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

arXiv: https://arxiv.org/abs/1910.04597 · HTML: https://mlsanity.com/paper/1910.04597/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2019.

## Built on by (most cited first, 30 of 43)

- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [How Robust is Unsupervised Representation Learning to Distribution Shift?](https://mlsanity.com/paper/2206.08871/) (2022)
- [Detecting when pre-trained nnU-Net models fail silently for Covid-19 lung lesion segmentation](https://mlsanity.com/paper/2107.05975/) (2021)
- [The Open Kidney Ultrasound Data Set](https://mlsanity.com/paper/2206.06657/) (2022)
- [Shortcut Learning in Medical Image Segmentation](https://mlsanity.com/paper/2403.06748/) (2024)
- [Preventing dataset shift from breaking machine-learning biomarkers](https://mlsanity.com/paper/2107.09947/) (2021)
- [Contrastive learning for regression in multi-site brain age prediction](https://mlsanity.com/paper/2211.08326/) (2022)
- [The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review](https://mlsanity.com/paper/2402.13635/) (2024)
- [Robustness and Cybersecurity in the EU Artificial Intelligence Act](https://mlsanity.com/paper/2502.16184/) (2025)
- [Anatomy of Domain Shift Impact on U-Net Layers in MRI Segmentation](https://mlsanity.com/paper/2107.04914/) (2021)
- [Robust White Matter Hyperintensity Segmentation on Unseen Domain](https://mlsanity.com/paper/2102.06650/) (2021)
- [Reverse Engineering Breast MRIs: Predicting Acquisition Parameters Directly from Images](https://mlsanity.com/paper/2303.04911/) (2023)
- [Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practice](https://mlsanity.com/paper/2102.01979/) (2021)
- [Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning](https://mlsanity.com/paper/2106.01132/) (2021)
- [Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework](https://mlsanity.com/paper/2402.06875/) (2024)
- [Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research](https://mlsanity.com/paper/2301.08525/) (2023)
- [Contrast Adaptive Tissue Classification by Alternating Segmentation and Synthesis](https://mlsanity.com/paper/2103.02767/) (2021)
- [Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition Characteristics](https://mlsanity.com/paper/2111.13069/) (2021)
- [Efficient Large Scale Medical Image Dataset Preparation for Machine Learning Applications](https://mlsanity.com/paper/2309.17285/) (2023)
- [Harmonization and the Worst Scanner Syndrome](https://mlsanity.com/paper/2101.06255/) (2021)
- [Brain Age Estimation with a Greedy Dual-Stream Model for Limited Datasets](https://mlsanity.com/paper/2407.04808/) (2024)
- [Prompt-Based Tuning of Transformer Models for Multi-Center Medical Image Segmentation of Head and Neck Cancer](https://mlsanity.com/paper/2305.18948/) (2023)
- [AI-Assisted Diagnosis for Covid-19 CXR Screening: From Data Collection to Clinical Validation](https://mlsanity.com/paper/2405.11598/) (2024)
- [PRISM: Privacy-preserving Inter-Site MRI Harmonization via Disentangled Representation Learning](https://mlsanity.com/paper/2411.06513/) (2024)
- [Benchmarking and Explaining Deep Learning Cortical Lesion MRI Segmentation in Multiple Sclerosis](https://mlsanity.com/paper/2507.12092/) (2025)
- [Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations](https://mlsanity.com/paper/2605.00904/) (2026)
- [Metadata Supervised Imaging Representations for Modelling and Controlling Acquisition Variability](https://mlsanity.com/paper/2607.11295/) (2026)
- [Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustness](https://mlsanity.com/paper/2608.06613/) (2026)
- [Site Is Decodable Before Pretraining: Negative Controls for Probing Frozen Brain-MRI Foundation Models](https://mlsanity.com/paper/2608.10295/) (2026)
- [Pseudo-Label Guided Multi-Contrast Generalization for Non-Contrast Organ-Aware Segmentation](https://mlsanity.com/paper/2205.05898/) (2022)

## 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.