- AI
- Molecular Imaging
- CT
- X-Ray
- Ultrasound
- MRI
- Facility Management
- Mammography
FDA Clears AI-Powered MRI Software for ARIA Detection in Patients with Alzheimer’s Disease
Icobrain.aria is reportedly the first AI software geared toward the detection and monitoring of amyloid-related imaging abnormalities (ARIAs) on brain MRI.
The Food and Drug Administration (FDA) has granted 510(k) clearance for icobrain.aria, an artificial intelligence (AI)-enabled software that may enhance the detection of amyloid-related imaging abnormalities (ARIAs) on brain MRI for patients being treated for Alzheimer’s disease.
Noting that ARIAs have been associated with recently approved disease-modifying agents for Alzheimer’s disease, Icometrix, the developer of icobrain.aria, said icobrain.aria is the first AI software dedicated to the diagnosis and monitoring of ARIAs in this patient population.
The images above reveal severe ARIA-E in a patient who presented with parenchymal edema. The AI-enabled software icobrain.aria, which was recently cleared by the FDA, demonstrated a 16 percent increase in sensitivity for ARIA-E and a 10 percent increase in sensitivity for ARIA-H, in a retrospective study published earlier this year in JAMA Network Open. (Images courtesy of JAMA Network Open.)
In a retrospective study published earlier this year in JAMA Network Open, icobrain.aria demonstrated a 16 percent increase in sensitivity for ARIA-E and a 10 percent increase in sensitivity for ARIA-H.
“New standardized tools are needed … to assist radiologists and treating clinicians in detecting and managing ARIA to optimize patient safety. I am excited that icobrain.aria has received FDA approval, clearing the way for wider use in clinical practice,” noted Stephen Salloway, M.D., the director of neurology and the Memory and Aging Program at Butler Hospital in Providence, R.I.
Study: AI Boosts Ultrasound AUC for Predicting Thyroid Malignancy Risk by 34 Percent Over TI-RADS
February 17th 2025In a study involving assessment of over 1,000 thyroid nodules, researchers found the machine learning model led to substantial increases in sensitivity and specificity for estimating the risk of thyroid malignancy over traditional TI-RADS and guidelines from the American Thyroid Association.
