EUVIMEDEUVIMED entdecken
Crossref

Quadruplet loss and SqueezeNets for Covid-19 detection from Chest-X ray

Pranshav Gajjar, Naishadh Mehta, Pooja Shah

Computer Science Journal of Moldova · 2022

DOI: 10.56415/csjm.v30.12 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Science Journal of Moldova, 2022. Verfasst von Pranshav Gajjar und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Coronavirus Pandemic triggered by SARS-CoV-2 has wreaked havoc on the planet and is expanding exponentially. While scanning methods, including CT scans and chest X-rays, are commonly used, artificial intelligence implementations are also deployed for COVID-based pneumonia detection. Due to image biases in X-ray data, bilateral filtration and Histogram Equalization are used followed by lung segmentation by a U-Net, which successfully segmented 83.2\% of the collected dataset. The segmented lungs are fed into a Quadruplet Network with SqueezeNet encoders for increased computational efficiency and high-level embeddings generation. The embeddings are computed using a Multi-Layer Perceptron and visualized by T-SNE (T-Distributed Stochastic Neighbor Embedding) scatterplots. The proposed research results in a 94.6\% classifying accuracy which is 2\% more than the baseline Convolutional Neural Network and a 90.2\% decrease in prediction time.

Zitieren

APA

Gajjar, P., Mehta, N., & Shah, P. (2022). Quadruplet loss and SqueezeNets for Covid-19 detection from Chest-X ray. Computer Science Journal of Moldova. https://doi.org/10.56415/csjm.v30.12

Vancouver

Gajjar P, Mehta N, Shah P. Quadruplet loss and SqueezeNets for Covid-19 detection from Chest-X ray. Computer Science Journal of Moldova. 2022. doi:10.56415/csjm.v30.12

BibTeX
@article{Gajjar2022,
  author = {Gajjar, Pranshav and Mehta, Naishadh and Shah, Pooja},
  title = {Quadruplet loss and SqueezeNets for Covid-19 detection from Chest-X ray},
  journal = {Computer Science Journal of Moldova},
  year = {2022},
  doi = {10.56415/csjm.v30.12}
}
Kostenlos starten →