Open AccessDetección de Neumonía viral y bacteriana en imágenes de rayos x utilizando redes neuronales artificiales
Author(s) -
Itzel Guadalupe Guerrero-Gasca,
Juan Israel Yañez-Vargas,
J. Quintanilla-Domínguez,
Luis Rey Lara-González,
Arturo Gasca-Ortega
Publication year - 2019
Publication title -
ecorfan journal bolivia
Language(s) - English
Resource type - Journals
ISSN - 2410-4191
DOI - 10.35429/ejb.2019.11.6.9.16
Subject(s) - confusion matrix , artificial intelligence , artificial neural network , confusion , pattern recognition (psychology) , backpropagation , classifier (uml) , pixel , pneumonia , computer science , medicine , psychology , psychoanalysis
This paper presents the experiments and results on the viraland bacterial pneumonia identification, which were obtainedby means of image processing techniques and artificialneural networks. The objective of this research is to reducethe patient’s waiting time to obtain the result of the x-raysdiagnosis of a pulmonary disease of pneumonia. At the timeof this writing, pneumonia is considered the most commoncause of infant mortality in the world, responsible for 15%of all deaths in children under 5 years. To obtain theclassifier model we start from the detection in thepulmonary region through digital image processing andobtaining the characteristics in the segmented images,discriminating against those that provide a diagnosisthrough Gray Level Co-occurrence Matrix (GLCM).Finally, those features are used as the description in theclassification of images such as: healthy, viral pneumoniaand bacterial pneumonia. We use a total of eight features:autocorrelation, contrast, cluster prominence, variancecluster shade, sum of entropy, difference of entropy andnumber of pixels. These characteristics were used to modeland train an artificial neural network Backpropagation,obtaining results that are presented in their confusion matrixalong with the accuracy percentage obtained.