Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review
Open accessThe DOI matches its Crossref record; 195 of the 195 references it cites were found in a registry or an index.
Abstract
(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer’s diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.
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.
Integrity signals
Registry
Cites
Statistics
Figures



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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“though this approach demands substantial computational resources and curated pre-training data to avoid negative transfer (Valverde et al., 2021).”
From Multimodal neuroimaging and AI integration in cognitive disorders: advances, challenges, and future directions for precision medicine (2026) · cites this paper as Valverde et al., 2021
Experimental — accuracy not yet measured
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“The most popular were VGG [156] (23), ResNet [157] (15), and Inception [158–160] (11).”
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“The demonstrations of outperformance of CNNs over other methods [168], and the availability of trained CNNs in ImageNet [124], such as AlexNet [169], VGG [156], and Inception [158], probably explains CNNs’ popularity.”
Preferred Reporting Items for Systematic Reviews and Meta-Analyses: the PRISMA statement
Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., & for the PRISMA Group (2009) · BMJ · doi:10.1136/bmj.b2535 · Cited by 83,823
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“, ImageNet [124]) whereas 26 approaches pretrained on medical images.”
Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement
Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., & The PRISMA Group (2009) · PLoS Medicine · doi:10.1371/journal.pmed.1000097 · Cited by 64,042
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Preferred reporting items for systematic reviews and meta-analyses: the PRISMA Statement.
(2009) · PubMed Central · Cited by 44,859
(2008) · Journal of Machine Learning Research · Cited by 33,051
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Research works printed but not linked: 1
- Jones, D.K. (2010). Diffusion Mri, Oxford University Press.
Cited by
Items 101–149 of 149
Dufumier, B. (2022) · theses.fr (ABES) · doi:10.70675/d7d71a04z0514z43e3z840cz71ee3bb8a35b · Cited by 4
Clèrigues, A., Valverde, S., Oliver, A., & Lladó, X. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108811 · Cited by 1
Athisayamani, S., Singh, A. R., Joshi, G. P., & Cho, W. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.056129 · Cited by 1
Silva, J. C. P., Nogueira, F. D. C., Honório, D. D. D. C., Shiguemori, E. H., & Pássaro, A. (2024) · Journal of Aerospace Technology and Management · doi:10.1590/jatm.v16.1353 · Cited by 1
Luo, Y., & Kobayashi, I. (2025) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2025.p0754 · Cited by 1
Optimizing Deep Learning Models for Medical Imaging and Genomics
Kamala, V., Malarvizhi, K., & Subburathinam, K. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5137-7.ch005 · Cited by 1
Ural, B., & Çalım, M. C. (2025) · Traitement du signal · doi:10.18280/ts.420421 · Cited by 1
Graf, S., Wohlgemuth, W. A., & Deistung, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-09513-8_12 · Cited by 1
Wu, H., Weng, J., & Zeng, Y. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110382 · Cited by 1
An Explainable Multi-Scale Deep Learning Framework for Multi-Class Brain MRI Classification
Alshammari, H. H., & Mahmood, M. A. (2026) · Diagnostics · doi:10.3390/diagnostics16121791 · Cited by 1
“…MRI interpretation offers diagnostic value, interpretation is still time-consuming, and inter-reader variability exists, especially when the patterns of various disease classes have visual similarity or when small abnormalities need to be separated out from normal anatomical variation [5–7].”
Li, J., & Bjørnerud, A. (2023) · Proceedings of the Northern Lights Deep Learning Workshop · doi:10.7557/18.6826 · Cited by 1
“The frozen part typically corresponds to the first shallow layers of the neural network, which tend to capture low-level features that are shared across domains, while deeper layers can learn high-level features that are more task-specific [18].”
BackgroundApply Agglomerative Algorithm and Vgg16 on Brain Tumor Segmentation (Dataset to be Used Brats)
Vempaty, L. N., Tatiya, M. R., Shrivastava, A., Kulkarni, G. L., Singh, P. K., & Saxena, V. (2023) · International Conference on Contemporary Computing and Informatics (IC3I) · doi:10.1109/ic3i59117.2023.10397911 · Cited by 1
“Therefore, it is of the utmost relevance in the area of medical imaging to create automated and trustworthy techniques for segmenting brain tumors [1].”
MethodWang, G., Bai, Z., Xu, Y., Song, S., Chen, M., & Chen, H. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10451828 · Cited by 1
“The Transformer network structure requires many parameters for training, which makes it dependent on large datasets to achieve effective training[19] .”
BackgroundA Deep Transfer Learning Model for Classifying Alzheimer's Disease Using MRI Images
Anitha, T., Jayarain, P. J., & Narmatha, C. (2025) · International Conference on Computing and Information Technology (ICCIT) · doi:10.1109/iccit63348.2025.10989476 · Cited by 1
“…or deep learning, algorithms demonstrate similar performance to that of skilled radiologists #2025 4th International Conference on Computing and Information Technology (ICCIT) 13 and 14 April 2025, Tabuk, Saudi Arabia. when it comes to categorizing MRI of individuals with Alzheimer's disease [3].”
Machine Learning Application In Neuroscience For Pre-Surgical Brain Tumor Removal Procedure
Ismaila, L. (2023) · theses.fr (ABES) · doi:10.70675/3daf9354z9b6fz4e3bz9928z13d3049e3627
Bridging Simulation-based Inference and Hierarchical Modeling : Applications in Neuroscience
Rouillard, L. (2024) · theses.fr (ABES) · doi:10.70675/a47096c5zef68z40f5z92c6zc056f01f10e3
Fast Whole-Brain MR Multi-Parametric Mapping with Scan-Specific Self-Supervised NetworksPreprint
Heydari, A., Ahmadi, A., Kim, T. H., & Bilgiç, B. (2024) · PubMed · doi:10.48550/arxiv.2408.02988
“Employment of transfer learning in medical image analysis aims to address the generalization problem of deep learning methods as they often need large numbers of samples to train the network and to achieve robust generalization (Lv et al., 2021; Valverde et al., 2021).”
BackgroundWang, S., & Boutelle, M. G. (2026) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2026.109461
Alden, Z. S., & Ata, O. (2025) · doi:10.5121/csit.2024.150207
“These models are trained on big data sets for a given goal, such as image classification[20], andthe idea is that the features learned by the pre-trained model during its previous task capture broad patterns and representations that may also apply to the current task.”
Transfer Learning for Pancreatic Ductal Adenocarcinoma: A Comprehensive ReviewPreprint
Song, J. W. (2025) · doi:10.58445/rars.2587
GUnet3++: UNet-based architecture for brain MRI segmentation
Singh, H., Kumar, S., & Garg, V. (2025) · International Conference on Recent Advances in Information Technology · doi:10.1109/rait65068.2025.11088915
“[13] Transfer learning has recently shown promise in capturing long-range dependencies in medical images, making it a valuable addition to segmentation tasks, especially for complex tumor structures [14].”
Amsavalli, S., Saminathan, K., & Devi, M. C. (2025) · Indian Journal of Science and Technology · doi:10.17485/ijst/v18i32.1265
Transfer Learning in Cancer Research
Mamta, M., & Nitin (2025) · Wiley eBooks · doi:10.1002/9781394270613.ch18
Additional file 3 of Transfer learning for medical image classification: a literature review
Kim, H. E., Cosa‐Linan, A., Santhanam, N., Jannesari, M., Maros, M. E., & Ganslandt, T. (2022) · Figshare · doi:10.6084/m9.figshare.19593962
Relaxing Supervision Requirements for Tomographic Data Analysis with Machine Learning
Zharov, Y. (2025) · heiDOK (Heidelberg University) · doi:10.11588/heidok.00036385
Additional file 1 of Transfer learning for medical image classification: a literature review
Kim, H. E., Cosa‐Linan, A., Santhanam, N., Jannesari, M., Maros, M. E., & Ganslandt, T. (2022) · Figshare · doi:10.6084/m9.figshare.19593956
Additional file 2 of Transfer learning for medical image classification: a literature review
Kim, H. E., Cosa‐Linan, A., Santhanam, N., Jannesari, M., Maros, M. E., & Ganslandt, T. (2022) · Figshare · doi:10.6084/m9.figshare.19593959
Multi-task learning for joint diagnosis of CNVs and psychiatric conditions from rs-fMRI
Harvey, A. (2023) · Papyrus : Institutional Repository (Université de Montréal) · doi:10.71781/10494
Leveraging large scale data sets: a transfer learning approach for 7T super resolution
Ellis, R. (2021) · eScholarship (California Digital Library) · Cited by 1
Transfer learning from 2D natural images to 4D fMRI brain images via geometric mapping
Gao, K., Wang, L., Li, L., Chen, X., Li, B., Wang, Y.-W., Li, X.-Y., Wang, Z.-H., Li, H.-X., Liao, Y., et al. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.103949
Harshitha, M. S., Mythri, G., Thomas, A., Francis, B., Gopi, V. P., & Sehrawat, A. (2026) · Neuroinformatics · doi:10.1007/s12021-025-09750-5
“Magnetic Resonance Imaging (MRI) has become a cornerstone in evaluating brain development and myelination due to its noninvasive nature (Valverde et al., 2021).”
Madvit: multiview Alzheimer’s disease detection based on vision transformer networks
Hlawa, S., Romdhane, N. B., & Fendri, E. (2026) · International Conference on Machine Vision · doi:10.1117/12.3096269
“With its high spatial resolution and ability to quantify brain atrophy, sMRI provides deeper insights into the brain's shape, position, and tissue volume, which are crucial for AD classification [2][3][4].”
Transfer learning and domain adaptation in neuroinformatics
Lawal, M. A., Abayomi, A., Salihu, A. A., Aliyu, A. A., Aliyu, M. A., & Yakubu, I. Z. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-41459-6.00007-9
Transfer Learning for Pancreatic Ductal Adenocarcinoma Detection: A Comprehensive Review
Song, J. W. (2026) · International journal of high school research · doi:10.36838/v8i4.36
Restoration of structural MRI images for the preclinical study of markers of cerebral aging
Bazzi, F. (2021) · theses.fr (ABES) · doi:10.70675/3390be2fzafd0z4eb6z870bz4603eaad6522
Novel Prospects of Image Restoration Inspired by Concepts of Quantum Mechanics
Dutta, S. (2023) · theses.fr (ABES) · doi:10.70675/8fe483d0z8da8z4b27z9b57z484d2a51ec01
MORPHOLOGICAL CHARACTERIZATION OF BRAIN TUMOR TISSUE IN MRI IMAGES USING CNN AND TRANSFER LEARNING
Hilmi, D. F., Wibawa, A. P., Agustavada, A. A. P., Sholum, A., & Dwiyanto, F. A. (2026) · BIOMA Jurnal Ilmiah Biologi · doi:10.26877/bioma.v15i1.3550
Pandey, N., & Sharma, O. (2026) · Discover Computing · doi:10.1007/s10791-026-10163-4
“In the literature, there were several articles that present systematic reviews that emphasize the role of transfer learning in MRI brain imaging, noting that applications in Alzheimer’s diagnostics have gained traction due to the availability of comprehensive datasets like ADNI [16].”
Chavan, A. M., & Mane, V. (2026) · Journal of The Institution of Engineers (India) Series B · doi:10.1007/s40031-026-01347-z
“Medical image processing has benefited substantially from deep learning, yet most existing methods rely on only one CNN [25].”
Arnold, A., Crum, J. E., II, Čeko, M., & Hirshfield, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29548-4_7
Pant, K. V., Pramanik, P. K. D., Ganie, S. M., Saha, A., & Zhao, Z. (2026) · Frontiers in Genetics · doi:10.3389/fgene.2026.1814786
“Automated brain tumor analysis has evolved from conventional CNN pipelines (Rasool et al., 2024) to transfer learning (Valverde et al., 2021), Transformers (Aamir et al., 2025), and hybrid/ensemble strategies (Das and Goswami, 2025).”
Advancing the Volumetric Analysis of Ultra‐Low‐Field Brain MRI Using Image‐to‐Image Translation
Hsu, P., Marchetto, E., Johnson, P. M., & Veraart, J. (2026) · Magnetic Resonance in Medicine · doi:10.1002/mrm.70488
“This approach allows us to leverage large, publicly available low-field and HF datasets for model pretraining before fine-tuning on real ULF acquisitions, substantially expanding the effective training data pool beyond the limited number of available ULF scans [70].”
Asymptotic Theory of Efficient Nonparametric Estimation of the Ratio of Two Densities
Efromovich, S. (2026) · Mathematical Methods of Statistics · doi:10.3103/s1066530726700110
Griffiths-King, D., Mulvany, T., Rose, H., Peet, A. C., Apps, J. R., Arvanitis, T. N., & Novák, J. (2026) · Brain Communications · doi:10.1093/braincomms/fcag317
“In the current study, we specifically conducted inductive transfer learning 39 to account for the rarity of paediatric brain tumours and the relatively low abundance of DWI data, both of which can harm sample sizes and have the ability to train robust learners.”
Building Efficient Neural Networks For Brain Tumor Detection
Shree, C. K. (. A. D. (2022) · Journal of Positive School Psychology
Михайленко, И. И. (2026) · Digital models and solutions · doi:10.29141/2949-477x-2026-5-3-1
Advances in artificial intelligence-driven MRI research in Alzheimer’s disease
Deng, L., Zeng, Y., Ou, P., Zhou, S., Gou, Y., & Huang, C. (2026) · Frontiers in Neurology · doi:10.3389/fneur.2026.1943265
“Transfer learning, which leverages pretrained convolutional neural networks on large datasets, has demonstrated improved performance in AD classification tasks, especially when training data are scarce or heterogeneous (57, 58).”
Seraji, Z., Heidari, M., Rashidi, S., & Ashrafi, M. (2026) · Journal of Neuroradiology · doi:10.1016/j.neurad.2026.101617
Hudnurkar, M., Sahu, G. A., Hussain, M. S., & Lokhande, A. (2026) · doi:10.1109/aidml70736.2026.11749108
Metadata
- Authors
- Valverde, J. M., Imani, V., Abdollahzadeh, A., De Feo, R., Prakash, M., Ciszek, R., & Tohka, J.
- Affiliations
- University of Eastern Finland (FI)
- A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, 70150 Kuopio, Finland
- Corresponding author
- Tohka, Jussi
- ORCID
- Venue
- Journal of Imaging
- Publisher
- MDPI AG
- Published
- 2021-04-01
- Volume
- 7
- Issue
- 4
- Pages
- 66
- ISSN
- 2313-433X (ISSN-L)
- PMC
- PMC8321322
- OpenAlex
- W3126990165
- Cited by
- 137
- References
- 186
- Citations by year
- 2026: 23 · 2025: 24 · 2024: 24 · 2023: 32 · 2022: 29 · 2021: 5
- FWCI
- 1.63
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Journal of Imaging (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Academy of Finland (316258)
- H2020 Marie Skłodowska-Curie Actions (740264)
- European Social Fund (S21770)
- Topics
- 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
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Brain Tumor Detection and Classification
- Keywords
- transfer learning, brain MRI, convolutional neural networks, pre-training and fine-tuning, dementia classification, brain tumor segmentation, Alzheimer's disease, unseen target domains, unlabeled data
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
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.