# The Impact of Scanner Domain Shift on Deep Learning Performance in Medical Imaging: an Experimental Study

arXiv: https://arxiv.org/abs/2409.04368 · HTML: https://mlsanity.com/paper/2409.04368/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 6 Sep 2024.

## Builds on (most cited first, 15 of 15)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge](https://mlsanity.com/paper/1912.01054/) (2019)
- [The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort study](https://mlsanity.com/paper/1911.00515/) (2019)
- [Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation](https://mlsanity.com/paper/2103.12857/) (2021)
- [Highly accurate model for prediction of lung nodule malignancy with CT scans](https://mlsanity.com/paper/1802.01756/) (2018)
- [A Strong Baseline for Domain Adaptation and Generalization in Medical Imaging](https://mlsanity.com/paper/1904.01638/) (2019)
- [Reverse Engineering Breast MRIs: Predicting Acquisition Parameters Directly from Images](https://mlsanity.com/paper/2303.04911/) (2023)
- [Deep Learning for Breast MRI Style Transfer with Limited Training Data](https://mlsanity.com/paper/2301.02069/) (2023)

## Built on by (most cited first, 16 of 16)

- [Fr'echet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets](https://mlsanity.com/paper/2412.01496/) (2024)
- [Predicting brain tumour enhancement from non-contrast MR imaging with artificial intelligence: a multi-cohort retrospective diagnostic accuracy study](https://mlsanity.com/paper/2508.16650/) (2025)
- [DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization via Disentangled Anatomy-Contrast Representations](https://mlsanity.com/paper/2512.07674/) (2025)
- [Parameter Efficient Fine-tuning for Domain-specific Gastrointestinal Disease Recognition](https://mlsanity.com/paper/2604.10451/) (2026)
- [JANUS: Anatomy-Conditioned Gating for Robust CT Triage Under Distribution Shift](https://mlsanity.com/paper/2605.13813/) (2026)
- [EAGT: Echocardiography Augmentation for Generalisability and Transferability](https://mlsanity.com/paper/2605.16427/) (2026)
- [Field strength-dependent performance variability in deep learning-based analysis of magnetic resonance imaging](https://mlsanity.com/paper/2512.22176/) (2025)
- [Projection Guided Personalized Federated Learning for Low Dose CT Denoising](https://mlsanity.com/paper/2603.13422/) (2026)
- [What Are We Really Measuring? Rethinking Dataset Bias in Web-Scale Natural Image Collections via Unsupervised Semantic Clustering](https://mlsanity.com/paper/2604.13610/) (2026)
- [AI Approach for MRI-only Full-Spine Vertebral Segmentation and 3D Reconstruction in Paediatric Scoliosis](https://mlsanity.com/paper/2604.17846/) (2026)
- [Orientation-Aware Unsupervised Domain Adaptation for Brain Tumor Classification Across Multi-Modal MRI](https://mlsanity.com/paper/2605.03490/) (2026)
- [Hyper-FSAD: Training-Free and Language-Free Few-Shot Anomaly Detection via Sparse Hyper Matching](https://mlsanity.com/paper/2605.10628/) (2026)
- [Temporally Consistent and Controllable Video Generation of 2D Cine CMR via Latent Space Motion Modeling](https://mlsanity.com/paper/2606.14759/) (2026)
- [Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis](https://mlsanity.com/paper/2606.26764/) (2026)
- [Domain Shift in Echocardiography: Interpretable Quantification and Prediction of Cross-Dataset Left Ventricular Segmentation](https://mlsanity.com/paper/2607.19643/) (2026)
- [TotalSynth: Robust Whole-Body Synthetic CT from MRI and CBCT](https://mlsanity.com/paper/2609.13838/) (2026)

## Abstract (arXiv)

Purpose: Medical images acquired using different scanners and protocols can differ substantially in their appearance. This phenomenon, scanner domain shift, can result in a drop in the performance of deep neural networks which are trained on data acquired by one scanner and tested on another. This significant practical issue is well-acknowledged, however, no systematic study of the issue is available across different modalities and diagnostic tasks. Materials and Methods: In this paper, we present a broad experimental study evaluating the impact of scanner domain shift on convolutional neural network performance for different automated diagnostic tasks. We evaluate this phenomenon in common radiological modalities, including X-ray, CT, and MRI. Results: We find that network performance on data from a different scanner is almost always worse than on same-scanner data, and we quantify the degree of performance drop across different datasets. Notably, we find that this drop is most severe for MRI, moderate for X-ray, and quite small for CT, on average, which we attribute to the standardized nature of CT acquisition systems which is not present in MRI or X-ray. We also study how injecting varying amounts of target domain data into the training set, as well as adding noise to the training data, helps with generalization. Conclusion: Our results provide extensive experimental evidence and quantification of the extent of performance drop caused by scanner domain shift in deep learning across different modalities, with the goal of guiding the future development of robust deep learning models for medical image analysis.