Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients
Chest X-ray images are useful for early COVID-19 diagnosis with the advantage that X-ray devices are already available in health centers and images are obtained immediately. Some datasets containing X-ray images with cases (pneumonia or COVID-19) and controls have been made available to develop mach...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9374968/ |
_version_ | 1811274364916596736 |
---|---|
author | Omar Del Tejo Catala Ismael Salvador Igual Francisco Javier Perez-Benito David Millan Escriva Vicent Ortiz Castello Rafael Llobet Juan-Carlos Perez-Cortes |
author_facet | Omar Del Tejo Catala Ismael Salvador Igual Francisco Javier Perez-Benito David Millan Escriva Vicent Ortiz Castello Rafael Llobet Juan-Carlos Perez-Cortes |
author_sort | Omar Del Tejo Catala |
collection | DOAJ |
description | Chest X-ray images are useful for early COVID-19 diagnosis with the advantage that X-ray devices are already available in health centers and images are obtained immediately. Some datasets containing X-ray images with cases (pneumonia or COVID-19) and controls have been made available to develop machine-learning-based methods to aid in diagnosing the disease. However, these datasets are mainly composed of different sources coming from pre-COVID-19 datasets and COVID-19 datasets. Particularly, we have detected a significant bias in some of the released datasets used to train and test diagnostic systems, which might imply that the results published are optimistic and may overestimate the actual predictive capacity of the techniques proposed. In this article, we analyze the existing bias in some commonly used datasets and propose a series of preliminary steps to carry out before the classic machine learning pipeline in order to detect possible biases, to avoid them if possible and to report results that are more representative of the actual predictive power of the methods under analysis. |
first_indexed | 2024-04-12T23:17:40Z |
format | Article |
id | doaj.art-d9c75879ae434c1bbd124ceb66d22ce0 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-12T23:17:40Z |
publishDate | 2021-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-d9c75879ae434c1bbd124ceb66d22ce02022-12-22T03:12:38ZengIEEEIEEE Access2169-35362021-01-019423704238310.1109/ACCESS.2021.30654569374968Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 PatientsOmar Del Tejo Catala0https://orcid.org/0000-0002-8953-0344Ismael Salvador Igual1https://orcid.org/0000-0001-9269-3737Francisco Javier Perez-Benito2https://orcid.org/0000-0002-6290-5644David Millan Escriva3https://orcid.org/0000-0003-4224-2334Vicent Ortiz Castello4https://orcid.org/0000-0002-4390-6190Rafael Llobet5https://orcid.org/0000-0002-8278-9740Juan-Carlos Perez-Cortes6https://orcid.org/0000-0001-6506-090XInstituto Tecnológico de Informática (ITI), Universitat Politècnica de València, Valencia, SpainInstituto Tecnológico de Informática (ITI), Universitat Politècnica de València, Valencia, SpainInstituto Tecnológico de Informática (ITI), Universitat Politècnica de València, Valencia, SpainInstituto Tecnológico de Informática (ITI), Universitat Politècnica de València, Valencia, SpainInstituto Tecnológico de Informática (ITI), Universitat Politècnica de València, Valencia, SpainInstituto Tecnológico de Informática (ITI), Universitat Politècnica de València, Valencia, SpainInstituto Tecnológico de Informática (ITI), Universitat Politècnica de València, Valencia, SpainChest X-ray images are useful for early COVID-19 diagnosis with the advantage that X-ray devices are already available in health centers and images are obtained immediately. Some datasets containing X-ray images with cases (pneumonia or COVID-19) and controls have been made available to develop machine-learning-based methods to aid in diagnosing the disease. However, these datasets are mainly composed of different sources coming from pre-COVID-19 datasets and COVID-19 datasets. Particularly, we have detected a significant bias in some of the released datasets used to train and test diagnostic systems, which might imply that the results published are optimistic and may overestimate the actual predictive capacity of the techniques proposed. In this article, we analyze the existing bias in some commonly used datasets and propose a series of preliminary steps to carry out before the classic machine learning pipeline in order to detect possible biases, to avoid them if possible and to report results that are more representative of the actual predictive power of the methods under analysis.https://ieeexplore.ieee.org/document/9374968/Deep learningCOVID-19convolutional neural networkschest X-raybiassegmentation |
spellingShingle | Omar Del Tejo Catala Ismael Salvador Igual Francisco Javier Perez-Benito David Millan Escriva Vicent Ortiz Castello Rafael Llobet Juan-Carlos Perez-Cortes Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients IEEE Access Deep learning COVID-19 convolutional neural networks chest X-ray bias segmentation |
title | Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients |
title_full | Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients |
title_fullStr | Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients |
title_full_unstemmed | Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients |
title_short | Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients |
title_sort | bias analysis on public x ray image datasets of pneumonia and covid 19 patients |
topic | Deep learning COVID-19 convolutional neural networks chest X-ray bias segmentation |
url | https://ieeexplore.ieee.org/document/9374968/ |
work_keys_str_mv | AT omardeltejocatala biasanalysisonpublicxrayimagedatasetsofpneumoniaandcovid19patients AT ismaelsalvadorigual biasanalysisonpublicxrayimagedatasetsofpneumoniaandcovid19patients AT franciscojavierperezbenito biasanalysisonpublicxrayimagedatasetsofpneumoniaandcovid19patients AT davidmillanescriva biasanalysisonpublicxrayimagedatasetsofpneumoniaandcovid19patients AT vicentortizcastello biasanalysisonpublicxrayimagedatasetsofpneumoniaandcovid19patients AT rafaelllobet biasanalysisonpublicxrayimagedatasetsofpneumoniaandcovid19patients AT juancarlosperezcortes biasanalysisonpublicxrayimagedatasetsofpneumoniaandcovid19patients |