Hybrid Deep Convolutional Generative Adversarial Network (DCGAN) and Xtreme Gradient Boost for X-ray Image Augmentation and Detection DOI Creative Commons
Ahmad Hoirul Basori, Sharaf J. Malebary, Sami Alesawi

et al.

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(23), P. 12725 - 12725

Published: Nov. 27, 2023

The COVID-19 pandemic has exerted a widespread influence on global scale, leading numerous nations to prepare for the endemicity of COVID-19. polymerase chain reaction (PCR) swab test emerged as prevailing technique identifying viral infections within current pandemic. Following this, application chest X-ray imaging in individuals provides an alternate approach evaluating existence infection. However, it is imperative further boost quality collected pictures via additional data augmentation. aim this paper provide automated analysis using server processing with deep convolutional generative adversarial network (DCGAN). proposed methodology aims improve overall image scans. integration learning Xtreme Gradient Boosting DCGAN processed server. training model employed work based Inception V3 model, which combined XGradient Boost. results obtained from procedure were quite interesting: had accuracy rate 98.86%, sensitivity score 99.1%, and recall 98.7%.

Language: Английский

COVID-19 image classification using deep learning: Advances, challenges and opportunities DOI Open Access
Priya Aggarwal, Narendra Kumar Mishra, Binish Fatimah

et al.

Computers in Biology and Medicine, Journal Year: 2022, Volume and Issue: 144, P. 105350 - 105350

Published: March 3, 2022

Language: Английский

Citations

118
An IoT-Based Deep Learning Framework for Early Assessment of Covid-19 DOI Open Access
Imran Ahmed, Awais Ahmad, Gwanggil Jeon

et al.

IEEE Internet of Things Journal, Journal Year: 2020, Volume and Issue: 8(21), P. 15855 - 15862

Published: Oct. 27, 2020

Advancement in the Internet of Medical Things (IoMT), along with machine learning, deep and artificial intelligence techniques, initiated a world possibilities healthcare. It has an extensive range applications: when connected to Internet, ordinary medical devices sensors can collect valuable data, techniques utilize this data give insight symptoms, trends enable remote care. Recently, Covid-19 pandemic outbreak caused death large number people. This virus infected millions people, still, rate people is increasing day by day. Researchers are endeavoring images learning-based models for detection Covid-19. Various have been presented that X-Ray chest However, importance regional-based convolutional neural networks (CNNs) currently confined. Thus, research aimed introduce IoT-based learning framework early assessment reduce working pressure experts/radiologists contribute control. A model, i.e., faster regions CNNs (Faster-RCNN) ResNet-101, applied on detection. uses region proposal network (RPN) perform By employing we achieve accuracy 98%. Therefore, believe system might be capable order assist expert/radiologist, verify toward

Language: Английский

Citations

99
Current limitations to identify COVID-19 using artificial intelligence with chest X-ray imaging DOI Creative Commons
José Daniel López-Cabrera, Rubén Orozco‐Morales, Jorge Armando Portal-Díaz

et al.

Health and Technology, Journal Year: 2021, Volume and Issue: 11(2), P. 411 - 424

Published: Feb. 5, 2021

The scientific community has joined forces to mitigate the scope of current COVID-19 pandemic. early identification disease, as well evaluation its evolution is a primary task for timely application medical protocols. use images chest provides valuable information specialists. Specifically, X-ray have been focus many investigations that apply artificial intelligence techniques automatic classification this disease. results achieved date on subject are promising. However, some these contain errors must be corrected obtain appropriate models clinical use. This research discusses problems found in literature COVID-19. It evident most reviewed works an incorrect protocol applied, which leads overestimating results.

Language: Английский

Citations

80
Viral outbreaks detection and surveillance using wastewater-based epidemiology, viral air sampling, and machine learning techniques: A comprehensive review and outlook DOI Open Access
Omar M. Abdeldayem, Areeg M. Dabbish,

Mahmoud M. Habashy

et al.

The Science of The Total Environment, Journal Year: 2021, Volume and Issue: 803, P. 149834 - 149834

Published: Aug. 21, 2021

Language: Английский

Citations

68
COVID-19 Detection in Chest X-ray Images Using a New Channel Boosted CNN DOI Creative Commons
Saddam Hussain Khan, Anabia Sohail, Asifullah Khan

et al.

Diagnostics, Journal Year: 2022, Volume and Issue: 12(2), P. 267 - 267

Published: Jan. 21, 2022

COVID-19 is a respiratory illness that has affected large population worldwide and continues to have devastating consequences. It imperative detect at the earliest opportunity limit span of infection. In this work, we developed new CNN architecture STM-RENet interpret radiographic patterns from X-ray images. The proposed block-based employs idea split-transform-merge in way. regard, convolutional block STM implements region edge-based operations separately, as well jointly. systematic use edge implementations combination with helps exploring homogeneity, intensity inhomogeneity, boundary-defining features. learning capacity further enhanced by developing CB-STM-RENet exploits channel boosting learns textural variations effectively screen images exploited generating auxiliary channels two additional CNNs using Transfer Learning, which are then concatenated original STM-RENet. A significant performance improvement shown comparison standard on three datasets, especially stringent CoV-NonCoV-15k dataset. good detection rate (97%), accuracy (96.53%), reasonable F-score (95%) technique suggest it can be adapted infected patients.

Language: Английский

Citations

65
COVID-19 classification of X-ray images using deep neural networks DOI Creative Commons
Daphna Keidar,

Daniel Yaron,

Elisha Goldstein

et al.

European Radiology, Journal Year: 2021, Volume and Issue: 31(12), P. 9654 - 9663

Published: May 29, 2021

In the midst of coronavirus disease 2019 (COVID-19) outbreak, chest X-ray (CXR) imaging is playing an important role in diagnosis and monitoring patients with COVID-19. We propose a deep learning model for detection COVID-19 from CXRs, as well tool retrieving similar according to model's results on their CXRs. For training evaluating our model, we collected CXRs inpatients hospitalized four different hospitals.In this retrospective study, 1384 frontal confirmed imaged between March August 2020, 1024 matching non-COVID before pandemic, were used build classifier detecting positive The consists ensemble pre-trained neural networks (DNNS), specifically, ReNet34, ReNet50¸ ReNet152, vgg16, enhanced by data augmentation lung segmentation. further implemented nearest-neighbors algorithm that uses DNN-based image embeddings retrieve images most given image.Our achieved accuracy 90.3%, (95% CI: 86.3-93.7%) specificity 90% 84.3-94%), sensitivity 90.5% 85-94%) test dataset comprising 15% (350/2326) original images. AUC ROC curve 0.96 0.93-0.97).We provide models, trained evaluated can assist medical efforts reduce staff workload handling COVID-19.• A machine was able detect tested rate above 90%. • created finding existing CXR characteristics CXR, embeddings.

Language: Английский

Citations

58
Machine Learning-Based Research for COVID-19 Detection, Diagnosis, and Prediction: A Survey DOI Open Access
Yassine Meraihi, Asma Benmessaoud Gabis, Seyedali Mirjalili

et al.

SN Computer Science, Journal Year: 2022, Volume and Issue: 3(4)

Published: May 12, 2022

Language: Английский

Citations

51
Covid-MANet: Multi-task attention network for explainable diagnosis and severity assessment of COVID-19 from CXR images DOI
Ajay Sharma, Pramod Kumar Mishra

Pattern Recognition, Journal Year: 2022, Volume and Issue: 131, P. 108826 - 108826

Published: June 6, 2022

Language: Английский

Citations

43
Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets DOI Creative Commons
Xingsi Xue,

C. Seelammal,

Ghaida Muttashar Abdulsahib

et al.

Bioengineering, Journal Year: 2023, Volume and Issue: 10(3), P. 363 - 363

Published: March 16, 2023

Recently, various methods have been developed to identify COVID-19 cases, such as PCR testing and non-contact procedures chest X-rays computed tomography (CT) scans. Deep learning (DL) artificial intelligence (AI) are critical tools for early accurate detection of COVID-19. This research explores the different DL techniques identifying pneumonia on medical CT radiography images using ResNet152, VGG16, ResNet50, DenseNet121. The ResNet framework uses scan with accuracy precision. automates optimum model architecture training parameters. Transfer approaches also employed solve content gaps shorten duration. An upgraded VGG16 deep transfer is applied perform multi-class classification X-ray imaging tasks. Enhanced has proven recognize three types radiographic 99% accuracy, typical pneumonia. validity performance metrics proposed were validated publicly available data sets. suggested outperforms competing in diagnosing primary outcomes this result an average F-score (95%, 97%). In event healthy viral infections, more efficient than existing methodologies coronavirus detection. created appropriate recognition pre-training. traditional strategies categorization illnesses.

Language: Английский

Citations

36
Dual-path information enhanced pyramid Unet for COVID-19 lung infection segmentation DOI
Zhang Yan, Qi Mao,

Yi Tian

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 142, P. 109977 - 109977

Published: Jan. 5, 2025

Language: Английский

Citations

1