Related Experiment Video
Updated: Aug 12, 2025
04:23
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
1.9K
Nomogram based on spectral CT quantitative parameters and typical radiological features for distinguishing benign
Zuhua Song1, Qian Li1, Dan Zhang1
1Department of Radiology, Chongqing General Hospital, No.118, Xingguang Avenue, Liangjiang New Area, Chongqing, 401147, China.
Summary
A new dual-layer spectral CT nomogram effectively distinguishes benign thyroid micro-nodules from thyroid microcarcinoma (TMC). This tool combines quantitative CT parameters with imaging features, offering improved diagnostic accuracy for TMC detection.
Area of Science:
- Radiology
- Oncology
- Medical Imaging
Background:
- Thyroid microcarcinoma (TMC) detection requires accurate differentiation from benign nodules.
- Dual-layer spectral computed tomography (DSCT) offers advanced quantitative imaging capabilities.
- Distinguishing benign micro-nodules from TMC remains a diagnostic challenge.
Purpose of the Study:
- To develop and validate a predictive nomogram for differentiating benign micro-nodules from TMC.
- To assess the combined diagnostic performance of DSCT quantitative parameters and radiological features.
Main Methods:
- Retrospective analysis of 342 thyroid micro-nodule cases (≤1 cm) using DSCT.
- Measurement of DSCT quantitative parameters (e.g., λHU, NIC, NZeff) and radiological features (micro-calcification, enhanced blurring).
- Development of a nomogram using logistic regression and evaluation via ROC curves and calibration plots.
Main Results:
- The DSCT parameter APλHU demonstrated significant diagnostic efficiency (AUC 0.829).
- The combined DSCT-Radiological nomogram achieved higher diagnostic performance (AUC 0.858, sensitivity 0.791, specificity 0.800).
- The nomogram showed good calibration and clinical utility based on decision curve analysis.
Conclusions:
- The DSCT-Radiological nomogram is a valid, noninvasive tool for predicting benign versus malignant thyroid micro-nodules.
- Incorporating DSCT quantitative parameters enhances diagnostic accuracy for TMC detection.
- This nomogram offers favorable predictive efficiency in clinical practice.
