mlsanityData to 7 Oct 2026

Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects

arXiv 1910.04597 ↗First posted 10 Oct 2019eess.IV cs.CV cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

This is an empirical study to investigate the impact of scanner effects when using machine learning on multi-site neuroimaging data. We utilize structural T1-weighted brain MRI obtained from two different studies, Cam-CAN and UK Biobank. For the purpose of our investigation, we construct a dataset consisting of brain scans from 592 age- and sex-matched individuals, 296 subjects from each original study. Our results demonstrate that even after careful pre-processing with state-of-the-art neuroimaging pipelines a classifier can easily distinguish between the origin of the data with very high accuracy. Our analysis on the example application of sex classification suggests that current approaches to harmonize data are unable to remove scanner-specific bias leading to overly optimistic performance estimates and poor generalization. We conclude that multi-site data harmonization remains an open challenge and particular care needs to be taken when using such data with advanced machine learning methods for predictive modelling.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 4; 2023: 6; 2024: 6; 2025: 4; 2026: 10.

40 papers.

Sort:

By area:

  1. 2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
  2. 2022How Robust is Unsupervised Representation Learning to Distribution Shift?cited by 24
  3. 2021Detecting when pre-trained nnU-Net models fail silently for Covid-19 lung lesion segmentationcited by 19
  4. 2022The Open Kidney Ultrasound Data Setcited by 18
  5. 2024Shortcut Learning in Medical Image Segmentationcited by 16
  6. 2021Preventing dataset shift from breaking machine-learning biomarkerscited by 14
  7. 2022Contrastive learning for regression in multi-site brain age predictioncited by 14
  8. 2024The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic reviewcited by 13
  9. 2025Robustness and Cybersecurity in the EU Artificial Intelligence Actcited by 10
  10. 2021Anatomy of Domain Shift Impact on U-Net Layers in MRI Segmentationcited by 9
  11. 2021Robust White Matter Hyperintensity Segmentation on Unseen Domaincited by 8
  12. 2023Reverse Engineering Breast MRIs: Predicting Acquisition Parameters Directly from Imagescited by 7
28 more
  1. 2021Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practicecited by 6
  2. 2021Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learningcited by 6
  3. 2023Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric researchcited by 4
  4. 2024Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Frameworkcited by 4
  5. 2021Contrast Adaptive Tissue Classification by Alternating Segmentation and Synthesiscited by 3
  6. 2021Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition Characteristicscited by 3
  7. 2023Efficient Large Scale Medical Image Dataset Preparation for Machine Learning Applicationscited by 3
  8. 2021Harmonization and the Worst Scanner Syndromecited by 2
  9. 2024Brain Age Estimation with a Greedy Dual-Stream Model for Limited Datasetscited by 2
  10. 2023Prompt-Based Tuning of Transformer Models for Multi-Center Medical Image Segmentation of Head and Neck Cancercited by 1
  11. 2024AI-Assisted Diagnosis for Covid-19 CXR Screening: From Data Collection to Clinical Validationcited by 1
  12. 2025Benchmarking and Explaining Deep Learning Cortical Lesion MRI Segmentation in Multiple Sclerosiscited by 1
  13. 2026Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbationscited by 1
  14. 2022Pseudo-Label Guided Multi-Contrast Generalization for Non-Contrast Organ-Aware Segmentationcited by 0
  15. 2023SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysiscited by 0
  16. 2023A quality assurance framework for real-time monitoring of deep learning segmentation models in radiotherapycited by 0
  17. 2024PRISM: Privacy-preserving Inter-Site MRI Harmonization via Disentangled Representation Learningcited by 0
  18. 2025Robust brain age estimation from structural MRI with contrastive learningcited by 0
  19. 2025Learning Semantic Directions for Feature Augmentation in Domain-Generalized Medical Segmentationcited by 0
  20. 2026Unified Multi-Site Multi-Sequence Brain MRI Harmonization Enriched by Biomedical Semantic Stylecited by 0
  21. 2026A Causal Framework for Mitigating Data Shifts in Healthcarecited by 0
  22. 2026Robustness Evaluation of a Foundation Segmentation Model Under Simulated Domain Shifts in Abdominal CT: Implications for Health Digital Twin Deploymentcited by 0
  23. 2026Multi-Dataset Cross-Domain Knowledge Distillation for Unified Medical Image Segmentation, Classification, and Detectioncited by 0
  24. 2026Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustnesscited by 0
  25. 2026Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matchingcited by 0
  26. 2026Site Is Decodable Before Pretraining: Negative Controls for Probing Frozen Brain-MRI Foundation Modelscited by 0
  27. 2026PANDA - Prototype-Anchored Alignment for Partially Unpaired Multimodal Learning, with Applications to Alzheimers MRI and TCGA Pathologycited by 0
  28. 2026M3-Score: Fidelity, Memorization and Coverage as Separate Axes for Evaluating Generative Radiology Image Modelscited by 0