On-device AI algorithms pinpoint suspected pneumothorax, alerting radiologists sooner.
CHICAGO - Radiologists now have an artificial intelligence (AI) tool that can help them identify critical pneumothorax cases with X-ray.
GE Healthcare displayed its Critical Care Suite, a collection of on-device AI algorithms that is embedded on the company’s Optima XR240amc mobile X-ray machine, at this year’s annual meeting of the Radiological Society of North America. This collection, powered by GE Healthcare’s secure intelligent platform Edison, is an industry-first product. In addition, it also includes a first-of-its-kind AI quality check, as well as workflow improvement features that flag acquisition errors so technologists can correct them before submitting the images to the radiologist.
Critical Care Suite received approval from the U.S. Food & Drug Administration in September. It is designed for use in the operating suite, the emergency department, and the intensive care unit.
Currently, more than 60 percent of chest X-rays are marked “STAT,” leading to a potential reading wait time of up to eight hours. In that time, a patient could leave the hospital or experience negative outcomes. According to company information, however, the Critical Care Suite analyzes images and pinpoints suspected pneumothorax cases within seconds of acquisition.
When a suspicious image occurs, the system not only sends the image to the PACS, accompanied by a pneumothorax alert, but it also informs the technologist of the finding so he or she can prepare for any follow-up from the radiologist. This push notification is designed to give these images priority.
Critical Care Suite includes four AI algorithms designed to streamline image acquisition, giving the technologist the opportunity to reject or reprocess images at the patient’s bedside prior to sending them to the PACS for radiologist review.
Intelligent Auto Rotate: This feature eliminates the need for technologists to actively click to rotate chest images. On average, GE Healthcare representatives said, this algorithm can save more than 70,000 manual clicks -- the equivalent to 20 work hours -- annually in a medium-to-large size hospital.
Intelligent Field-of-View: Technologists can use this algorithm to ensure they’ve captured everything in the image necessary for the most comprehensive exam. Using this feature can reduce the likelihood that a radiologist will ask for additional images of other areas of anatomy.
Intelligent Protocol Check: This algorithm can alert technologists if they’ve selected a protocol that doesn’t match the images captured. For example, if he or she chooses an abdominal protocol, but positions the X-Ray to capture chest images, this feature can identify the error, giving the technologist the opportunity to fix it.
X-Ray Quality Application: Designed to improve efficiency through automated data gathering, this feature can identify and analyze the root causes of rejected X-Ray images, potentially reducing unnecessary patient radiation exposure or any operational efficiencies, such as decreased throughput or repeat scans.
Because the Optima XR240amc is equipped with badge log-in, this algorithm can also gather information about technologist performance across machines and compile it into a dashboard. Healthcare providers can use the accumulated information to identify potential targeted improvement training efforts.
Can AI Facilitate Effective Triage for Supplemental Breast MRI After Negative Mammography Screening?
July 10th 2024The AISmartDensity software facilitated a cancer detection rate (CDR) with breast MRI that was nearly four times higher than the CDR previously reported in trials involving traditional breast density assessment.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.
Can AI Facilitate Improved Dual-Energy X-Ray Screening for Patients at High Risk of Osteoporosis?
June 28th 2024Out of 315 patients identified by artificial intelligence (AI) as being at high risk for osteoporosis, subsequent screening with dual-energy X-ray absorptiometry (DXA) in a randomized controlled trial revealed new-onset osteoporosis in 237 patients.
FDA Clears Pocket-Sized ECG System and AI Technology for Detection of Cardiac Conditions
June 27th 2024Using a reduced leadset and deep neural network algorithms trained on more than 175 million electrocardiograms, the KAI 12L technology reportedly detects up to 35 cardiac determinations, including acute myocardial infarction.