Related Experiment Video
Updated: Jun 28, 2026
04:23
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Can quantitative diffusion-weighted MR imaging differentiate benign and malignant cold thyroid nodules? Initial
C Schueller-Weidekamm1, K Kaserer, G Schueller
1Department of Diagnostic Radiology, Medical University of Vienna, Vienna, Austria. claudia.schueller-weidekamm@meduniwien.ac.at
AJNR. American Journal of Neuroradiology
|October 24, 2008
Summary
Quantitative diffusion-weighted MRI (DWI) can distinguish between malignant and benign cold thyroid nodules. This imaging technique achieved 88% accuracy in identifying thyroid cancer, offering a promising non-invasive diagnostic tool.
Area of Science:
- Radiology
- Oncology
- Endocrinology
Background:
- Cold thyroid nodules require characterization due to a 20% malignancy rate.
- Accurate differentiation of cold thyroid nodules is crucial for patient management.
Purpose of the Study:
- To evaluate the effectiveness of quantitative diffusion-weighted magnetic resonance imaging (DWI) in distinguishing cold thyroid nodules.
- To assess the diagnostic performance of apparent diffusion coefficient (ADC) values in differentiating benign from malignant nodules.
Main Methods:
- Quantitative DWI was prospectively performed on 25 patients with cold nodules.
- Apparent diffusion coefficient (ADC) values were measured in cold nodules and normal thyroid parenchyma.
- Statistical analysis (Mann-Whitney U test) compared ADC values between benign and malignant nodules.
Main Results:
- Mean ADC values significantly differed between carcinoma, adenoma, and normal parenchyma (P < .05).
- Non-overlapping ADC value ranges were observed for carcinoma, adenoma, and normal parenchyma.
- An ADC threshold of 2.25 or higher yielded 88% accuracy, 85% sensitivity, and 100% specificity for malignancy.
Conclusions:
- Quantitative DWI is a feasible tool for differentiating thyroid carcinomas from adenomas.
- Further studies with larger patient cohorts are needed to validate these findings.
