Pneumonia detection based on transfer learning and a combination of VGG19 and a CNN Built from scratch

Autor:	Dahmane, Oussama, Khelifi, Mustapha, Beladgham, Mohammed, Kadri, Ibrahim
Rok vydání:	2021
Předmět:	Control and Optimization Object detection Computer Networks and Communications Hardware and Architecture Signal Processing BBHE Convolutional neural network Deep learning Electrical and Electronic Engineering CLAHE VGG19 Transfer learning Information Systems
Zdroj:	Indonesian Journal of Electrical Engineering and Computer Science. 24:1469
ISSN:	2502-4760 2502-4752
DOI:	10.11591/ijeecs.v24.i3.pp1469-1480
Popis:	In this paper, to categorize and detect pneumonia from a collection of chest X-ray picture samples, we propose a deep learning technique based on object detection, convolutional neural networks, and transfer learning. The proposed model is a combination of the pre-trained model (VGG19) and our designed architecture. The Guangzhou Women and Children's Medical Center in Guangzhou, China provided the chest X-ray dataset used in this study. There are 5,000 samples in the data set, with 1,583 healthy samples and 4,273 pneumonia samples. Preprocessing techniques such as contrast limited adaptive histogram equalization (CLAHE) and brightness preserving bi-histogram equalization was also used (BBHE) to improve accuracy. Due to the imbalance of the data set, we adopted some training techniques to improve the learning process of the samples. This network achieved over 99% accuracy due to the proposed architecture that is based on a combination of two models. The pre-trained VGG19 as feature extractor and our designed convolutional neural network (CNN).
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7b3d645f9786842be0280c5f949f47bc https://doi.org/10.11591/ijeecs.v24.i3.pp1469-1480 Zobrazit plný text záznamu