Related Experiment Video
Updated: Nov 1, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Prediction of thyroid nodule histopathology by expert ultrasound evaluation
Olav Inge Håskjold1, Henrik Stenestø Foshaug2, Therese Benedikte Iversen3
1Department of Breast and Endocrine Surgery, University Hospital of North Norway, Tromsø, Norway.
Objective:
The basis of thyroid nodule diagnostics is ultrasound-guided fine needle biopsy with cytological evaluation (FNC) if ultrasound appearance is not clearly benign. The aim of this study was to investigate the predictive potential of dedicated, expert high-resolution ultrasound, to see if histopathological entities of thyroid nodules can be diagnosed without invasive FNC biopsies.
Design:
Prospective case-cohort study.
Methods:
187 patients with 221 thyroid nodules were examined with ultrasound and prospectively assigned to the expected histopathological diagnosis: colloid nodule, adenomatoid colloid nodule, follicular adenoma, follicular carcinoma, follicular variant of papillary thyroid carcinoma, papillary thyroid carcinoma, or other thyroid cancer. In 101 of these, we later obtained histopathological reports for comparison.
Results:
Overall accuracy for classification into discrete histopathological categories by expert ultrasound was 71.3% and Cohen's Kappa was 0.62. The sensitivity and specificity for detecting malignancy were 97.3% and 78.1%. The diagnostic accuracy for malignancy was 85.1%. ACR-TIRADS scores for the same nodules had a sensitivity of 97.3%, specificity of 26.6%, and accuracy of 52.5%.
Conclusion:
Dedicated expert high-resolution ultrasound without FNC can reliably distinguish benign vs malignant nodules, but also differentiate between several histopathological entities in thyroid nodules. There is potential for a reduction in the number of invasive FNC biopsies and diagnostic operations.
