Artificial Intelligence for Medical Image Analysis in Low-Resource Settings: A Systematic Review
Authors:
- Tanya AkumuTATanya Akumu
- Victor M. CampelloVCVictor M. Campello
- Lidia GarruchoLGLidia Garrucho
- Vien Ngoc DangVDVien Ngoc Dang
- Thomas KellerTKThomas Keller
- Xue ZhaoXZXue Zhao
- Emmah Ng'Ang'AENEmmah Ng'Ang'A
- María J. Ledesma-CarbayoMLMaría J. Ledesma-Carbayo
- Marius G. LinguraruMLMarius G. Linguraru
- Karim LekadirKLKarim Lekadir
Preprint
- 10 October 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Artificial intelligence (AI) for medical image analysis is increasingly being developed for low-resource settings, where specialist expertise, imaging equipment, labelled data, and computing resources may be limited. We systematically reviewed 189 studies published between January 2021 and January 2026 to examine how these constraints relate to imaging modalities, clinical applications, and AI methods in low-resource settings. Each study was also assessed against 15 criteria adapted from the FUTURE-AI principles for trustworthy AI. Shortages of clinical expertise were the most common constraint, and portable or lower-cost imaging was widely used. Transfer learning was the most frequent technical strategy (59%), followed by data augmentation (54%) and efficient model design (36%). Medical-image pretraining and self-supervised learning were each used in 4% of studies, and model compression in 3%. Applications were concentrated in retinal disease, pulmonary disease, antenatal care, parasitic diseases, and cervical screening. Beyond these technical and clinical patterns, the trustworthy AI assessment showed a clear gap between documenting how systems were developed and demonstrating how they performed under relevant local conditions. Subgroup performance was evaluated in 24% of studies, intended users or realistic working conditions in 25%, and model explanations with intended users in 4%. Consistent with this gap, among 15 studies that reported the same model and metric during development and in the local setting, 12 performed worse locally. Future research should prioritise representative local evaluation, intended-user assessment, demonstrated resource suitability, and reproducible research practices.Keywords
All Related Versions
This publication has 99 references indexed in Scilit:
- Evidence on the Utility of Artificial Intelligence in the Interpretation of Diagnostic Radiological Images in Low and Middle-Income Countries: A Scoping ReviewAcademic Radiology, 2025
- A perspective on AI implementation in medical imaging in LMICs: challenges, priorities, and strategiesEuropean Radiology, 2025
- Adaptive Frame Selection for Gestational Age Estimation from Blind Sweep Fetal Ultrasound Videos2025
- Artificial intelligence system for predicting areal bone mineral density from plain X-raysOsteoporosis International, 2025
- Generative Diffusion Model Bootstraps Zero-Shot Classification of Fetal Ultrasound Images in Underrepresented African Populations2024
- Diagnostic Accuracy of an Integrated AI Tool to Estimate Gestational Age From Blind Ultrasound SweepsJAMA, 2024
- Internal validation of Automated Visual Evaluation (AVE) on smartphone images for cervical cancer screening in a prospective study in ZambiaCancer Medicine, 2024
- External Validation of a Retinopathy of Prematurity Screening Model Using Artificial Intelligence in 3 Low- and Middle-Income PopulationsJAMA Ophthalmology, 2022
- Truncating fined-tuned vision-based models to lightweight deployable diagnostic tools for SARS-CoV-2 infected chest X-rays and CT-scansMultimedia Tools and Applications, 2022
- Deep learning in medical image registration: a surveyMachine Vision and Applications, 2020