
Researchers have developed an AI-enhanced three-phase CT perfusion protocol that reduces radiation exposure by over 80% while accurately generating perfusion maps for stroke evaluation.
Key Details
- 1Traditional CT perfusion (CTP) uses continuous scanning, resulting in high radiation doses (~5260 mGy·cm) and workflow complexity.
- 2The new protocol samples only three phases and uses a GAN-based deep learning model to generate cerebral blood flow (CBF) and Tmax maps.
- 3The approach reduces patient radiation exposure by more than 80% compared to standard CTP methods.
- 4Internal validation demonstrated high fidelity of AI-generated blood flow maps, even with slight deviations in timing of image acquisition.
- 5The method preserves diagnostic accuracy essential for stroke management and is more robust to patient motion.
Why It Matters

Source
EurekAlert
Related News

AI-Enabled Hydrogel Patch Provides Long-Term High-Fidelity EEG and Attention Monitoring
Researchers unveil a reusable hydrogel patch with machine learning capabilities for high-fidelity EEG recording and attention assessment.

Sybil AI Model Accurately Predicts Lung Cancer Risk in Diverse Urban Populations
A new study validates the Sybil AI model for predicting lung cancer risk using low-dose CT in a predominantly Black cohort at an urban safety-net hospital.

AI and Imaging Reveal Atomic Order in 2D Nanomaterials
A multi-university team has uncovered how atomic order and disorder in 2D MXene nanomaterials can be predicted and tailored using AI, enabled by advanced imaging analysis.