Related Experiment Video
Updated: Sep 21, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Toward Reduction in False-Positive Thyroid Nodule Biopsies with a Deep Learning-based Risk Stratification System
Rikiya Yamashita1, Tara Kapoor1, Minhaj Nur Alam1
1Departments of Biomedical Data Science (R.Y., T.K., M.N.A., A.G., M.U.A., E.A., N.D.S., H.S., D.L.R.) and Radiology (S.A.S., A.L.W., N.M., D.G., V.B., D.L.R., T.S.D.), Stanford University School of Medicine, 300 Pasteur Dr, Stanford, CA 94305.
Purpose:
To develop a deep learning-based risk stratification system for thyroid nodules using US cine images.
Materials And Methods:
In this retrospective study, 192 biopsy-confirmed thyroid nodules (175 benign, 17 malignant) in 167 unique patients (mean age, 56 years ± 16 [SD], 137 women) undergoing cine US between April 2017 and May 2018 with American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS)-structured radiology reports were evaluated. A deep learning-based system that exploits the cine images obtained during three-dimensional volumetric thyroid scans and outputs malignancy risk was developed and compared, using fivefold cross-validation, against a two-dimensional (2D) deep learning-based model (Static-2DCNN), a radiomics-based model using cine images (Cine-Radiomics), and the ACR TI-RADS level, with histopathologic diagnosis as ground truth. The system was used to revise the ACR TI-RADS recommendation, and its diagnostic performance was compared against the original ACR TI-RADS.
Results:
The system achieved higher average area under the receiver operating characteristic curve (AUC, 0.88) than Static-2DCNN (0.72, P = .03) and tended toward higher average AUC than Cine-Radiomics (0.78, P = .16) and ACR TI-RADS level (0.80, P = .21). The system downgraded recommendations for 92 benign and two malignant nodules and upgraded none. The revised recommendation achieved higher specificity (139 of 175, 79.4%) than the original ACR TI-RADS (47 of 175, 26.9%; P < .001), with no difference in sensitivity (12 of 17, 71% and 14 of 17, 82%, respectively; P = .63).
Conclusion:
The risk stratification system using US cine images had higher diagnostic performance than prior models and improved specificity of ACR TI-RADS when used to revise ACR TI-RADS recommendation.Keywords: Neural Networks, US, Abdomen/GI, Head/Neck, Thyroid, Computer Applications-3D, Oncology, Diagnosis, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2022.
