Related Experiment Video
Updated: Aug 5, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Ultrasound Risk Stratification and Bethesda Cytology for Predicting Malignancy in Thyroid Nodules: A
Poonam Kujur1, Sunil Kumar Mahto1, Smita Kumari Gupta1
1Pathology, Rajendra Institute of Medical Sciences, Ranchi, IND.
Background:
Thyroid nodules are one of the most frequently seen endocrine conditions in clinical practice and a major challenge in diagnosis, as only a small proportion of them are malignant. The current study aimed to compare the American College of Radiology Thyroid Imaging Reporting and Data System (ACR-TIRADS) ultrasonographic classification with the Bethesda cytological category in thyroid nodules with histopathological diagnosis.
Methods:
Our study was conducted as a hospital-based cross-sectional observational analysis in the Departments of Pathology and Radiodiagnosis at Rajendra Institute of Medical Sciences (RIMS), Ranchi. A total of 50 consecutive patients fulfilling the eligibility criteria were included. Ultrasonographic examination was performed using ACR-TIRADS criteria, and fine needle aspiration cytology (FNAC) findings were interpreted according to The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC). Histopathological examination served as the reference standard.
Results:
In our study, the mean age was 33.76 ± 12.85 years, and females constituted 34 (68.0%) cases. TIRADS 3 nodules constituted the largest subgroup with 16 (32.0%) cases. Histopathological examination identified 29 (58.0%) benign lesions and 21 (42.0%) malignant lesions. Bethesda cytology demonstrated superior concordance with histopathology, with a specificity of 100% and excellent diagnostic accuracy with an area under the curve (AUC) of 0.81. In contrast, ACR-TIRADS showed poor discriminatory ability with an AUC of 0.51.
Conclusion:
Bethesda cytology showed superior concordance and diagnostic accuracy compared with ultrasonographic ACR-TIRADS classification in predicting malignant thyroid nodules. Combined radiological and cytological evaluation may improve diagnostic certainty and support appropriate surgical decision-making.
