The technology will help to accurately identify bleeds, fractures and other critical abnormalities in head CT scans.
Qure.ai noted that the clinical validation study confirmed its algorithms' near-radiologist performance on 21,000 patients and preserved dataset of near 500 AI-analyzed head CT scans.
The person with head injury or symptoms suggesting stroke will first undergo CT scan of the head. Accurate reading of the CT scan is crucial for stroke patients, as every minute that passes by, brain cells will die.
Qure.ai co-founder and CEO Prashant Warier said: "Qure.ai's new head CT scan technology rapidly screens scans in under 10 seconds to detect, localize and quantify abnormalities, as well as assess their severity.”
The company developed new AI by using a collection of 313,318 anonymized head CT scans along with their corresponding clinical reports.
Qure.ai has used 21,095 scans for the validation of AI's algorithms. Lastly, the AI was clinically validated on 491 CT scans, where the results were compared by a panel of three senior radiologists.
The firm has made a dataset of 491 AI-interpreted head CT scans, in addition to the study. The dataset is from the Centre for Advanced Research in Imaging, Neurosciences and Genomics, and comprises both out-patient and in-patient scans from seven centers.
The new AI-powered technology can automatically generate abnormality reports, which will help radiologists and hospitals to efficiently carry out diagnoses and reduce costs.
Qure.ai already provides AI-powered chest, abdomen and musculoskeletal image interpretation technology.
Qure.ai. AI scientist Sasank Chilamkurthy said: “Our deep learning algorithms can accurately detect and highlight head CT scan abnormalities, reducing the chances of missing a diagnosis.
“Our technology can also localize the brain regions affected and quantify the bleed regions in a fully-automated report."
Image: Qure.ai’s new AI-powered technology will identify abnormalities in head CT scans. Photo: courtesy of Qure.ai.
