Supercomputer taught to create MRI of the brain for rapid research of diseases

The system consists of 80 DGX A100 modules (80 GB), united by an InfiniBand HDR interconnect based on the Bluefield-2 DPU. Creation

The supercomputer cost NVIDIA $100 million; it currently occupies 41st place in the world TOP500 ranking.

King's College London usesCambridge-1 to create artificial intelligence models capable of generating synthetic images of the brain based on images obtained using MRI. They are given to patients of different ages and with various diseases.

This makes it possible to teach AI to distinguish healthythe brain from the patient, since it is trained on the images of patients of different ages and with various ailments. It is expected that in the long term this will make it possible to diagnose possible neurological abnormalities or brain diseases at an early stage.

In addition, a new technique using AIwill come in handy in learning how the brain is formed, how injury and illness affect it, and how to help it recover. NVIDIA noted that the supercomputer accelerated the work, cutting the time for training AI models from several months to weeks. In addition, it allows you to create clearer images.

Read more

Japanese scientists presented a method of moving objects with sound waves

For the first time in history, 9 stars disappeared in half an hour and did not return

Detailed photos of galaxies closest to us appeared