Researchers from the Center for Diagnostics and Telemedicine and Moscow State University have developed an artificial intelligence (AI) technique for quality control of MRI scanners. They promoted the method at the IEEE 35th International Symposium on Computer Based Medical Systems.
The researchers said the algorithm uses clinical images for training and allows for faster identification of malfunctioning MRI scanners. It is trained to distinguish between images from working and faulty devices.
The team added that this method helps reduce downtime and repair costs and that automated quality control can be done 24/7 as opposed to waiting on technicians to perform quality control inspections. While the system still requires extra training and testing, the team emphasized that the method is easy to implement.
"Quality control of the equipment should be carried out daily, at least weekly," the group noted in a statement. "The analysis of one 3D-image takes less than a second, so after the analysis the system will immediately flag 'suspicious' images. Staff will be able to analyze the information received and, if necessary, call a technical team."