IFIB MEPhI: A program to diagnose brain cancer

The main articles are:

• Artificial Intelligence in Medicine
• Artificial intelligence in radiology
• Cancer diagnosis
• Brain cancer

2025: System Announcement

Tatyana Kobyakova, a graduate of the Engineering and Physical Institute of Biomedicine (IFIB) of MEPhI, has developed a project for the automatic analysis of MRI images using artificial intelligence, which will help in the diagnosis of brain etastases . This was reported on June 19, 2025 in MEPhI.

Metastases brain to are secondary tumors that occur when cancer they spread from other organs to the brain. They are diagnosed in 20-40% of cancer patients. Metastases cause serious symptoms: headaches seizures, disorders memories and coordination. Without timely diagnosis, they can lead to serious consequences. Traditional diagnosis of metastases is complex: radiologists spend up to 40 minutes analyzing a single MRI image to identify and assess tumors. Small foci measuring several millimeters often go unnoticed, and the human factor increases the risk of errors. Even in modern clinics, this process remains laborious.

Tatyana Kobyakova has created a computer product that reduces the time of MRI analysis to 5 minutes and increases the accuracy of diagnostics. Its program uses a neural network that automatically detects and isolates metastases, including the smallest ones. The system compares images before and after treatment, monitors changes in tumors and generates reports that easily integrate with medical systems or electronic patient records. This solution saves doctors time, minimizes errors and creates opportunities for research, for example, to study the effect of radiation doses on the control of metastases.

The IFIB student collaborated with experts from the Business Center for Neurosurgery clinic, who helped adapt the program to the requirements of the clinics, and also provided pictures of 600 patients for training the neural network.

Tatiana's project makes the diagnostic process fast, accurate and accessible. It demonstrates how artificial intelligence can serve medicine, and the ideas of young scientists can find practical application, noted in MEPhI.

In the future, Tatyana plans to improve the system by adding more data to improve accuracy, and introduce it into clinics throughout Russia. 

"Such systems, sharpened only for brain tumors, have not yet been. There was image analysis and tumor segmentation, but no one output statistics as a function of time. And in oncology, it is important to see the dynamics. That's the strength of my program. It is now licensed and will be introduced into clinics on a commercial basis , "Tatyana Kobyakova shared.