Yandex B2B Tech, in collaboration with the School of Data Analysis and SPbSPMU, has created a neural network that helps doctors assess brain MRIs 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 central nervous system disorders in order to quickly select the optimal therapy.
The neural network automatically highlights brain contours and calculates the ratio of gray and white matter with over 90% accuracy. 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
Герой России Гарнаев: никто из профессионалов о возобновлении производства на КАЗ всерьёз не говорит
Система отслеживает спутники на высотах до 50 000 км и ведёт за ними наблюдение
The armored vehicle is equipped with a KamAZ-740.35-400 diesel engine with a power of 400 hp.
Constant improvements in avionics, weapons and tactical capabilities will make the aircraft a flexible response to future challenges
The exterior of the KamAZ-54901 features fairings on the cab and chassis for fuel economy
Fighters are in demand both domestically and abroad
Tyazhpromexport and Venezuela Agree on Plant Revival
The company not only completed the state order, but also quickly mastered the production of AK-12K for special forces
Experts have developed a photogrammetric complex with a resolution of less than 1 cm
