Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.

Effects of MRI scanner manufacturers in classification tasks with deep learning models

Open access

Abstract

Deep learning has become a leading subset of machine learning and has been successfully employed in diverse areas, ranging from natural language processing to medical image analysis. In medical imaging, researchers have progressively turned towards multi-center neuroimaging studies to address complex questions in neuroscience, leveraging larger sample sizes and aiming to enhance the accuracy of deep learning models. However, variations in image pixel/voxel characteristics can arise between centers due to factors including differences in magnetic resonance imaging scanners. Such variations create challenges, particularly inconsistent performance in machine learning-based approaches, often referred to as domain shift, where the trained models fail to achieve satisfactory or improved results when confronted with dissimilar test data. This study analyzes the performance of multiple disease classification tasks using multi-center MRI data obtained from three widely used scanner manufacturers (GE, Philips, and Siemens) across several deep learning-based networks. Furthermore, we investigate the efficacy of mitigating scanner vendor effects using ComBat-based harmonization techniques when applied to multi-center datasets of 3D structural MR images. Our experimental results reveal a substantial decline in classification performance when models trained on one type of scanner manufacturer are tested with data from different manufacturers. Moreover, despite applying ComBat-based harmonization, the harmonized images do not demonstrate any noticeable performance enhancement for disease classification tasks.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-023-43715-5

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The processing pipeline used in our study to carry out different disease classification tasks with different DL networks.
Figure 1 The processing pipeline used in our study to carry out different disease classification tasks with different DL networks.CC BY · PubMed Central
Figure 2 MRI scanner manufacturer classification results for the ADNI1, ADNI2, PPMI, and CALSNIC2 datasets generated by ResNet model. The classification accuracy is approximately 99% for the (a) ADNI1, (b) ADNI2, and (d) CALSNIC2 datasets whereas the accuracy is around 95% for the (c) PPMI dataset.
Figure 2 MRI scanner manufacturer classification results for the ADNI1, ADNI2, PPMI, and CALSNIC2 datasets generated by ResNet model. The classification accuracy is approximately 99% for the (a) ADNI1, (b) ADNI2, and (d) CALSNIC2 datasets whereas the accuracy is around 95% for the (c) PPMI dataset.CC BY · PubMed Central
Figure 3 t-SNE plots for the ADNI1, ADNI2, PPMI, and CALSNIC2 datasets using the features generated by MRQy evaluation metrics. Different clusters are primarily formed based on the scanner manufacturer. In panels (a) and (b), bounding boxes are delineated, incorporating information about the scanner model, field strength, and flip angle. These annotations visually highlight their role in inducing domain shift within a dataset.
Figure 3 t-SNE plots for the ADNI1, ADNI2, PPMI, and CALSNIC2 datasets using the features generated by MRQy evaluation metrics. Different clusters are primarily formed based on the scanner manufacturer. In panels (a) and (b), bounding boxes are delineated, incorporating information about the scanner model, field strength, and flip angle. These annotations visually highlight their role in inducing domain shift within a dataset.CC BY · PubMed Central
Figure 4 Patient-level split process for longitudinal data to train different DL models.
Figure 4 Patient-level split process for longitudinal data to train different DL models.CC BY · PubMed Central
Figure 5 Minor changes in voxel-wise ComBat harmonization using structural MRI. (A) One 2D axial slice of preprocessed 3D T1-weighted MR image of CALSNIC2 dataset before harmonization, (B) corresponding slice after harmonization. The red, yellow, and blue arrows point to the regions with manipulated structures, including the disappearance of minor details resulting from the ComBat harmonization.
Figure 5 Minor changes in voxel-wise ComBat harmonization using structural MRI. (A) One 2D axial slice of preprocessed 3D T1-weighted MR image of CALSNIC2 dataset before harmonization, (B) corresponding slice after harmonization. The red, yellow, and blue arrows point to the regions with manipulated structures, including the disappearance of minor details resulting from the ComBat harmonization.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 44 references

Research works printed but not linked: 1

  1. Van der Maaten, L. & Hinton, G. Visualizing data using t-sne. J. Mach. Learn. Res. 9, 896 (2008).

Cited by

See all 54

Metadata

Authors
Kushol, R., Parnianpour, P., Wilman, A. H., Kalra, S., & Yang, Y.-H.
Affiliations
University of Alberta (CA)
Corresponding author
Kushol, Rafsanjany
Venue
Scientific Reports
Published
2023-10-05
Volume
13
Issue
1
Pages
16791-16791
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4387376141
Cited by
54
References
44
Citations by year
2026: 21 · 2025: 22 · 2024: 11
FWCI
8.94
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • ALS Society of Canada (100009017)
  • Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada (501100002790)
  • Fondation Brain Canada (100009408)
  • Gouvernement du Canada | Canadian Institutes of Health Research (501100000024)
  • Prime Minister Fellowship Bangladesh
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Advanced MRI Techniques and Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
Keywords
domain shift, multi-center MRI, structural MRI, combat, image harmonization, disease classification, neuroimaging, deep learning
MeSH terms
Machine Learning, Deep Learning, Magnetic Resonance Imaging, Natural Language Processing, Neuroimaging

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Effects of MRI scanner manufacturers in classification tasks with deep learning models. https://app.cochat.ai/papers/10.1038/s41598-023-43715-5
The paper
Kushol, R., Parnianpour, P., Wilman, A. H., Kalra, S., & Yang, Y.-H. (2023). Effects of MRI scanner manufacturers in classification tasks with deep learning models. Scientific Reports. https://doi.org/10.1038/s41598-023-43715-5

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.