An imaging algorithm reduced the number of CT angiography and CT perfusion studies performed on patients with aneurysmal subarachnoid hemorrhages, a form of stroke.
An imaging algorithm reduced the number of CT angiography and CT perfusion studies performed on patients with aneurysmal subarachnoid hemorrhages, a form of stroke. The study was performed by New York Presbyterian Hospital – Weill Cornell Medical Center researchers and included 60 patients.
The algorithm identifies the most appropriate points at which to detect vasospasm with CT angiography and CT perfusion imaging. A flow chart establishes imaging pathways and time frames.
With the new algorithm, the mean number of CT examinations per patient dropped from 7.8 to 5.8, a decrease of 25.6%, according to the investigators.
The number of CT perfusion exams per patient decreased 32.1% and overall cumulative radiation exposure decreased by 12.1%.
The results were published in the American Journal of Roentgenology (AJR 2010;195[1]:176-180).
Study Assesses Lung CT-Based AI Models for Predicting Interstitial Lung Abnormality
September 6th 2024A machine-learning-based model demonstrated an 87 percent area under the curve and a 90 percent specificity rate for predicting interstitial lung abnormality on CT scans, according to new research.