GE Healthcare said the US Food and Drug Administration has cleared its collection of algorithms on mobile X-ray devices.
The company's Critical Care Suite, a collection of AI algorithms, is designed to prioritize critical cases for pneumothorax, a type of collapsed lung. The algorithms prioritizes and offer automated quality checks to detect errors before they go to radiologists to review.
GE Healthcare's algorithms, which run on GE Healthcare's Edison platform, were developed with UC San Francisco. If successful, the algorithms should fast track critical cases with time savings of up to 8 hours. The Edison platform includes a series of applications, smart devices and services for developers to create algorithms quickly, assimilate data and use analytics.
AI and machine learning is expected to play a big role in radiology and medical imaging as algorithms speed up the review process. GE Healthcare is looking to embed AI in its imaging hardware, notably the Optima XR240amx system.
Recent medical imaging and AI advances include:
- LG CNS, Lunit to apply AI, cloud into X-Ray analysis
- Researchers find crowdsourcing, AI go together in battle vs. lung cancer
- Samsung applies AI to medical imaging
- Facebook, NYU aim to use AI to speed up MRI scans
- Medical imaging at the 'speed of light': Nvidia's Clara supercomputer
Here's how GE Healthcare's algorithms work:
- A patient image scanned on a device with GE Healthcare's Critical Care Suite is automatically searched for pneumothorax.
- If pneumothorax is suspected, an alert with the original chest X-ray, is sent to the radiologist to review.
- That technologist would also receive an on-device notification to highlight prioritized cases.
- Algorithms would then analyze and flag protocol and field of view errors and auto rotate images on device.
GE Healthcare said its algorithms on device are designed to work without dependency on connectivity or transfer speeds.
- Enterprise AI in 2019: What you need to know
- Survey: Tech leaders cautiously approach artificial intelligence and machine learning projects
- Free PDF download: Managing AI and ML in the enterprise
- Enterprise AI and machine learning: Comparing the companies and applications
- The true costs and ROI of implementing AI in the enterprise
- Machine learning and information architecture: Success factors