MD+DI Online is part of the Informa Markets Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Intracranial Hemorrhage Detection Software Receives FDA Clearance

Intracranial Hemorrhage Detection Software Receives FDA Clearance
Product representations of the Accipio ICH detection software.
Artificial intelligence–powered software prioritizes the assessment of computed tomography cases that may have indications of brain bleed.

“AI and machine learning are going to transform healthcare, as they have virtually every other industry they have touched,” said Gene Saragnese, chairman and CEO of MaxQ AI in an interview with MD+DI. “Our world is surrounded by algorithms that present information, but one place it’s been lacking is healthcare.”

MaxQ AI is doing its best to remedy that deficiency, starting with software that can detect intracranial hemorrhage (ICH). The company’s recently FDA-cleared Accipio Ix is used with noncontrast computed tomography (CT). It can be natively integrated into CT machines and Picture Archiving and Communication Systems (PACS), using the imaging industry standard DICOM, installed both on premise and cloud capable.

When a patient comes into the emergency room with a head injury or symptoms of a stroke, one of the first things a physician wants to find out is if there is blood present in the brain, said Saragnese. But ICH can be hard to see on CT, as they can be very small and subtle. “So our software takes a noncontrast CT and processes it in the background using an algorithm,” he explained. “It identifies a patient who has potential intracranial hemorrhaging, and it highlights that patient is to be prioritized, so that person could be moved higher in the list to be examined.”

The application provides an answer within three to five minutes once the CT is done. The physician is not required to initiate the analysis—it is done automatically.

Accipio Ix is machine–learning based and is “literally able to look at the image, identify objects within that image, and then assess them,” explained Saragnese. “For every object it finds, it applies and calculates about 3000 to 4000 characteristics of that object and, using those 3000 to 4000 different attributes, it can figure out whether or not that image is an intracranial hemorrhage,” he said.

Two future versions of the software are in the development stages and have been granted FDA breakthrough status. “One is an application that can annotate the image and say, here it is,” said Saragnese, speaking about ICH. The third is the series is an application that rules out the presence of a hemorrhage.

“There are 13,000 hospitals in the United States and CE mark countries,” said Saragnese. “If you can just divert one patient per hospital per year, from long-term care to wellness, due to intervention, that’s a two-billion-dollar savings, and 13,000 lives you return to productive life spans, to their homes, to their families. And that’s the opportunity, that’s what motivates us as a company, as a team—that promise and that capability.”

Accipio Ix is being rolled out in both Europe and the United States. Saragnese expects the platform to be in commercial use by the first quarter of 2019.

TAGS: News
Hide comments


  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.