A Systematic Review of Cross-Population Shifts in Medical Imaging Analysis with Deep Learning
Top Cited Papers
Open Access
- 4 March 2026
- journal article
- review article
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (3) , 76
Abstract
Deep learning has achieved expert-level performance in medical imaging analysis. However, models often fail to generalize across patient populations due to cross-population domain shifts, distributional differences arising from demographic variability, variations in imaging protocols, scanner hardware, and differences in disease prevalence. This challenge limits the real-world deployment and can increase health inequities. This review systematically examines the nature, causes, and impact of cross-population domain shift in deep learning-based medical imaging analysis. We analyzed 50 peer-reviewed studies from 2020 to 2025, evaluating the proposed methodologies for handling population shifts, the datasets employed, and the metrics used to assess performance. Our findings demonstrate that performance degradation ranged from 10–25% when models were tested on unseen populations, emphasizing the substantial impact of domain shifts on model generalizability. The literature reveals that mitigation strategies broadly fall into two categories: data-centric approaches, such as augmentation and harmonization, and model-centric approaches, including domain adaptation, transfer learning, adversarial learning, multi-task learning, and continual learning. While domain adaptation and transfer learning are the most widely used, their performance gains across populations remain modest, ranging from 5–15%, and are not supported by external validation. Our synthesis reveals a significant reliance on large, publicly available datasets from limited regions, with an underrepresentation of data from low- and middle-income countries. Evaluation practices are inconsistent, with few studies employing standardized external test sets. This review provides a structured taxonomy of mitigation techniques, a refined analysis of domain shift characteristics, and an in-depth critique of methodological challenges. We highlight the urgent need for more geographically and demographically inclusive datasets, adaptable modeling techniques, and standardized evaluation protocols to enable accurate and equitable AI-driven diagnostics across diverse populations. Finally, we outline future research directions to guide the development of robust, generalizable, and fair models for medical imaging analysis.Keywords
All Related Versions
Funding Information
- Spanish Ministry of Science, Innovation, and Universities project (PID2022-138703OB-I00)
- Gobierno de Aragón (ECU/1871/2023 PROY-B50-24)
- Carlos III Health Institute Network (RD24/0007/0022)
- Government of Aragon COS2MOS research group T64 23R
This publication has 160 references indexed in Scilit:
- C2‐GAN: Content‐consistent generative adversarial networks for unsupervised domain adaptation in medical image segmentationMedical Physics, 2022
- Deep Generative Medical Image Harmonization for Improving Cross‐Site Generalization in Deep Learning PredictorsJournal of Magnetic Resonance Imaging, 2021
- Deep Learning Pitfall: Impact of Novel Ultrasound Equipment Introduction on Algorithm Performance and the Realities of Domain AdaptationJournal of Ultrasound in Medicine, 2021
- Deep Learning in Medical Image Analysis2020
- TUNA-Net: Task-Oriented UNsupervised Adversarial Network for Disease Recognition in Cross-domain Chest X-rays2019
- Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data2019
- Trends in Use of Medical Imaging in US Health Care Systems and in Ontario, Canada, 2000-2016JAMA, 2019
- Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images2018
- Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-Ray Segmentation2018
- Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With DiabetesJAMA, 2017