Antonio Quintero-Rincón, Ricardo Di-Pasquale, Karina Quintero-Rodríguez, Hadj Batatia
Abstract
Despite tremendous efforts devoted to the area, image texture analysis is still an open research field. This paper presents an algorithm and experimental results demonstrating the feasibility of developing automated tools to detect abnormal X-ray images based on tissue attenuation.
Introduction
Image texture analysis, quantification, and recognition are active research topics in biomedical imaging, computer vision, and pattern recognition. In the biomedical context, texture arises from the micro-and-macro-structural patterns of biological tissues [1]. Physicians are trained to visually interpret texture information across various imaging modalities, such as radiographic X-rays.
Materials and methods
The Kaggle public database COVID-19 Radiography Dataset [28] was considered for experimentation purposes. The dataset consists of chest X-ray images with 3616 COVID-19 positive cases, 6012 lung opacity cases (non-COVID lung infection), 1345 viral pneumonia cases (non-COVID infection) along with 10192 normal cases.
Results & Discussion
This section reports the evaluation results of the proposed method using the previously introduced database. The dataset comprises chest X-ray images distributed as follows: 3 , 616 COVID-19, 1 , 345 viral pneumonia, 6 , 012 lung opacity, and 10 , 192 normal cases. Each chest X-ray image has a size of N × K (where N = K = 299).
Conclusion
This work proposed an original method to classify chest X-ray images corresponding to different diseases, such as COVID-19, viral pneumonia, lung opacity, and normal. The proposed method is based on two features estimated using an SVD decomposition.
Citation: Quintero-Rincón A, Di-Pasquale R, Quintero-Rodríguez K, Batatia H (2025) Computer-based quantitative image texture analysis using multi-collinearity diagnosis in chest X-ray images. PLoS ONE 20(4): e0320706. https://doi.org/10.1371/journal.pone.0320706
Editor: Khan Bahadar Khan, Islamia University of Bahawalpur: The Islamia University of Bahawalpur Pakistan, PAKISTAN
Received: December 12, 2024; Accepted: February 23, 2025; Published: April 14, 2025
Copyright: © 2025 Quintero-Rincón et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: All chest X-ray images files are available from the Kaggle public database https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database
Funding: The author(s) received no specific funding for this work.
Competing interests: The authors have declared that no competing interests exist.
