Romanian Journal of Information Science and Technology (ROMJIST)

An open – access publication

  |  HOME  |   GENERAL INFORMATION  |   ROMJIST ON-LINE  |  KEY INFORMATION FOR AUTHORS  |   COMMITTEES  |  

ROMJIST is a publication of Romanian Academy,
Section for Information Science and Technology

Editor – in – Chief:
Academician Dan Dascalu

Secretariate (office):
Adriana Neagu
Adress for correspondence: romjist@nano-link.net (after 1st of January, 2019)

Editing of the printed version: Mihaela Marian (Publishing House of the Romanian Academy, Bucharest)

Technical editor
of the on-line version:
Lucian Milea (University POLITEHNICA of Bucharest)

Sponsors:
• National Institute for R & D
in Microtechnologies
(IMT Bucharest), www.imt.ro
• Association for Generic
and Industrial Technologies (ASTEGI), www.astegi.ro

ROMJIST Volume 23, No. S, 2020, pp. S117-S129, Paper no. 658/2020
 

Houssam BENBRAHIM, Hanaâ HACHIMI and Aouatif AMINE
Deep Transfer Learning with Apache Spark to Detect COVID-19 in Chest X-ray Images

ABSTRACT: A chest X-ray test is one of the most important and recurrent medical imaging examinations. It is the first imaging technique that represents a significant role in the diagnosis of SARS-CoV-2 disease. Automatic classification of 2019-nCoV using X-ray images is a major request that can help doctors to make the best decisions. In this paper, we adopted, developed, and validated a Deep Transfer Learning (DTL) method using Convolutional Neural Network (CNN) based models InceptionV3 and ResNet50 with Apache Spark framework for the classification of COVID-19 in chest X-ray images collected from Kaggle repository. High accuracy was obtained by our model in the detection of COVID-19 X-ray images 99.01% by the pre-trained InceptionV3 model and 98.03% for the ResNet50 model.

KEYWORDS: COVID-19, SARS-CoV-2, 2019-nCoV, chest X-ray images, deep transfer learning, convolutional neural network, CNN, apache spark, InceptionV3, ResNet50

Read full text (pdf)






  |  HOME  |   GENERAL INFORMATION  |   ROMJIST ON-LINE  |  KEY INFORMATION FOR AUTHORS  |   COMMITTEES  |