Download PDFOpen PDF in browser

Analysis of Imbalanced Datasets in the Performance of Deep Learning Approaches for COVID-19 Screening from Chest X-ray Imaging: Impact of Sex and Age Factors

4 pagesPublished: February 16, 2023

Abstract

In this work, we analysed 11 imbalance scenarios with female and male COVID-19 patients present in different proportions for the sex analysis, and 6 scenarios where only one specific age range was used for training for the age factor. In each study, 3 different approaches for automatic COVID-19 screening were used: (I) Normal vs COVID-19, (II) Pneumonia vs COVID-19 and (III) Non-COVID-19 vs COVID-19.
The present study was validated using two representative public chest X-ray datasets, allowing a reliable analysis to support the clinical decision-making process.
The results for the sex-related analysis indicate this factor slightly affects the COVID- 19 deep learning-based systems, although the identified differences are not relevant enough to considerably worsen the system. Regarding the age-related analysis, this factor was observed to be influencing the system in a more consistent way than the sex factor, as it was present in all considered scenarios.

Keyphrases: cad system, chest x ray, covid 19, deep learning

In: Alvaro Leitao and Lucía Ramos (editors). Proceedings of V XoveTIC Conference. XoveTIC 2022, vol 14, pages 174-177.

BibTeX entry
@inproceedings{XoveTIC2022:Analysis_Imbalanced_Datasets_Performance,
  author    = {Lorena Alvarez and Joaquim de Moura and Lucía Ramos and Jorge Novo and Marcos Ortega},
  title     = {Analysis of Imbalanced Datasets in the Performance of Deep Learning Approaches for COVID-19 Screening from Chest X-ray Imaging: Impact of Sex and Age Factors},
  booktitle = {Proceedings of V XoveTIC Conference. XoveTIC 2022},
  editor    = {Alvaro Leitao and Lucía Ramos},
  series    = {Kalpa Publications in Computing},
  volume    = {14},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2515-1762},
  url       = {/publications/paper/NvJG},
  doi       = {10.29007/v25g},
  pages     = {174-177},
  year      = {2023}}
Download PDFOpen PDF in browser