SAN MATEO, California, April 26, 2018 /PRNewswire/ --
Clinical study shows company's deep learning algorithms can identify bleeds, fractures and other critical trauma in head CT scans with more than 95% accuracy
Qure.ai (http://www.qure.ai), a healthcare AI startup, today launched a new AI-powered technology to accurately identify bleeds, fractures and other critical abnormalities in head CT scans. Qure.ai has also released the results of an unprecedented clinical validation study confirming its algorithms' near-radiologist performance on 21,000 patients and has made a dataset of almost 500 AI-analyzed head CT scans available for download.
A CT scan of the head is usually the first diagnostic test patients undergo if they have a head injury or symptoms suggesting stroke. The problem, however, is that radiologists might not be immediately available to read a scan or might have many scans pending. Prompt reading of the CT scan is critical for stroke patients, as every minute that goes by, brain cells die.
"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," said Prashant Warier, Co-Founder and CEO, Qure.ai. "This enables patient prioritization and the appropriate clinical intervention."
Qure.ai trained the new AI using a collection of 313,318 anonymized head CT scans, along with their corresponding clinical reports. Of these, 21,095 scans were then used to validate the AI's algorithms. Finally, the AI was clinically validated on 491 CT scans, with the results compared against a panel of three senior radiologists. The panel of radiologists included Norbert G. Campeau, M.D., a senior neuro-radiologist from the Mayo Clinic's Department of Radiology. The validation study found that Qure.ai's AI was more than 95% accurate in identifying abnormalities.
The results have been published today in a research paper on Cornell University's online distribution system for research, arXiv.org. The paper is titled "Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans." The Mayo Clinic's Dr. Campeau co-authored the paper with Qure.ai. Additional co-authors hailed from the CT & MRI Center, India and the Centre for Advanced Research in Imaging, Neurosciences and Genomics. Further details are available here: http://headctstudy.qure.ai.
"This is important new technology," said Dr. Campeau. "The strong results of the deep learning system support the feasibility for use of automated head CT scan interpretation as an adjunct to medical care. This improves the quality and consistency of radiologic interpretation."
In addition to the study, Qure.ai has made a dataset of 491 AI-interpreted head CT scans, as well as the corresponding interpretations from the three radiologists, publicly available for download. This dataset is from the Centre for Advanced Research in Imaging, Neurosciences and Genomics, and includes both out-patient and in-patient scans from 7 centers. To download the full dataset, visit: http://headctstudy.qure.ai.
"We are releasing these scans so that others can compare and build on the results we have achieved," added Warier. "We encourage others to explore the data, review our work, and consider possibilities for the future."
"We are delivering near-radiologist accurate AI to support radiologists, physicians and healthcare providers," said Sasank Chilamkurthy, AI Scientist, Qure.ai. "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."
Qure.ai's new solution can automatically generate abnormality reports. These automated reports are a first-to-market capability in the AI and radiology category, helping radiologists and hospitals prioritize care, make smarter and faster diagnoses and reduce costs.
To date, Qure.ai has delivered AI-powered chest, abdomen and musculoskeletal image interpretation technology. With today's launch, Qure.ai is launching capabilities for head and brain CT scans for the first-time.
Founded in 2016, Qure.ai is funded by Fractal Analytics, a global leader in artificial intelligence and analytics that powers decision-making in Fortune 500 companies.
For more information about Qure.ai, please visit, http://www.qure.ai.
Qure.ai's mission is to make healthcare affordable and accessible using the power of artificial intelligence. Qure.ai's deep neural networks can understand and interpret medical images with unprecedented accuracy and enable machines to perform routine diagnostics, thus improving healthcare outcomes and costs.
Qure.ai was founded in 2016, with funding from Fractal Analytics, and has a team comprising computer scientists, deep learning experts, medical practitioners and bioinformaticians.