[ Système de détection de la pneumonie dans les images radiographiques thoraciques ]
Volume 38, Issue 4, February 2023, Pages 860–872
ILUNGA MBUYAMBA Elisée1 and MUSENGA SHAMBUYI Plamedi2
1 Institut Supérieur de Techniques Appliquées (ISTA), Kinshasa, RD Congo
2 Institut Supérieur de Techniques Appliquées (ISTA), Kinshasa, RD Congo
Original language: French
Copyright © 2023 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
The dark and worrying health picture characterized by the revelations made by international organizations concerning pneumonia challenged us as researchers. It is in this perspective that we decided to make our contribution to this problem by presenting a system for pneumonia detection in chest x-ray images. To achieve this goal, we used an approach based on deep learning to properly identify pathological or non-pathological radiographs by setting up a convolutional neural network called Xception. Two optimization algorithms were selected, namely Adam and SGD. The setting of hyperparameters of our convolutional neural network led us to a promising result compared to the size of our dataset. In conclusion, the obtained results in our experiments showed that the SGD optimization algorithm reached the best result of 92% accuracy on new data with a learning rate of 0.001 for 20 epochs.
Author Keywords: Pneumonia, CNN, Xception, SGD, x-ray.
Volume 38, Issue 4, February 2023, Pages 860–872
ILUNGA MBUYAMBA Elisée1 and MUSENGA SHAMBUYI Plamedi2
1 Institut Supérieur de Techniques Appliquées (ISTA), Kinshasa, RD Congo
2 Institut Supérieur de Techniques Appliquées (ISTA), Kinshasa, RD Congo
Original language: French
Copyright © 2023 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
The dark and worrying health picture characterized by the revelations made by international organizations concerning pneumonia challenged us as researchers. It is in this perspective that we decided to make our contribution to this problem by presenting a system for pneumonia detection in chest x-ray images. To achieve this goal, we used an approach based on deep learning to properly identify pathological or non-pathological radiographs by setting up a convolutional neural network called Xception. Two optimization algorithms were selected, namely Adam and SGD. The setting of hyperparameters of our convolutional neural network led us to a promising result compared to the size of our dataset. In conclusion, the obtained results in our experiments showed that the SGD optimization algorithm reached the best result of 92% accuracy on new data with a learning rate of 0.001 for 20 epochs.
Author Keywords: Pneumonia, CNN, Xception, SGD, x-ray.
Abstract: (french)
Le tableau sanitaire sombre et inquiétant caractérisé par les révélations faites par les organisations internationales concernant la pneumonie nous a interpellés en tant que chercheur. C’est dans cette perspective que nous avons décidé d’apporter notre contribution à cette problématique en présentant un système de détection des pneumonies sur les images radiographiques thoraciques. Pour atteindre cet objectif, nous avons utilisé une approche basée sur le deep learning pour bien identifier les radiographies pathologiques ou non pathologiques en mettant en place un réseau de neurones convolutifs appelé Xception. Deux algorithmes d’optimisation ont été sélectionnés, à savoir Adam et SGD. Le paramétrage des hyperparamètres de notre réseau de neurones convolutifs nous a conduit à des résultats prometteurs par rapport à la taille de notre jeu de données. En conclusion, les résultats obtenus dans nos expériences ont montré que l’algorithme d’optimisation SGD a atteint le meilleur résultat de 92% de précision sur les nouvelles données avec un taux d’apprentissage de 0,001 pour 20 époques.
Author Keywords: Pneumonie, CNN, Xception, SGD, Radiographie.
How to Cite this Article
ILUNGA MBUYAMBA Elisée and MUSENGA SHAMBUYI Plamedi, “System for pneumonia detection in chest X-ray images,” International Journal of Innovation and Applied Studies, vol. 38, no. 4, pp. 860–872, February 2023.
