At ITMO University in Saint Petersburg, it was reported about a new domestic development. A group of chemists under the leadership of Professor ITMO Vladimir Vinogradov developed a machine learning system that allows to automatically select the size, composition and shape of magnetic nanoparticles for optimal operation of MRI systems and "burning out" tumors in various organs of the body.
Scientists have developed a machine learning algorithm that translates nanoparticle parameters into diagnostic and treatment efficiency parameters based on open lab data. The system can predict what efficiency indicators for MRI and hyperthermia will be in case of use of nanoparticles with certain parameters.
To create the neural network, scientists used data on 1282 unique types of magnetic nanoparticles. Researchers compared how the shape, chemical composition, length, width and magnetic parameters of these nanostructures affected how actively they absorb radio waves and how quickly they "magnetize" when interacting with tomograph radiation.
Further development and practical application of the neural network requires new data, including obtained during observations of the action of magnetic nanoparticles in experiments on animals, cell cultures and body tissues.
Unfortunately, the data we need is almost non-existent in the public domain and what exists, is very little for further training of the algorithm. We reach out to relevant organizations, request this information - our team is ready for joint research. The more data we get, the more accurate our system can work.