Domain Shift in Computer Vision models for MRI data analysis: An Overview

TL;DR

This paper reviews methods addressing the domain shift problem in MRI data analysis using machine learning, focusing on techniques like data processing, model architecture, and domain-invariant features to improve transferability.

Contribution

It provides a comprehensive overview of current methods for domain adaptation in MRI analysis, highlighting recent advances and proposing future research directions.

Findings

Autoencoding neural networks are heavily used for domain-invariant features.

Recent methods show promising results in MRI domain adaptation.

The survey identifies key challenges and potential solutions for clinical application.

Abstract

Machine learning and computer vision methods are showing good performance in medical imagery analysis. Yetonly a few applications are now in clinical use and one of the reasons for that is poor transferability of themodels to data from different sources or acquisition domains. Development of new methods and algorithms forthe transfer of training and adaptation of the domain in multi-modal medical imaging data is crucial for thedevelopment of accurate models and their use in clinics. In present work, we overview methods used to tackle thedomain shift problem in machine learning and computer vision. The algorithms discussed in this survey includeadvanced data processing, model architecture enhancing and featured training, as well as predicting in domaininvariant latent space. The application of the autoencoding neural networks and their domain-invariant variationsare 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.