Novosibirsk Researchers Develop Neural Network to Detect Multiple Sclerosis

Researchers at the International Tomography Center of the Siberian Branch of the Russian Academy of Sciences, Novosibirsk State University, and the Novosibirsk Regional Multiple Sclerosis Center are developing software to detect brain lesions associated with multiple sclerosis. Bair Tuchinov, a researcher at the AI Center of Novosibirsk State University, announced the project at the Siberian Healthcare Forum.

Essentially, the system is a neural network designed to help doctors identify potential risks in a timely manner.

He noted that medical neural networks carry certain risks, including false-positive and false-negative results, a tendency to “hallucinate,” and data misclassification. Nevertheless, participants in the discussion said the technology could become an effective assistant to doctors.