Review on COVID‐19 diagnosis models based on machine learning and deep learning approaches

Expert Systems, Journal Year: 2021, Volume and Issue: 39(3)

Published: July 28, 2021

COVID-19 is the disease evoked by a new breed of coronavirus called severe acute respiratory syndrome 2 (SARS-CoV-2). Recently, has become pandemic infecting more than 152 million people in over 216 countries and territories. The exponential increase number infections rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) machine (ML), which can assist healthcare sector providing quick precise diagnosis. this paper provides comprehensive review most recent DL ML for studies are published from December 2019 until April 2021. In general, includes 200 that been carefully selected publishers, IEEE, Springer Elsevier. We classify research tracks into two categories: present public datasets established extracted different countries. measures used to evaluate methods comparatively analysed proper discussion provided. conclusion, diagnosing outbreak prediction, SVM widely mechanism, CNN mechanism. Accuracy, sensitivity, specificity measurements previous studies. Finally, will guide community on upcoming development inspire their works future development. This

Language: Английский

---

Detection and analysis of COVID-19 in medical images using deep learning techniques

Scientific Reports, Journal Year: 2021, Volume and Issue: 11(1)

Published: Oct. 4, 2021

Abstract The main purpose of this work is to investigate and compare several deep learning enhanced techniques applied X-ray CT-scan medical images for the detection COVID-19. In paper, we used four powerful pre-trained CNN models, VGG16, DenseNet121, ResNet50,and ResNet152, COVID-19 binary classification task. proposed Fast.AI ResNet framework was designed find out best architecture, pre-processing, training parameters models largely automatically. accuracy F1-score were both above 96% in diagnosis using images. addition, transfer overcome insufficient data improve time. multi-class tasks performed by utilizing VGG16 architecture. High 99% achieved from pneumonia. validity algorithms assessed on well-known public datasets. methods have better results than other related literature. our opinion, can help virologists radiologists make a faster struggle against outbreak

Language: Английский

---

A New Deep Hybrid Boosted and Ensemble Learning-Based Brain Tumor Analysis Using MRI

Sensors, Journal Year: 2022, Volume and Issue: 22(7), P. 2726 - 2726

Published: April 1, 2022

Brain tumor analysis is essential to the timely diagnosis and effective treatment of patients. Tumor challenging because morphology factors like size, location, texture, heteromorphic appearance in medical images. In this regard, a novel two-phase deep learning-based framework proposed detect categorize brain tumors magnetic resonance images (MRIs). first phase, deep-boosted features space ensemble classifiers (DBFS-EC) scheme effectively MRI from healthy individuals. The feature achieved through customized well-performing convolutional neural networks (CNNs), consequently, fed into machine learning (ML) classifiers. While second new hybrid fusion-based brain-tumor classification approach proposed, comprised both static dynamic with an ML classifier different types. are extracted region-edge net (BRAIN-RENet) CNN, which able learn inconsistent behavior various tumors. contrast, by using histogram gradients (HOG) descriptor. effectiveness validated on two standard benchmark datasets, were collected Kaggle Figshare contain types tumors, including glioma, meningioma, pituitary, normal Experimental results suggest that DBFS-EC detection outperforms accuracy (99.56%), precision (0.9991), recall (0.9899), F1-Score (0.9945), MCC (0.9892), AUC-PR (0.9990). scheme, based fusion spaces BRAIN-RENet HOG, outperform state-of-the-art methods significantly terms (0.9913), (0.9906), (99.20%), (0.9909) CE-MRI dataset.

Language: Английский

---

Automated detection and forecasting of COVID-19 using deep learning techniques: A review

Neurocomputing, Journal Year: 2024, Volume and Issue: 577, P. 127317 - 127317

Published: Jan. 26, 2024

Language: Английский

---

A Survey of Deep Learning Techniques for the Analysis of COVID-19 and their usability for Detecting Omicron

Journal of Experimental & Theoretical Artificial Intelligence, Journal Year: 2023, Volume and Issue: 36(8), P. 1779 - 1821

Published: Jan. 12, 2023

The Coronavirus (COVID-19) outbreak in December 2019 has drastically affected humans worldwide, creating a health crisis that infected millions of lives and devastated the global economy. COVID-19 is ongoing, with emergence many new strains. Deep learning (DL) techniques have proven helpful efficiently analysing delineating infectious regions radiological images. This survey paper draws taxonomy deep for detecting infection radiographic imaging modalities Chest X-Ray, Computer Tomography. DL are broadly categorised into classification, segmentation, multi-stage approaches diagnosis at image region-level analysis. These further classified as pre-trained custom-made Convolutional Neural Network architectures. Furthermore, discussion drawn on datasets, evaluation metrics, commercial platforms provided detection. In end, brief look paid to emerging ideas, gaps existing research, challenges developing diagnostic techniques. provides insight promising areas research likely guide community upcoming development COVID-19. will pave way accelerate designing customised DL-based tools effectively dealing variants challenges.

Language: Английский

---

Brain Tumor MRI Classification Using a Novel Deep Residual and Regional CNN

Biomedicines, Journal Year: 2024, Volume and Issue: 12(7), P. 1395 - 1395

Published: June 23, 2024

Brain tumor classification is essential for clinical diagnosis and treatment planning. Deep learning models have shown great promise in this task, but they are often challenged by the complex diverse nature of brain tumors. To address challenge, we propose a novel deep residual region-based convolutional neural network (CNN) architecture, called Res-BRNet, using magnetic resonance imaging (MRI) scans. Res-BRNet employs systematic combination regional boundary-based operations within modified spatial blocks. The blocks extract homogeneity, heterogeneity, boundary-related features tumors, while significantly capture local global texture variations. We evaluated performance on challenging dataset collected from Kaggle repositories, Br35H, figshare, containing various categories, including meningioma, glioma, pituitary, healthy images. outperformed standard CNN models, achieving excellent accuracy (98.22%), sensitivity (0.9811), F1-score (0.9841), precision (0.9822). Our results suggest that promising tool classification, with potential to improve efficiency

Language: Английский

---

COVID-19 detection in chest X-ray images using deep boosted hybrid learning

Computers in Biology and Medicine, Journal Year: 2021, Volume and Issue: 137, P. 104816 - 104816

Published: Aug. 29, 2021

Language: Английский

---

Deep convolutional neural network and emotional learning based breast cancer detection using digital mammography

Computers in Biology and Medicine, Journal Year: 2021, Volume and Issue: 132, P. 104318 - 104318

Published: March 14, 2021

Language: Английский

---

Application of CycleGAN and transfer learning techniques for automated detection of COVID-19 using X-ray images

Pattern Recognition Letters, Journal Year: 2021, Volume and Issue: 153, P. 67 - 74

Published: Dec. 3, 2021

Language: Английский

---

IoT malware detection architecture using a novel channel boosted and squeezed CNN

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Sept. 15, 2022

Interaction between devices, people, and the Internet has given birth to a new digital communication model, internet of things (IoT). The integration smart devices constitute network introduces many security challenges. These connected have created blind spot, where cybercriminals can easily launch attacks compromise using malware proliferation techniques. Therefore, detection is lifeline for securing IoT against cyberattacks. This study addresses challenge in by proposing CNN-based architecture (iMDA). proposed iMDA modular design that incorporates multiple feature learning schemes blocks including (1) edge exploration smoothing, (2) multi-path dilated convolutional operations, (3) channel squeezing boosting CNN learn diverse set features. local structural variations within classes are learned Edge smoothing operations implemented split-transform-merge (STM) block. operation used recognize global structure patterns. At same time, merging helped regulate complexity get maps. performance evaluated on benchmark dataset compared with several state-of-the architectures. shows promising capacity achieving accuracy: 97.93%, F1-Score: 0.9394, precision: 0.9864, MCC: 0. 8796, recall: 0.8873, AUC-PR: 0.9689 AUC-ROC: 0.9938. strong discrimination suggests may be extended android-based Elf files compositely future.

Language: Английский

---