Pattern Recognition and Image Analysis. Vol. 33, No. 4, Pages 769-783, 2023

A. S. Ingacheva^a^,^b^,*, M. I. Gilmanov^a^,^b^,**, A. V. Yamaev^a^,^d^,***, A. V. Buzmakov^c^,****, D. D. Kazimirov^a^,^b^,*****, I. A. Kunina^a^,^b^,******, Zh. V. Soldatova^a^,*******, M. V. Chukalina^a^,^b^,********, and V. V. Arlazarov^a^,^c^,*********

^bInstitute for Information Transmission Problems, Russian Academy of Sciences, Moscow, 127051 Russian Federation

^cFederal Research Center “Computer Science and Control” of the Russian Academy of Sciences, Moscow, 119333 Russian Federation

Correspondence to: *e-mail: a.ingacheva@smartengines.com
Correspondence to: **e-mail: m.gilmanov@smartengines.com
Correspondence to: ***e-mail: yamaev@smartengines.com
Correspondence to: ****e-mail: buzmakov@gmail.com
Correspondence to: *****e-mail: d.kazimirov@smartengines.com
Correspondence to: ******e-mail: kunina@iitp.ru
Correspondence to: *******e-mail: zh.soldatova@smartengines.com
Correspondence to: ********e-mail: m.chukalina@smartengines.com
Correspondence to: *********e-mail: vva@smartengines.com

Abstract—The article presents the results of research in the field of computational X-ray tomography, obtained within the framework of the scientific school, by Doctor of Engineering, Corresponding Member of the Russian Academy of Sciences V.L. Arlazarov, on artificial intelligence. The field of computed tomography, which is relatively young for the school, arose as a result of a combination of combinatorial optimization approaches, training neural network models, image processing, and solving the problem of stopping information acquisition. Thanks to the accumulated experience, four areas of research can be distinguished: fast algorithms for tomographic reconstruction, scanning protocols for monitored tomographic reconstruction, neural network approaches to reconstruction, as well as methods for suppressing artifacts and distortions that occur in tomographic reconstructions. This article reflects the main successes and achievements obtained in these areas, which are demonstrated using the example of specific applied solutions.

Keywords: computed tomography, monitored tomographic reconstruction, stopping rule, cupping effect, beam hardening, neural networks, deep learning, reconstruction algorithm, radiation exposure, ring artifacts, orthotropic artifacts

Computer Tomography as an Artificial Intelligence Instrument—the Survey of Approach and Results of V.L. Arlazarov’s Scientific School