| Title:
|
An AI Based Screening Tool for Detection of Cerebral Venous Thrombosis on Non-Contrast Brain CT
|
| Author(s):
|
1
|
| Subject:
|
Artificial Intelligence and Brain Mapping
|
|
|
|
Presenter Author:
|
|
| Name:
|
Ali Namjoomoghadam
|
|
|
|
Author:
|
|
| Name 1:
|
Ali Namjoomoghadam - Presenter
|
| Affiliation 1:
|
Clinical Neurology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
|
|
|
| Name 2:
|
Ali Mobaien
|
| Affiliation 2:
|
AI Clinical Lab and Biological Data Bank, Shiraz University of Medical Sciences, Shiraz, Iran
|
|
|
| Name 3:
|
Zahra Bayat
|
| Affiliation 3:
|
Emergency Medicine Department, Shiraz University of Medical Sciences, Shiraz, Iran
|
|
|
| Name 4:
|
Saba Nouri
|
| Affiliation 4:
|
Clinical Neurology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
|
|
|
| Name 5:
|
Nahid Abolpour
|
| Affiliation 5:
|
AI Clinical Lab and Biological Data Bank, Shiraz University of Medical Sciences, Shiraz, Iran
|
|
|
| Name 6:
|
Etrat Hooshmandi
|
| Affiliation 6:
|
Clinical Neurology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
|
|
|
| Name 7:
|
Mehrdad Sharifi
|
| Affiliation 7:
|
Emergency Medicine Department, Shiraz University of Medical Sciences, Shiraz, Iran
|
|
|
| Name 8:
|
Afshin Borhani-Haghighi - Corresponding
|
| Affiliation 8:
|
Clinical Neurology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
|
|
|
| Name 9:
|
|
| Affiliation 9:
|
|
|
|
| Name 10:
|
|
| Affiliation 10:
|
|
|
|
Abstract
|
Original Research
|
|
introduction :
|
While non-contrast computed tomography (NCCT) is the primary imaging modality in emergency settings, it has a low sensitivity for detection of Cerebral Venous Thrombosis (CVT). This study aims to develop an Artificial Intelligence (AI) tool to screen for CVT on routine NCCT scans.
|
|
Methods:
|
We used a retrospectively collected dataset of 692 patients, including 258 with CVT from Iran Cerebral Venous Thrombosis Registry (ICVTR) (code: 9001013381) and 434 controls. NCCT images were processed using the pre-trained CT-Foundation model to generate high-dimensional embeddings. These embeddings were used to train several machine learning classifiers: Support Vector Machine (SVM) with linear, polynomial, and RBF kernels, Logistic Regression, Random Forest, an Artificial Neural Network (ANN), and a soft-voting Ensemble model. Model performance was assessed using a 10-fold cross-validation protocol.
|
|
Results:
|
The Random Forest model achieved the highest specificity of 0.856 ± 0.050, excelling at identifying non-CVT cases. Conversely, the Ensemble model yielded the highest sensitivity of 0.614 ± 0.087. The SVM with a linear kernel provided the best overall discriminative ability, with the highest AUC of 0.718 ± 0.053. No single model demonstrated superiority across all metrics, reflecting the inherent challenge of detecting CVT on NCCT.
|
|
Conclusion:
|
Our findings demonstrate the feasibility of using an AI-based model to detect CVT on non-contrast CT scans. While not yet a replacement for expert radiological interpretation, this approach serves as a promising automated screening tool. It has the potential to reduce diagnostic delays and improve patient outcomes by flagging suspicious cases in emergency workflows.
|
| Attachment:
|
|
| Keywords:
|
Cerebral Venous Thrombosis, Artificial Intelligence, Computed Tomography, Machine Learning, Neuroimaging.
|
| Key message:
|
|
| Do you want your abstract to be indexed, if this is selected as one of the top 100
articles?
|
