EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Efficiency in the classification of chest X-ray images through generative parallelization of the Neural Architecture Search

Felix Mejía Cajicá, John Anderson García Henao, Carlos Jaime Barrios Hernandéz, Michel Riveill

ACI Avances en Ciencias e Ingenierías · 2025

DOI: 10.18272/9bp4dz26 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACI Avances en Ciencias e Ingenierías, 2025. Verfasst von Felix Mejía Cajicá und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Explore GenNAS for chest X-ray classification in lung diseases, leveraging novel parallel training methods for enhanced accuracy and efficiency. Medical image classification for pulmonary pathologies from chest X-rays is traditionally time-consuming. GenNAS, using GPT-4's generative capabilities, automates optimal architecture learning from data. This study investigates parallelization and generative algorithms to optimize neural network architectures for chest X-ray classification, analyzing their impact on the NAS algorithm using the ChexPert dataset. The study uses the CheXpert dataset with 224,316 chest X-rays to classify five lung disease pathologies. GenNASXRays evaluates 6561 architecture possibilities in an 8-layer search space, with AUC-ROC and Precision-Recall plots as metrics. Training on 187,641 images, the sequential algorithm took 190.2 hours for an AUC-ROC of 0.869. In parallel execution on two GPUs, an AUC-ROC of 0.87 was achieved in 127.09 hours, highlighting the efficiency of parallelization.

Zitieren

APA

Cajicá, F. M., Henao, J. A. G., Hernandéz, C. J. B., & Riveill, M. (2025). Efficiency in the classification of chest X-ray images through generative parallelization of the Neural Architecture Search. ACI Avances en Ciencias e Ingenierías. https://doi.org/10.18272/9bp4dz26

Vancouver

Cajicá FM, Henao JAG, Hernandéz CJB, Riveill M. Efficiency in the classification of chest X-ray images through generative parallelization of the Neural Architecture Search. ACI Avances en Ciencias e Ingenierías. 2025. doi:10.18272/9bp4dz26

BibTeX
@article{Cajic2025,
  author = {Cajicá, Felix Mejía and Henao, John Anderson García and Hernandéz, Carlos Jaime Barrios and Riveill, Michel},
  title = {Efficiency in the classification of chest X-ray images through generative parallelization of the Neural Architecture Search},
  journal = {ACI Avances en Ciencias e Ingenierías},
  year = {2025},
  doi = {10.18272/9bp4dz26}
}
Kostenlos starten →