Medical image analysis

Contact person: Olga Senyukova

Team: Olga Senyukova, Sergey Pyatkovsky, Gregory Shoroshov, Sergey Trubetskoy, Dmitry Vartanov

Overview

The main goal of this research direction is to develop the instruments that help doctors in various data analysis tasks. It is important that we are talking not about the replacement of a doctor by artificial intelligence, but about

  • reducing the amount of routine work, thus allowing to save more lives
  • finding invisible or unobvious patterns in data for better diagnostics

and other kinds of assistance.

Medical imaging refers to visualization of internal structures of human body. Our projects focus on magnetic resonance images (MRI) and computed tomography (CT) images. Besides images, we work with other kinds of signals such as electrocardiogram (ECG) and gait data from clinical and portable devices. We develop deep learning-based algorithms for automatic analysis of this data. Currently our group has a joint work with Diagnostics and Telemedicine Center of the Moscow Health Care Department and also with research group from the USA.

Our projects include:

  • human body composition analysis, involving segmentation of fat and muscle tissues
  • image-based detection and prediction of MRI hardware failures
  • diagnostics of heart and neurological diseases and monitoring of psychophysiological states.

Selected Publications

  1. Discovery of Hybrid Ensemble Models Resilient to Input Resolution Deterioration. Y. Zheniy, R. Miao, V. Gavrishchaka, O. Senyukova. 2021 4th International Conference on Information and Computer Technologies (ICICT), 2021
  2. Synergy of physics-based reasoning and machine learning in biomedical applications: towards unlimited deep learning with limited data. V. Gavrishchaka, O. Senyukova, M. Koepke. ADVANCES IN PHYSICS-X, 2019
  3. Automated Diagnostic Model Based on Isoline Map Analysis of Myocardial Tissue Structure. O. Senyukova, D. Brotikovskaya, S. Gorokhova, E. Tebenkova. Computational Intelligence, 9th International Joint Conference, IJCCI 2017 Funchal-Madeira, Portugal, November 1-3, 2017 Revised Selected Papers, 2019
  4. Fast Brain MRI Registration with Automatic Landmark Detection Using a Single Template Image. O. Senyukova, D. Zobnin. Pattern Recognition (37th German Conference, GCPR 2015, Aachen, Germany, October 7–10, 2015, Proceedings), 2015
  5. Segmentation of Blurred Objects by Classification of Isolabel Contours. O. Senyukova. Pattern Recognition, 2014