Yandex B2B Tech, together with the School of Data Analysis and SPbSPMU, has created a neural network that helps doctors assess 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.
1,500 anonymized infant images from SPbSPMU and an open dataset from the MICCAI international competition were used to train the model. 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:
«Ростех» 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 reason for indexation may be inflation, an increase in VAT, and rising production costs
The Ministry of Industry and Trade believes that the increase in the levy will not affect responsible manufacturers
The crew accelerated the aircraft to 580 km/h instead of the cruising speed of 450 km/h
Ship equipment comes to Russia from China at inflated prices
Almaz-Antey and the Belarusian Ministry of Defense signed a contract for equipment maintenance
The complex's computing resources allow for the competent distribution of targets between launchers
Among the spacecraft are Aist-2T No. 1 and No. 2
Deputy Prime Minister Novak announced a postponement of the deadlines, but confirmed the commitment to developing the sector
Design engineers without experience are promised salaries from 80 thousand rubles
Hard and dense shot ensures the destruction of the target from the first hit, regardless of the drone's body material
Almost all body elements are zinc-treated
SOGAZ lost the case in court against UEC-UMPO