Researchers from the Center for Diagnostics and Telemedicine and mathematicians from Moscow State University have developed a new method for quality control of scanners. This will provide timely detection of MRI scanner malfunctions automatically. The report on the topic “MRI Quality Control Algorithm Based on Image Analysis Using Convolutional and Recurrent Neural Networks” were presented at the “IEEE 35th International Symposium on Computer Based Medical Systems”.
Today, Moscow radiologists use artificial algorithms in their routine practice. However, imaging diagnostics are developing and becoming more efficient. To automate the identification of machine service problems, scientists present a method for monitoring MRI, using clinical images and trained AI-based solutions developed at Moscow State University. This will allow faster identification of malfunctioning MRI scanner and reduce downtime and repair costs. The system still requires extra training and testing, but the results indicate the feasibility of implementation. In the future, such an approach could improve the quality of diagnostics in the capital.
Magnetic resonance imaging is a high precision, 3D imaging diagnostics of internal organs without harmful ionizing radiation. A new quality control method for scanners has been developed to avoid breakdowns and downtime. It is based on machine learning technology. Setting up AI requires sampling of MRI images from various scanners with an accurate quality control result. The algorithm is trained to distinguish between images from working and faulty devices. An experimental evaluation based on the data showed the advantage of the developed method over analogues in terms of accuracy.
This technology has a number of advantages. Firstly, it saves time of a radiographer, who needs to manually assess the quality of the scanner. This procedure requires special training and time. Quality control of the equipment should be carried out daily, at least weekly. Automatic image quality control can be performed 24/7. 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.
The Center for Diagnostics and Telemedicine also provides guidelines for designing MRI suites, methodological and information recommendations, as well as training.
Briefly on the Diagnostics and Telemedicine Center: Diagnostics and Telemedicine Center was established in 1996. It is a top scientific and telemedicine organization under the Moscow Health Department. It specializes in AI implementation in medicine, researches radiation diagnostics, manages departments in medical organizations, including the telemedicine approach.