Artificial Intelligence for secure Computed Tomography
Receiving a high dose of radiation by the patient during the CT procedure, The disadvantage of using traditional neural networks for noise reduction of CT images is the presence of a noticeable proportion of random errors in their work, leading to false image artifacts and an erroneous diagnosis of the doctor. Our mathematical apparatus allows us to create and apply figurative-logical neural networks for additional noise reduction, while solving the problem of random errors and artifacts in CT images for existing neural networks.
Artificial Intelligence And Digital Services
Artificial intelligence
The development will take about 2 years.
Worldwide sales
We have developed a unique method for constructing computed tomography (hereinafter – CT) images based on CT projections, which is based on an original mathematical apparatus of spots, which allows to suppress the quantum noise of CT sensors, which improves the clarity and contrast of CT images at low and even ultra-low doses of X-ray irradiation. The peculiarity of the developed mathematical apparatus lies in the possibility of encoding the figurative-logical representation and processing of information, which has an analogy with human perception and reasoning.
1. Simonov, N.A. "Concept for use in an intelligent system", "Micronica", 2020, vol. 49, No. 6, pp. 459-473. , 2. Simonov N.A. "Application of the spot model to solve inverse problems". Sensors, 2023, Volume 23, № 3: 1247. , 3. Simonov N.A., Rusalova M.N. "Representation of mental images using the model of spots in psychology". Natural Systems of the mind, 2023, Volume 1, pp. 4-23. , 4. Simonov N.A. “Development of a mathematical apparatus with a figurative representation of information for neuromorphic systems". Russian Microelectronics, 2023, Volume 52, Supplement. 1, pp. S159–S162.
N.A.
