# The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort study

arXiv: https://arxiv.org/abs/1911.00515 · HTML: https://mlsanity.com/paper/1911.00515/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2019.

## Built on by (most cited first, 30 of 38)

- [Federated Learning Enables Big Data for Rare Cancer Boundary Detection](https://mlsanity.com/paper/2204.10836/) (2022)
- [Probable Domain Generalization via Quantile Risk Minimization](https://mlsanity.com/paper/2207.09944/) (2022)
- [OpenFL: An open-source framework for Federated Learning](https://mlsanity.com/paper/2105.06413/) (2021)
- [An Empirical Framework for Domain Generalization in Clinical Settings](https://mlsanity.com/paper/2103.11163/) (2021)
- [Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial](https://mlsanity.com/paper/2305.04933/) (2023)
- [GaNDLF: A Generally Nuanced Deep Learning Framework for Scalable End-to-End Clinical Workflows in Medical Imaging](https://mlsanity.com/paper/2103.01006/) (2021)
- [Improving Selective Visual Question Answering by Learning from Your Peers](https://mlsanity.com/paper/2306.08751/) (2023)
- [Data Harmonisation for Information Fusion in Digital Healthcare: A State-of-the-Art Systematic Review, Meta-Analysis and Future Research Directions](https://mlsanity.com/paper/2201.06505/) (2022)
- [Fr'echet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets](https://mlsanity.com/paper/2412.01496/) (2024)
- [Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts](https://mlsanity.com/paper/2209.11233/) (2022)
- [The Impact of Scanner Domain Shift on Deep Learning Performance in Medical Imaging: an Experimental Study](https://mlsanity.com/paper/2409.04368/) (2024)
- [Addressing catastrophic forgetting for medical domain expansion](https://mlsanity.com/paper/2103.13511/) (2021)
- [A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation](https://mlsanity.com/paper/2204.02779/) (2022)
- [Diffusion MRI with Machine Learning](https://mlsanity.com/paper/2402.00019/) (2024)
- [Statistical Perspectives on Reliability of Artificial Intelligence Systems](https://mlsanity.com/paper/2111.05391/) (2021)
- [Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study](https://mlsanity.com/paper/2201.11620/) (2022)
- [FedDAR: Federated Domain-Aware Representation Learning](https://mlsanity.com/paper/2209.04007/) (2022)
- [A Systematic Review of Generalization Research in Medical Image Classification](https://mlsanity.com/paper/2403.12167/) (2024)
- [Deepbet: Fast brain extraction of T1-weighted MRI using Convolutional Neural Networks](https://mlsanity.com/paper/2308.07003/) (2023)
- [Three Applications of Conformal Prediction for Rating Breast Density in Mammography](https://mlsanity.com/paper/2206.12008/) (2022)
- [Learn to Ignore: Domain Adaptation for Multi-Site MRI Analysis](https://mlsanity.com/paper/2110.06803/) (2021)
- [Federated brain tumor segmentation: an extensive benchmark](https://mlsanity.com/paper/2410.17265/) (2024)
- [Longitudinal detection of new MS lesions using Deep Learning](https://mlsanity.com/paper/2206.08272/) (2022)
- [Ordinal Classification with Distance Regularization for Robust Brain Age Prediction](https://mlsanity.com/paper/2403.10522/) (2023)
- [CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays](https://mlsanity.com/paper/2103.04590/) (2021)
- [Large-scale Multi-sequence Pretraining for Generalizable MRI Analysis in Versatile Clinical Applications](https://mlsanity.com/paper/2508.07165/) (2025)
- [Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge](https://mlsanity.com/paper/2604.11679/) (2026)
- [Out-of-Distribution Detection and Data Drift Monitoring using Statistical Process Control](https://mlsanity.com/paper/2402.08088/) (2024)
- [An augmentation strategy to mimic multi-scanner variability in MRI](https://mlsanity.com/paper/2103.12595/) (2021)
- [Interpretability Aware Model Training to Improve Robustness against Out-of-Distribution Magnetic Resonance Images in Alzheimer's Disease Classification](https://mlsanity.com/paper/2111.08701/) (2021)

## Abstract (arXiv)

Deep learning (DL) methods have in recent years yielded impressive results in medical imaging, with the potential to function as clinical aid to radiologists. However, DL models in medical imaging are often trained on public research cohorts with images acquired with a single scanner or with strict protocol harmonization, which is not representative of a clinical setting. The aim of this study was to investigate how well a DL model performs in unseen clinical data sets---collected with different scanners, protocols and disease populations---and whether more heterogeneous training data improves generalization. In total, 3117 MRI scans of brains from multiple dementia research cohorts and memory clinics, that had been visually rated by a neuroradiologist according to Scheltens' scale of medial temporal atrophy (MTA), were included in this study. By training multiple versions of a convolutional neural network on different subsets of this data to predict MTA ratings, we assessed the impact of including images from a wider distribution during training had on performance in external memory clinic data. Our results showed that our model generalized well to data sets acquired with similar protocols as the training data, but substantially worse in clinical cohorts with visibly different tissue contrasts in the images. This implies that future DL studies investigating performance in out-of-distribution (OOD) MRI data need to assess multiple external cohorts for reliable results. Further, by including data from a wider range of scanners and protocols the performance improved in OOD data, which suggests that more heterogeneous training data makes the model generalize better. To conclude, this is the most comprehensive study to date investigating the domain shift in deep learning on MRI data, and we advocate rigorous evaluation of DL models on clinical data prior to being certified for deployment.