EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Computational efficiency and scalability analysis of deep learning for diabetic retinopathy on ARM Grace superchip

Thiago Da Silva Araújo, Beatriz Schaan, Carla Maria Dal Sasso, Philippe O.A. Navaux

Journal of Parallel and Distributed Computing · 2027-01 · 219 · 105371

DOI: 10.1016/j.jpdc.2026.105371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Parallel and Distributed Computing, 2027-01. Verfasst von Thiago Da Silva Araújo und 3 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FAPERGS, FAPESP, CAPES.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic retinopathy (DR) is a leading cause of preventable vision loss, and deep learning models can automate its screening from retinal fundus images. In networks such as the Brazilian Unified Health System, specialist shortages delay diagnosis, and both diagnostic accuracy and computational efficiency matter. Two questions shape practical deployment: which convolutional neural network (CNN) architecture to pick, and how to run it efficiently on modern hardware. This paper extends our previous work with two additions: a distributed multi-node training experiment complemented by a TensorFlow XPlane execution profile, and a SimGrid discrete-event simulation calibrated on the physical runs. Predictive performance is now reported through AUC together with the specificity obtained at a fixed 95% sensitivity operating point, which brings the evaluation closer to how a screening pipeline is actually deployed. We benchmark 38 pretrained CNN architectures on a Brazilian DR dataset. MobileNet offers the best overall trade-off: relative to InceptionV3, it improves AUC by 3%, achieves a specificity of 0.67 versus 0.58, and reduces energy, model size, and training time by 77%, 85%, and 83%, respectively. A multi-objective hyperparameter study over activation function, optimizer, and input resolution further reduces energy and time without hurting predictive quality. It confirms an input size of 300 × 300 as the efficiency sweet spot. We then study the tuned MobileNet on the Grace Superchip. A thread sweep on one node identifies an 18–36-thread band where speedup and energy jointly optimize, achieving about 20 × speedup and 88% energy savings before scheduling and memory pressure dominate. Distributed training across two Grace nodes with TensorFlow MultiWorkerMirroredStrategy on a 6.13 × larger dataset reaches a 1.93 × speedup at 96.5% scaling efficiency, halves training time, adds less than 1% to total energy, and preserves both AUC and specificity. A TensorFlow XPlane profile of the distributed runs shows that 97% of the active time is spent in computation and only 0.74% in inter-node communication, which explains the near-linear scaling. A SimGrid simulation calibrated on the two physical configurations projects efficiency to about 74% at four nodes and 54% at eight nodes and beyond, and identifies the gRPC/10 Gbps Ethernet transport as the main bottleneck at larger scale. These results indicate that efficient DL for DR depends jointly on model choice, the clinical operating point at which the model is evaluated, and the system-level execution strategy chosen for the target hardware.

Förderung

  • FAPERGS
  • FAPESP
  • CAPES
  • CNPq

Zitieren

APA

Araújo, T. D. S., Schaan, B., Sasso, C. M. D., & Navaux, P. O. (2027). Computational efficiency and scalability analysis of deep learning for diabetic retinopathy on ARM Grace superchip. Journal of Parallel and Distributed Computing, 219, 105371. https://doi.org/10.1016/j.jpdc.2026.105371

Vancouver

Araújo TDS, Schaan B, Sasso CMD, Navaux PO. Computational efficiency and scalability analysis of deep learning for diabetic retinopathy on ARM Grace superchip. Journal of Parallel and Distributed Computing. 2027;219:105371. doi:10.1016/j.jpdc.2026.105371

BibTeX
@article{Arajo2027,
  author = {Araújo, Thiago Da Silva and Schaan, Beatriz and Sasso, Carla Maria Dal and Navaux, Philippe O.A.},
  title = {Computational efficiency and scalability analysis of deep learning for diabetic retinopathy on ARM Grace superchip},
  journal = {Journal of Parallel and Distributed Computing},
  year = {2027},
  volume = {219},
  pages = {105371},
  doi = {10.1016/j.jpdc.2026.105371}
}
Kostenlos starten →