AI will help determine the type of brain tumor by MRI

Scientists at the I.M. Sechenov First Moscow State Medical University have developed an innovative web application that uses artificial intelligence to accurately and quickly diagnose tumors in the brain. The system analyzes MRI scans to not only detect the tumor, but also to determine its exact location, as well as to give a tentative classification.

Cellular time: "brain on a chip" will help treat the most aggressive form of cancer

How the platform developed in the Russian Federation is used to study a new method of glioblastoma therapy

The application is based on the modern YOLO v11 neural network, which has been trained on more than 5,000 images. Due to this, the accuracy of tumor detection has reached an impressive 97.1%.

"The web application not only finds the tumor and determines its location, but also classifies the neoplasm, that is, it makes an assumption about its nature. The model determines that the detected formation is, for example, glioma, meningioma or pituitary adenoma," said Ivan Simonovich, the author of the project, a graduate of the master's degree in Intelligent Information Technologies in Medicine at the advanced engineering school of Sechenov University.

The development has an open source code. Most of the free AI solutions available on the market are usually limited to detecting neoplasms, while the Russian application offers a comprehensive analysis.

Read more in the exclusive Izvestia article:

Sound application: AI will help determine the type of brain tumor by MRI