article · Discover Data
Breast cancer remains a leading cause of mortality among women in low- and middle-income countries, where shortages of radiologists and diagnostic resources persist. An analysis of 45 publications from 2018 to 2025 compares deep learning architectures suited to resource-limited settings, focusing on lightweight options such as MobileNet and EfficientNet alongside standard convolutional and hybrid networks. MobileNet achieves 89 to 92 percent diagnostic accuracy while requiring minimal memory and processing capacity, making it viable for offline edge hardware like smartphones. EfficientNet achieves higher accuracy of 91 to 94 percent but demands cloud connectivity because of its larger size. Both approaches substantially reduce false positive and false negative results compared to older computer-aided detection tools. Nevertheless, current research is largely retrospective, relies on non-local reference datasets, and requires prospective trials and locally sourced data before clinical adoption.
Breast cancer diagnosis in resource-constrained regions is severely hindered by a shortage of trained radiologists and inconsistent internet infrastructure. Identifying deep learning models that function offline on low-cost hardware could expand access to automated screening in remote clinics, helping healthcare providers identify tumours earlier and reduce diagnostic errors without depending on expensive hospital facilities.
The findings could inform software applications deployed on portable edge hardware, such as smartphones, for frontline healthcare workers in rural or low-resource clinics. However, commercial implementation remains at an early stage. Real-world translation requires prospective clinical trials, regulatory pathways, privacy-preserving frameworks, and validation on locally collected patient imaging before these systems can be safely brought to market.
AI-generated from the published abstract. Always read the original work before citing.
Breast cancer remains a leading cause of mortality among women in low- and middle-income countries (LMICs), compounded by fewer radiologists available and resources for diagnosis. A narrative review that summarizes 45 peer-reviewed publications to date from 2018 to 2025 is presented for deep learning (DL) models for mammography detection for breast cancer, targeting low-resource-critical architectures for development in LMIC settings. We compare convolutional neural networks (CNNs), hybrid CNN-support vector machine (SVM) models, recurrent/LSTM networks, and lightweight architectures such as MobileNet and EfficientNet. In quantitative synthesis the reported diagnostic accuracy for MobileNet is between 89 and 92%, supported with 128 MB RAM and 0.3 GFLOPs. Therefore it is appropriate for offline edge devices (smartphones, NVIDIA Jetson Nano). EfficientNet achieves 91–94% accuracy—though it requires stable internet to enable cloud deployment, due to its greater parameter size (5.3 million). Both architectures reduce false positives by 7 to 69% and false negatives by 9% compared to traditional computer-aided detection, though most evidence is retrospective. The most important contributions from this review are: (1) a quantitative comparison of efficiency for edge versus cloud deployment, (2) detection of dataset bias (no LMIC-specific validation exists), and (3) practical recommendations regarding infrastructure, regulatory pathways, and privacy-preserving federated learning. Limitations include cross-study heterogeneity in datasets (CBIS-DDSM, INbreast, MIAS) and evaluation protocols. We conclude that MobileNet and EfficientNet provide good trade-offs for LMICs but call for prospective trials and locally curated datasets before clinical implementation.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s44248-026-00116-z
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
