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

Authors

  • Elliot Ward Faculty of Engineering, UNSW Sydney, Sydney, Australia Author
  • Grace Spencer Faculty of Engineering, UNSW Sydney, Sydney, Australia Author
  • Grace Murray Faculty of Engineering, UNSW Sydney, Sydney, Australia Author
  • Sayaka Kameda Faculty of Engineering, UNSW Sydney, Sydney, Australia Author

DOI:

https://doi.org/10.66525/ijictt101

Keywords:

Mobile Health, Edge Computing, Deep Learning, Cataract Screening, Adaptive Partitioning

Abstract

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

Downloads

Download data is not yet available.

References

1. Yang, Z., Hu, D., Guo, Q., Zuo, L., & Ji, W. (2023). Visual E 2 C: AI-driven visual end-edge-cloud architecture for 6G in low-carbon smart cities. IEEE Wireless Communications, 30(3), 204-210.

2. Yang, Y., Ma, X., Li, C., Zheng, Z., Zhang, Q., Huang, G., ... & Zhao, Q. (2021). Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 34, 10299-10312.

3. Fang, Z., Yang, G., Lyu, W., Hong, Z., Zhong, S., Zuo, W., ... & Zhang, D. (2025). Cellular Infrastructure Sharing for Network Robustness: A Citywide Empirical Study. IEEE Transactions on Mobile Computing.

4. Yang, Z., Ji, W., Guo, Q., & Wang, Z. (2023, October). Javp: Joint-aware video processing with edge-cloud collaboration for dnn inference. In Proceedings of the 31st ACM International Conference on Multimedia (pp. 9152-9160).

5. Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.

6. Zhou, D. (2025, December). M-VP2: Microservice-Oriented Vulnerability Patch Planning-A Cost-Aware Approachusing Multi-Agent Reinforcement Learning. In 2025 5th International Conference on Computer, Internet of Things and Control Engineering (CITCE) (pp. 248-254). IEEE.

7. Yang, Z., Liang, B., & Ji, W. (2021). An intelligent end–edge–cloud architecture for visual IoT-assisted healthcare systems. IEEE internet of things journal, 8(23), 16779-16786.

8. Chen, Y., Zhao, C., & Gao, Y. (2025). Blockchain applications in health insurance: a review of applications, challenges, and prospects. Frontiers in Blockchain, 8, 1699290.

9. Chen, L., Jiang, X., Xiao, P., Liu, X., & Haardt, M. (2025). Structured tensor decomposition for fdd massive mimo downlink channel reconstruction. IEEE Transactions on Signal Processing, 73, 887-902.

10. Burrows, M. (2006). The Chubby lock service for loosely-coupled distributed systems. In Proceedings of OSDI.

11. Hu, Y., Yang, Z., Zhao, C., & Ji, W. (2026, May). Adaptive guidance semantically enhanced via multimodal llm for edge-cloud object detection. In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 12962-12966). IEEE.

12. Zaharia, M., Chowdhury, M., Franklin, M. J., Shenker, S., & Stoica, I. (2012). Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In Proceedings of NSDI.

13. Luo, H., Li, Q., Cheng, H., Li, W., Sun, W., Zhao, W., & Liu, Z. (2025). A²Tformer: Addressing temporal bias and non-stationarity in transformer-based IoT time series classification. IEEE Internet of Things Journal, 12(20), 42198–42213.

14. Zhao, Y., & Han, Z. (2025, December). Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model. In 2025 7th International Academic Exchange Conference on Science and Technology Innovation (IAECST) (pp. 89-94). IEEE.

15. Tian, Y., & Yang, Z. (2026, May). SAEC: scene-aware enhanced edge-cloud collaborative industrial vision inspection with multimodal LLM. In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 19747-19751). IEEE.

16. Yang, W., Qin, Y., Yi, Z., & Yang, Y. (2019, May). Content-based hyperbolic routing and push mechanism in named data networking. In ICC 2019-2019 IEEE International Conference on Communications (ICC) (pp. 1-6). IEEE.

17. Yang, W., Qin, Y., Jiang, Z., & Chu, X. (2021, June). Traffic Management for Distributed Machine Learning in RDMA-enabled Data Center Networks. In ICC 2021-IEEE International Conference on Communications (pp. 1-6). IEEE.

18. Qu, Q., Lu, S., Shang, L., Jung, S., Liang, Q., & Pan, C. (2025, August). Fast and Energy-Efficient Analog Accelerator for Vision Transformer. In 2025 IEEE 68th International Midwest Symposium on Circuits and Systems (MWSCAS) (pp. 827-831). IEEE.

19. Wuyang Zhang and Shichao Pei. 2026. Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool

Use. arXiv:2604.05432 [cs.CR] doi:10.48550/arXiv.2604.05432

20. Yang, Z., Ji, W., Guo, Q., Zhao, J., Zhao, C., Zhang, X., ... & You, Y. (2026). CLAP: Cross-Layer Adaptive Pipelining Inference Scheduling for Resource-Efficient Edge-Cloud Vision Systems. ACM Transactions on Architecture and Code Optimization.

21. Yang, Z., Ji, W., & Wang, Z. (2024). Adaptive joint configuration optimization for collaborative inference in edge-cloud systems. Science China Information Sciences, 67(4), 149103.

22. Shen, B., Wang, Y., Shang, D., & Ning, T. (2026). Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking. Publication date: 2026-06-04.

23. Sun, L., Wang, W., Yuan, T., Mi, L., Dai, H., Liu, Y., & Fu, X. (2024, May). BiSwift: Bandwidth orchestrator for multi-stream video analytics on edge. In IEEE INFOCOM 2024-IEEE Conference on Computer Communications (pp. 1181-1190). IEEE.

24. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.

25. Yang, W., Qin, Y., & Li, R. (2022). A network-embedding-based approach for scalable network navigability in content-centric social IoT. IEEE Internet of Things Journal, 9(17), 16418-16428.

26. Zhou, D. (2026). AI-Driven Hybrid SAST–DAST–SCA–IAST Framework for Risk-Based Vulnerability Prioritization in Microservice Architectures.

27. Li, Q., Li, L., Liu, Z., Sun, W., Li, W., Li, J., & Zhao, W. (2025). Cloud-edge collaboration for industrial Internet of Things: Scalable neurocomputing and rolling-horizon optimization. IEEE Internet of Things Journal, 12(12), 19929–19943.

Downloads

Published

2026-06-10