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
The innovation could make stroke diagnosis safer and more accessible, significantly lowering radiation risks while maintaining diagnostic efficacy. Adopting this protocol may benefit vulnerable populations, improve workflow, and expand access to functional brain imaging in acute care.
Source
EurekAlert
Related News
•EurekAlert
NIH-Backed AI Model Predicts Cancer Survival Using Single-Cell Data
Researchers have developed scSurvival, a machine learning tool that uses single-cell tumor data to accurately predict cancer patient survival and identify high-risk cell populations.
•EurekAlert
Deep Learning Pathomics Platform Improves Immunotherapy Prediction in Lung Cancer
A deep learning pathomics platform accurately predicts immunotherapy response in metastatic NSCLC using routine pathology slides.
•EurekAlert
AI Pathology Model Outperforms PD-L1 in Predicting NSCLC Immunotherapy Response
MD Anderson's Path-IO machine learning platform accurately predicts immunotherapy responses in metastatic non-small cell lung cancer, surpassing current biomarker standards.