Machine Learning for Brain MRI Data Harmonisation: A Systematic Review

Abstract

Background: Magnetic Resonance Imaging (MRI) data collected from multiple centres can be heterogeneous due to factors such as the scanner used and the site location. To reduce this heterogeneity, the data needs to be harmonised. In recent years, machine learning (ML) has been used to solve different types of problems related to MRI data, showing great promise. Objective: This study explores how well various ML algorithms perform in harmonising MRI data, both implicitly and explicitly, by summarising the findings in relevant peer-reviewed articles. Furthermore, it provides guidelines for the use of current methods and identifies potential future research directions. Method: This review covers articles published through PubMed, Web of Science, and IEEE databases through June 2022. Data from studies were analysed based on the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Quality assessment questions were derived to assess the quality of the included publications. Results: a total of 41 articles published between 2015 and 2022 were identified and analysed. In the review, MRI data has been found to be harmonised either in an implicit (n = 21) or an explicit (n = 20) way. Three MRI modalities were identified: structural MRI (n = 28), diffusion MRI (n = 7) and functional MRI (n = 6). Conclusion: Various ML techniques have been employed to harmonise different types of MRI data. There is currently a lack of consistent evaluation methods and metrics used across studies, and it is recommended that the issue be addressed in future studies. Harmonisation of MRI data using ML shows promises in improving performance for ML downstream tasks, while caution should be exercised when using ML-harmonised data for direct interpretation.

Investigating the value of radiomics stemming from DSC quantitative biomarkers in IDH mutation prediction in gliomas

“…computation of parametric maps, since different software packages can produce results with significant variability in multi-center studies (48-50). In addition, our workflow does not require data harmonization, which can be challenging due to the presence of confounding variables and unknown factors that cause cross-site variations (28). Driven from the results of Tables 2, 3, the radiomics analysis showed promising results on identifying the IDH mutation status.…”

“…Bratumia software (https://www.nitrc.org/projects/bratumia) (28), was used to delineate the regions of interest (ROIs). This software uses as input four different MR contrasts (T1 before and after contrast, T2, T2 FLAIR) in order to correctly identify tumor enhancement, oedema and necrosis.…”

“…The heterogeneity in MRI scanner characteristics, such as software variations, MRI equipment (receiver coils), scan protocols, and reconstruction algorithms, can lead to inter-and intra-site variations. These variations affect the signal intensity of the MR image, which may conceal the region of interest in terms of signal to noise ratio (SNR) and lead to the failure of (ML) analysis (28). To account for this heterogeneity, harmonization and normalization techniques are applied to the data as a pre-processing step which is not intuitive since there is variety of normalization choices that can lead to different results.…”

Standardized brain tumor imaging protocols for clinical trials: current recommendations and tips for integration

“…SyMRI is already available on some commercial scanners (e.g., “SyntAc” on Siemens, “MAGiC” on GE), and some studies advocate for the accuracy of SyMRI in parameter quantification ( 152 ) and for its potential usefulness in gliomas ( 151 ). An alternative approach to improve the comparability of images across institutions and manufacturers may be represented by standardization methods applied during post-processing ( 153 ), possibly with the aid of AI ( 154 ).…”

Brain-Inspired Spatio-Temporal Associative Memories for Neuroimaging Data Classification: EEG and fMRI

“…Wider applications of the proposed STAM models can be anticipated, such as predicting air pollution [36] with the use of neuromorphic hardware [37][38][39][40] -Developing new functions in the NeuCube SNN, enabling a better STAM system design that are inspired by neurogenetic [41] and brain cognition [42][43][44] and also enhancing already existing SNN models for transfer learning and knowledge discovery [45][46][47]. -Normalizing or/and harmonizing NI data across various data sources [48]. Establishing an effective "mapping" between training variables and synchronized time units will be crucial.…”