Show simple item record

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorExterne beoordelaar - External assesor,
dc.contributor.authorPollitt, Ryan
dc.date.accessioned2022-08-13T00:00:34Z
dc.date.available2022-08-13T00:00:34Z
dc.date.issued2022
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/42266
dc.description.abstractDeep learning-based approaches have seen a lot of success in the space of Magnetic Resonance Imaging from segmentation to real-time registration. However, these methods often fail to generalize to different domains, that is to say scans from different scanners, sequences or populations. We review two classes of approaches to counteract these so-called domain shifts in deep learning for MRI data: data harmonization and domain generalization, and discuss their pros and cons. Data harmonization removes domain-specific information from MR images themselves, whereas domain generalization trains a neural network to be robust to a wide variety of input images from different domains. Five papers were found for data harmonization and sixteen papers for domain generalization. Based on these papers, we conclude that both data harmonization and domain generalization are viable for small expected domain shifts. In practice, the extent of domain shifts will often be unknown prior to deployment of the neural network or will be too large. In this more realistic case, we determine that domain generalization offers better generalization capabilities than data harmonization. On the other hand, data harmonization can be used to remove domain-specific information from new data, making it possible to use already trained task networks (e.g. a segmentation network) without having to retrain on the new domain or requiring labelled data from this domain. Both methods therefore have useful applications in different scenarios.
dc.description.sponsorshipUtrecht University
dc.language.isoEN
dc.subjectIn this review two classes of methods of counteracting domain shifts were assessed. A domain shift occurs when the testing data of a deep learning application is statistically different from that of the training data, leading to a performance drop. We assessed both of these classes in the context of magnetic resonance images.
dc.titleRobustness to Domain Shifts in MRI for Deep Learning-based Methods: A Review
dc.type.contentMaster Thesis
dc.rights.accessrightsOpen Access
dc.subject.keywordsData harmonization; deep learning; domain generalization; domain shift; MRI
dc.subject.courseuuMedical Imaging
dc.thesis.id8423


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record