EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive Inference Stage Partitioning for Mobile Cataract Screening Across Edge Pipelines and Clinical Deployment Workflows

Elliot Ward, Grace Spencer, Grace Murray, Sayaka Kameda

International Journal of Information and Communication Technology Trends · 10.06.2026 · 6 (1) · 331-340

DOI: 10.66525/ijictt101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Information and Communication Technology Trends, online erschienen am 10.06.2026. Verfasst von Elliot Ward und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The global prevalence of cataracts represents a significant burden on public health systems, particularly in low-resource and remote rural environments where specialized ophthalmological care is chronically scarce. Mobile health applications utilizing deep learning have emerged as promising solutions for early detection and triage. However, executing complex convolutional neural networks on resource-constrained mobile devices poses severe challenges regarding latency, energy consumption, and thermal management. Conversely, fully cloud-based inference paradigms are heavily reliant on stable, high-bandwidth network connectivity, which is frequently unavailable in target deployment regions. This paper presents a novel framework for adaptive inference stage partitioning within mobile cataract screening pipelines. By conceptualizing the deep learning model as a directed acyclic graph of computational layers, our system dynamically determines the optimal partition point between the mobile edge device and the cloud server. This decision is continuously informed by real-time profiling of available network bandwidth, device battery status, and local computational load. We propose a comprehensive architecture that seamlessly migrates intermediate feature representations across the network, minimizing overall end-to-end latency while preserving diagnostic accuracy. Extensive evaluation across diverse simulated network conditions and mobile hardware profiles demonstrates that the adaptive partitioning approach significantly outperforms both purely edge-based and purely cloud-based paradigms. The findings provide a critical foundation for deploying robust, scalable, and energy-efficient artificial intelligence diagnostics in unpredictable real-world clinical environments

Zitieren

APA

Ward, E., Spencer, G., Murray, G., & Kameda, S. (2026). Adaptive Inference Stage Partitioning for Mobile Cataract Screening Across Edge Pipelines and Clinical Deployment Workflows. International Journal of Information and Communication Technology Trends, 6(1), 331-340. https://doi.org/10.66525/ijictt101

Vancouver

Ward E, Spencer G, Murray G, Kameda S. Adaptive Inference Stage Partitioning for Mobile Cataract Screening Across Edge Pipelines and Clinical Deployment Workflows. International Journal of Information and Communication Technology Trends. 2026;6(1):331-340. doi:10.66525/ijictt101

BibTeX
@article{Ward2026,
  author = {Ward, Elliot and Spencer, Grace and Murray, Grace and Kameda, Sayaka},
  title = {Adaptive Inference Stage Partitioning for Mobile Cataract Screening Across Edge Pipelines and Clinical Deployment Workflows},
  journal = {International Journal of Information and Communication Technology Trends},
  year = {2026},
  volume = {6},
  number = {1},
  pages = {331--340},
  doi = {10.66525/ijictt101}
}
Kostenlos starten →