Communication Dans Un Congrès Année : 2026

Efficient pyramidal analysis of gigapixel images on a decentralized modest computer cluster

Résumé

Analyzing gigapixel images is recognized as computationally demanding. In this paper, we introduce PyramidAI, a technique for analyzing gigapixel images with reduced computational cost. The proposed approach adopts a gradual analysis of the image, beginning with lower resolutions and progressively concentrating on regions of interest for detailed examination at higher resolutions. We investigated two strategies for tuning the accuracy-computation performance trade-off when implementing the adaptive resolution selection, validated against the Camelyon 16 dataset of biomedical images. Our results demonstrate that Pyra-midAI substantially decreases the amount of processed data required for analysis by up to 2.65×, while preserving the accuracy in identifying relevant sections on a single computer. To ensure democratization of gigapixel image analysis, we evaluated the potential to use mainstream computers to perform the computation by exploiting the parallelism potential of the approach. Using a simulator, we estimated the best data distribution and load balancing algorithm according to the number of workers. The selected algorithms were implemented and highlighted the same conclusions in a real-world setting. Analysis time is reduced from more than an hour to a few minutes using 12 modest workers, offering a practical solution for efficient large-scale image analysis.

Fichier principal
Vignette du fichier
2509.02440v1.pdf (1.6 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-05287176 , version 1 (29-09-2025)

Identifiants

Citer

Marie Reinbigler, Rishi Sharma, Rafael Pires, Elisabeth Brunet, Anne-Marie Kermarrec, et al.. Efficient pyramidal analysis of gigapixel images on a decentralized modest computer cluster. 31st International European Conference on Parallel and Distributed Computing (Euro-Par), Aug 2025, Dresden, Germany. pp.298-312, ⟨10.1007/978-3-031-99872-0_21⟩. ⟨hal-05287176⟩
885 Consultations
41 Téléchargements

Altmetric

Partager

  • More