADS and thyroid nodule size as sensitive predictors of malignancy.
