A Robust End-to-End CNN Architecture for Efficient COVID-19 Prediction form X-ray Images with Imbalanced Data

被引：0

作者：

Oraibi Z.A. ^{[1
]}

Albasri S. ^{[2
]}

机构：

[1] Department of Computer Science, College of Education for Pure Sciences, Unviersity of Basrah, Basrah

[2] Electrical Engineering Department, College of Engineering, Mustansiriyah University, Baghdad

来源：

Informatica (Slovenia) | 2023年 / 47卷 / 07期

关键词：

Coronavirus Infection; COVID-19; Data Augmentation; Deep Learning; Pandemic;

D O I：

10.31449/INF.V47I7.4790

中图分类号：

学科分类号：

摘要：

The world witnessed big changes in 2019 when a new virus called coronavirus affected the lives of hundreds of millions of individuals and led to huge disruptions in healthcare systems. Early prediction of this virus was a top priority to limit its damage and save countless lives. Many advanced artificial intelligence technologies like deep learning have used chest X-ray images for this task. In this paper, a new CNN architecture is introduced to classify chest X-ray images. The new model is applied on a 256 × 256 × 3 input image and consists of six convolutional blocks. In addition, we improve the performance of our model by adding regularization techniques, including batch normalization and dropout. We tested our model using an imbalanced COVID-19 dataset of 5000 COVID and Non-COVID images. Four metrics were used to test the new model: sensitivity, specificity, precision, and F1 score. In experiments, we achieved a sensitivity rate of 97%, a specificity rate of 99.32%, a precision rate of 99.90%, and F1 score of 97.73% despite being provided with fewer training images. In conclusion, we proposed a light deep learning model capable of achieving high prediction accuracy that outperformed the best deep learning methods in terms of specificity and achieved high sensitivity result. © 2023 Slovene Society Informatika. All rights reserved.

引用

页码：115 / 126

页数：11

共 29 条

[11] Chowdhury N. K., Rahman M., Kabir M. A., Et al., Pdcovidnet: a parallel-dilated convolutional neural network architecture for detecting covid-19 from chest x-ray images, Health information science and systems, 8, 1, pp. 1-14, (2020)
[12] Reshi A. A., Rustam F., Mehmood A., Alhossan A., Alrabiah Z., Ahmad A., Alsuwailem H., Choi G. S., An efficient cnn model for covid-19 disease detection based on x-ray image classification, Complexity, (2021)
[13] Pathan S., Siddalingaswamy P., Ali T., Automated detection of covid-19 from chest x-ray scans using an optimized cnn architecture, Applied Soft Computing, 104, (2021)
[14] Ahuja S., Panigrahi B. K., Dey N., Rajinikanth V., Gandhi T. K., Deep transfer learning-based automated detection of covid-19 from lung ct scan slices, Applied Intelligence, 51, 1, pp. 571-585, (2021)
[15] El-Rashidy N., El-Sappagh S., Islam S., El-Bakry H. M., Abdelrazek S., End-to-end deep learning framework for coronavirus (covid-19) detection and monitoring, Electronics, 9, 9, (2020)
[16] Wang D., Mo J., Zhou G., Xu L., Liu Y., An efficient mixture of deep and machine learning models for covid-19 diagnosis in chest x-ray images, PloS one, 15, 11, (2020)
[17] Khan I. U., Aslam N., A deep-learning-based framework for automated diagnosis of covid-19 using x-ray images, Information, 11, 9, (2020)
[18] Keidar D., Yaron D., Goldstein E., Shachar Y., Blass A., Charbinsky L., Aharony I., Lifshitz L., Lumelsky D., Neeman Z., Et al., Covid-19 classification of x-ray images using deep neural networks, European radiology, 31, 12, pp. 9654-9663, (2021)
[19] Cohen J. P., Morrison P., Dao L., Roth K., Duong T. Q., Ghassemi M., Covid-19 image data collection: Prospective predictions are the future, (2020)
[20] Khan A., Sohail A., Zahoora U., Qureshi A. S., A survey of the recent architectures of deep convolutional neural networks, Artificial intelligence review, 53, 8, pp. 5455-5516, (2020)

← 1 2 3 →