Yandex B2B Tech, together with the School of Data Analysis and SPbSPMU, has created a neural network that helps doctors evaluate MRI scans of infants in a matter of minutes. Previously, MRI analysis took hours or even days.
The system is designed to identify signs of cerebral palsy and other disorders of the central nervous system in order to quickly select the optimal therapy.
The neural network automatically highlights the contours of the brain and calculates the ratio of gray and white matter with an accuracy of over 90%. The solution runs on the Yandex Cloud platform and is available to doctors free of charge.
To train the model, 1,500 anonymized images of infants from SPbSPMU and an open dataset from the MICCAI international competition were used. BIBSNet, ResNet, and U-Net neural networks were used.
Early diagnosis of cerebral palsy is extremely important: the disease occurs in 2–3 cases per 1,000 newborns, and timely treatment improves the prognosis for recovery. The new tool allows doctors to make decisions faster and increases the effectiveness of therapy.
Read related materials:
Rostec presented a new Russian exoskeleton for the arm
A new device for treating head injuries and ADHD has been developed in the Moscow region
Now on home
The service contains data on 45,000 fraudulent sites
Modernized engines may equip the Lada Azimut crossover
The price is 132 billion 265.8 million rubles
The manufacturer plans to strengthen its lineup of light commercial vehicles
The production of carbon fiber was organized in the shortest possible time
Electric vans will speed up the repair of urban transport infrastructure
Countries are working to synchronize regulations in the field of AI
The service's average daily audience is 55 million people
Stable Isomaterial Based on Metakaolin Has a Density Below 300 kg/m³
Re-identification quality improved twofold with new DynaMix method
Russians will be able to find out about debts online