A Simplified Approach to Covid-19 Pneumonia Classification

• Ngonidzashe Mathew Kanyangarara ^[1] ; Rajendra Kumar ^[1]
  1. [1] Sharda University

     Sharda University

     IN.36.141.7279602, India

     
• Localización: Academic Journal of Health Sciences: Medicina Balear, ISSN-e 2255-0560, Vol. 38, Nº. 5, 2023, págs. 117-121
• Idioma: inglés
• DOI: 10.3306/AJHS.2023.38.05.117
• Títulos paralelos:
  • Un enfoque simplificado para la clasificación de neumonía por Covid-19
• Enlaces
  • Texto completo (pdf)
• Resumen
  • español

    Introducción: El brote de Covid-19 ha desencadenado un problema mundial, especialmente en Asia y América. La Organización Mundial de la Salud (OMS) declaró la enfermedad pandémica el 20 de marzo de 2020. Llegó en oleadas, y la mayoría de los países del mundo ya han experimentado dos oleadas y están a punto de experimentar la tercera. El objetivo de este estudio es construir y certificar un sistema de Diagnóstico Asistido por Ordenador (CADx) para distinguir entre pacientes COVID-19 positivos y personas No-Covid.

    Métodos: Se utilizan imágenes de radiografía de tórax (CXR) para realizar la clasificación de la neumonía Covid-19. De los conjuntos de datos públicos GitHub se obtuvieron 2295 imágenes CXR que incluyen 712 COVID-19 positivos y 1583 casos normales. El sistema CADx propuesto utiliza un modelo de Red Neuronal Convencional (CNN) para la argumentación de datos y la CNN se construye, compila y entrena con la ayuda de Tensor flow y Keras. Para la evaluación, el conjunto de datos se divide en tres categorías: Entrenamiento, Prueba y Validación.

    Resultados: Se evaluó la precisión de los tres conjuntos y los resultados de Entrenamiento, Validación y Prueba fueron del 97,77%, 97,81% y 97,72%, respectivamente.

    Conclusiones: El estudio presentado puede crear un sistema preciso de Diagnóstico Asistido por Ordenador para las dos categorías de clasificación.

  • English

    Introduction: The outbreak of Covid-19 has triggered a worldwide problem, especially in Asia and America. The World Health Organization (WHO) declared the sickness a pandemic on March 20, 2020. It arrived in waves, and most countries around the world have now experienced two waves and are on the approach of experiencing the third. The goal of this study is to build up and certify a Computer-Aided Diagnosis (CADx) system for distinguishing between COVID-19 positive patients and Non-Covid Patients people.

    Methods: Chest X-ray (CXR) images are used to accomplish Covid-19 Pneumonia Classification. From public datasets GitHub 2295 CXR images were obtained which include 712 COVID-19 positive and 1583 normal cases. The proposed CADx system utilized a Conventional Neural Network (CNN) model for data argumentation and CNN is built, compiled and trained with help of Tensor flow and Keras. For the sake of appraisal, the dataset is estranged into three categories: Train, Test and Validation.

    Results: The three sets accuracy was evaluated and the results for Training, Validation and Test were observed as 97.77%, 97.81% and 97.72%, respectively.

    Conclusion: The presented study can create a precise Computer-Aided Diagnosis system for the two categories of classification.

• Referencias bibliográficas
  • Abdullahi U I, Mehmet O, Sertan S, Fadi A, Polycarp S Y. Pneumonia Classification Using Deep Learning from Chest X-ray Images During COVID-19....
  • Chen N, Zhou M, Dong X, Qu J, Gong F, Han Y, et al. Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia...
  • Ching T, Himmelstein DS, Beaulieu-Jones BK, Kalinin AA, Do BT, Way GP, et al. Opportunities and obstacles for deep learning in biology and...
  • Cohen J. COVID-19 Chest X-ray Dataset. https://github.com/ieee8023/covid-chestxray-dataset
  • Esteva A, Kuprel B, Roberto AN, Justin K, Susan MS, Helen MB, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature,...
  • Gupta J K, Kumar R. An efficient ANN Based approach for Latent Fingerprint Matching. International Journal of Computer Application, 2010; 7(10):...
  • Kallianos K, Mongan J, Antani S, Henry T, Taylor A, Abuya J, et al. How far have we come? Artificial intelligence for chest radiograph interpretation....
  • Kalembo V S, Ngonidzashe M K, Prince T P, Gupta V, Kumar R.. A Deep Learning Model for Face Recognition in Presence of Mask. Acta Informatica Malaysia,...
  • Kumar R, Singh R C, Khokher R. A systematic review of palm and dorsal hand vein recognition techniques. Academic Journal of Health Sciences, 2022;...
  • Kumar R, Singh R C, Kant S. Dorsal Hand Vein Recognition Using Very Deep Learning. Macromolecular Symposia, 2021; 397(2000244): 1-13.
  • Kumar R, Singh R C, Kant S. Dorsal Hand Vein-Biometric Recognition using Convolution Neural Network. Adv. in Intell. Sys. and Comp. DOI: 10.1007/978-981-15-5113-0_92.
  • Mohammad T I, Md A A, Ahmed T M, Khalid A. Abnormality detection and localization in chest x-rays using deep convolutional neural networks. 2017;...
  • Okeke S, Mangal S, Uchenna J M, Do-Un J. An Efficient Deep Learning Approach to Pneumonia Classification in Healthcare. Journal of Healthcare Engineering,...
  • Peng H, Seyoun P, Rongkai Y, Junghoon L, Linda C C, Cheng T L, et al. Added value of computer-aided CT image features for early lung cancer diagnosis...
  • Varun G, Lily P, Marc C, Martin C S, Derek W, Arunachalam N, et al W. Development and validation of a deep learning algorithm for detection...