Related Experiment Video
Updated: May 1, 2026
Combined Near-infrared Fluorescent Imaging and Micro-computed Tomography for Directly Visualizing Cerebral Thromboemboli
Published on: September 25, 2016
Radiomics model based on dual-energy CT can determine the source of thrombus in strokes with middle cerebral artery
Yuzhu Ma1, Yao Dai1, Ying Zhao1
1Department of Radiology, The Fourth Affiliated Hospital of Soochow University, Suzhou, 215124, China.
Insights
Dual-energy CT (DECT) radiomics models effectively predict stroke thrombus source. The NCCT+IOM model showed high accuracy, outperforming others and not significantly differing from combined clinical models.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence in Medicine
Background:
- Stroke etiology prediction is crucial for targeted treatment.
- Dual-energy CT (DECT) offers advanced imaging capabilities for thrombus characterization.
- Radiomics extracts quantitative features from medical images for predictive modeling.
Purpose of the Study:
- To develop and validate DECT-based radiomics models for predicting the etiologic cause of stroke.
- To compare the performance of different radiomics models using various CT image types.
Main Methods:
- Retrospective analysis of middle cerebral artery occlusion patients using non-contrast CT (NCCT) and DECT angiography (DECTA).
- Reconstruction of 70 keV virtual monoenergetic images and iodine overlay maps (IOM).
- Development of logistic regression radiomics models to predict cardioembolism (CE), including a combined model with clinical data.
Main Results:
- The NCCT+IOM radiomics model demonstrated superior performance (AUC=0.95 training, 0.92 testing) compared to other models.
- Smoking and NIHSS score were identified as independent predictors of CE.
- The combined model showed comparable performance to the NCCT+IOM model.
Conclusions:
- Radiomics models using NCCT and IOM images can accurately determine stroke thrombus source.
- These models offer a promising non-reliance on clinical information for etiologic prediction.
Purpose:
To develop thrombus radiomics models based on dual-energy CT (DECT) for predicting etiologic cause of stroke.
Methods:
We retrospectively enrolled patients with occlusion of the middle cerebral artery who underwent computed tomography (NCCT) and DECT angiography (DECTA). 70 keV virtual monoenergetic images (simulate conventional 120kVp CTA images) and iodine overlay maps (IOM) were reconstructed for analysis. Five logistic regression radiomics models for predicting cardioembolism (CE) were built based on the features extracted from NCCT, CTA and IOM images. From these, the best one was selected to integrate with clinical information for further construction of the combined model. The performance of the different models was evaluated and compared using ROC curve analysis, clinical decision curves (DCA), calibration curves and Delong test.
Results:
Among all the radiomic models, model NCCT+IOM performed the best, with AUC = 0.95 significantly higher than model NCCT, model CTA, model IOM and model NCCT+CTA in the training set (AUC = 0.88, 0.78, 0.90,0.87, respectively, P < 0.05), and AUC = 0.92 in the testing set, significantly higher than model CTA (AUC = 0.71, P < 0.05). Smoking and NIHSS score were independent predictors of CE (P < 0.05). The combined model performed similarly to the model NCCT+IOM, with no statistically significant difference in AUC either in the training or test sets. (0.96 vs. 0.95; 0.94 vs. 0.92, both P > 0.05).
Conclusion:
Radiomics models constructed based on NCCT and IOM images can effectively determine the source of thrombus in stroke without relying on clinical information.
