Domain shift in computer vision models for MRI data analysis: An overview

Ekaterina Kondrateva, Marina Pominova, Elena Popova, Maxim Sharaev, Alexander Bernstein, Evgeny Burnaev

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Machine learning and computer vision methods are showing good performance in medical imagery analysis. Yet only a few applications are now in clinical use and one of the reasons for that is poor transferability of the models to data from different sources or acquisition domains. Development of new methods and algorithms for the transfer of training and adaptation of the domain in multi-modal medical imaging data is crucial for the development of accurate models and their use in clinics. In present work, we overview methods used to tackle the domain shift problem in machine learning and computer vision. The algorithms discussed in this survey include advanced data processing, model architecture enhancing and featured training, as well as predicting in domain invariant latent space. The application of the autoencoding neural networks and their domain-invariant variations are heavily discussed in a survey. We observe the latest methods applied to the magnetic resonance imaging (MRI) data analysis and conclude on their performance as well as propose directions for further research.

Original languageEnglish
Title of host publication13th International Conference on Machine Vision, ICMV 2020
EditorsWolfgang Osten, Dmitry P. Nikolaev, Jianhong Zhou
PublisherSPIE
ISBN (Electronic)9781510640405
DOIs
Publication statusPublished - 2020
Event13th International Conference on Machine Vision, ICMV 2020 - Rome, Italy
Duration: 2 Nov 20206 Nov 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11605
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference13th International Conference on Machine Vision, ICMV 2020
Country/TerritoryItaly
CityRome
Period2/11/206/11/20

Keywords

  • Deep Learning
  • Domain Adaptation
  • Fader Networks
  • Invariant Representation
  • MRI
  • Transfer Learning

Fingerprint

Dive into the research topics of 'Domain shift in computer vision models for MRI data analysis: An overview'. Together they form a unique fingerprint.

Cite this