Automated Detection and Forecasting of COVID-19 using Deep Learning Techniques: A Review

arXiv (Cornell University), Journal Year: 2020, Volume and Issue: unknown

Published: Jan. 1, 2020

Coronavirus, or COVID-19, is a hazardous disease that has endangered the health of many people around world by directly affecting lungs. COVID-19 medium-sized, coated virus with single-stranded RNA, and also one largest RNA genomes approximately 120 nm. The X-Ray computed tomography (CT) imaging modalities are widely used to obtain fast accurate medical diagnosis. Identifying from these images extremely challenging as it time-consuming prone human errors. Hence, artificial intelligence (AI) methodologies can be consistent high performance. Among AI methods, deep learning (DL) networks have gained popularity recently compared conventional machine (ML). Unlike ML, all stages feature extraction, selection, classification accomplished automatically in DL models. In this paper, complete survey studies on application techniques for diagnostic segmentation lungs discussed, concentrating works CT images. Additionally, review papers forecasting coronavirus prevalence different parts presented. Lastly, challenges faced detection using directions future research discussed.

Language: Английский

---

Deep Learning-Based Methods for Sentiment Analysis on Nepali COVID-19-Related Tweets

Computational Intelligence and Neuroscience, Journal Year: 2021, Volume and Issue: 2021, P. 1 - 11

Published: Jan. 1, 2021

COVID-19 has claimed several human lives to this date. People are dying not only because of physical infection the virus but also mental illness, which is linked people’s sentiments and psychologies. People’s written texts/posts scattered on web could help understand their psychology state they in during pandemic. In paper, we analyze sentiment based classification tweets collected from social media platform, Twitter, Nepal. For this, we, first, propose use three different feature extraction methods—fastText-based (ft), domain-specific (ds), domain-agnostic (da)—for representation tweets. Among these methods, two methods (“ds” “da”) novel used study. Second, convolution neural networks (CNNs) implement proposed features. Last, ensemble such CNNs models using CNN, works an end-to-end manner, achieve end results. evaluation CNN models, prepare a Nepali Twitter dataset, called NepCOV19Tweets, with 3 classes (positive, neutral, negative). The experimental results dataset show that our possess discriminating characteristics for classification. Moreover, impart robust stable performance Also, can be as benchmark study COVID-19-related analysis language.

Language: Английский

---

An Improved VGG16 Model for Pneumonia Image Classification

Applied Sciences, Journal Year: 2021, Volume and Issue: 11(23), P. 11185 - 11185

Published: Nov. 25, 2021

Image recognition has been applied to many fields, but it is relatively rarely medical images. Recent significant deep learning progress for image raised strong research interest in recognition. First of all, we found the prediction result using VGG16 model on failed pneumonia X-ray Thus, this paper proposes IVGG13 (Improved Visual Geometry Group-13), a modified classification X-rays Open-source thoracic images acquired from Kaggle platform were employed recognition, only few data obtained, and datasets unbalanced after classification, either which can extremely poor trained neural network models. Therefore, augmentation pre-processing compensate low volume poorly balanced datasets. The original without proposed some well-known convolutional networks, such as LeNet AlexNet, GoogLeNet VGG16. In experimental results, rates other evaluation criteria, precision, recall f-measure, evaluated each model. This process was repeated augmented datasets, with greatly improved metrics F1-measure. produced superior outcomes F1-measure compared current best practice networks confirming effectively accuracy.

Language: Английский

---

COVID-19 Case Recognition from Chest CT Images by Deep Learning, Entropy-Controlled Firefly Optimization, and Parallel Feature Fusion

Sensors, Journal Year: 2021, Volume and Issue: 21(21), P. 7286 - 7286

Published: Nov. 2, 2021

In healthcare, a multitude of data is collected from medical sensors and devices, such as X-ray machines, magnetic resonance imaging, computed tomography (CT), so on, that can be analyzed by artificial intelligence methods for early diagnosis diseases. Recently, the outbreak COVID-19 disease caused many deaths. Computer vision researchers support doctors employing deep learning techniques on images to diagnose patients. Various were proposed case classification. A new automated technique using parallel fusion optimization models. The starts with contrast enhancement combination top-hat Wiener filters. Two pre-trained models (AlexNet VGG16) are employed fine-tuned according target classes (COVID-19 healthy). Features extracted fused approach—parallel positive correlation. Optimal features selected entropy-controlled firefly method. classified machine classifiers multiclass vector (MC-SVM). Experiments carried out Radiopaedia database achieved an accuracy 98%. Moreover, detailed analysis conducted shows improved performance scheme.

Language: Английский

---

Deep learning for predicting COVID-19 malignant progression

Medical Image Analysis, Journal Year: 2021, Volume and Issue: 72, P. 102096 - 102096

Published: May 12, 2021

Language: Английский

---

Covid-19 Imaging Tools: How Big Data is Big?

Journal of Medical Systems, Journal Year: 2021, Volume and Issue: 45(7)

Published: June 3, 2021

Language: Английский

---

COVID-19 Detection Empowered with Machine Learning and Deep Learning Techniques: A Systematic Review

Applied Sciences, Journal Year: 2021, Volume and Issue: 11(8), P. 3414 - 3414

Published: April 10, 2021

COVID-19 has infected 223 countries and caused 2.8 million deaths worldwide (at the time of writing this article), death rate is increasing continuously. Early diagnosis COVID patients a critical challenge for medical practitioners, governments, organizations, to overcome rapid spread deadly virus in any geographical area. In situation, previous epidemic evidence on Machine Learning (ML) Deep (DL) techniques encouraged researchers play significant role detecting COVID-19. Similarly, rising scope ML/DL methodologies domain also advocates its detection. This systematic review presents ML DL practiced era predict, diagnose, classify, detect coronavirus. study, data was retrieved from three prevalent full-text archives, i.e., Science Direct, Web Science, PubMed, using search code strategy 16 March 2021. Using professional assessment, among 961 articles by an initial query, only 40 focusing ML/DL-based detection schemes were selected. Findings have been presented as country-wise distribution publications, article frequency, various collection, analyzed datasets, sample sizes, applied techniques. Precisely, study reveals that technique accuracy lay between 80% 100% when The RT-PCR-based model with Support Vector (SVM) exhibited lowest (80%), whereas X-ray-based achieved highest (99.7%) deep convolutional neural network. However, current studies shown anal swab test super accurate virus. Moreover, addresses limitations along detailed discussion prevailing challenges future research directions, which eventually highlight outstanding issues.

Language: Английский

---

Machine Learning-Based Research for COVID-19 Detection, Diagnosis, and Prediction: A Survey

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

Published: May 12, 2022

Language: Английский

---

Deep and Hybrid Learning Technique for Early Detection of Tuberculosis Based on X-ray Images Using Feature Fusion

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(14), P. 7092 - 7092

Published: July 14, 2022

Tuberculosis (TB) is a fatal disease in developing countries, with the infection spreading through direct contact or air. Despite its seriousness, early detection of tuberculosis by means reliable techniques can save patients’ lives. A chest X-ray recommended screening technique for locating pulmonary abnormalities. However, analyzing images to detect abnormalities requires highly experienced radiologists. Therefore, artificial intelligence come into play help radiologists perform an accurate diagnosis at stages TB disease. Hence, this study focuses on applying two AI techniques, CNN and ANN. Furthermore, proposes different approaches systems each diagnose from datasets. The first approach hybridizes models, which are Res-Net-50 GoogLeNet techniques. Prior classification stage, applies principal component analysis (PCA) algorithm reduce features’ dimensionality, aiming extract deep features. Then, SVM used classifying features high accuracy. This hybrid achieved superior results diagnosing based both In contrast, second neural networks (ANN) fused extracted ResNet-50 GoogleNet models combines them gray level co-occurrence matrix (GLCM), discrete wavelet transform (DWT) local binary pattern (LBP) algorithms. ANN When using dataset, ANN, ResNet-50, GLCM, DWT LBP features, accuracy 99.2%, sensitivity 99.23%, specificity 99.41%, AUC 99.78%. Meanwhile, LBP, reached 99.8%, 99.54%, 99.68%, 99.82%. Thus, proposed methods doctors increase chances survival.

Language: Английский

---

PneuNet: deep learning for COVID-19 pneumonia diagnosis on chest X-ray image analysis using Vision Transformer

Medical & Biological Engineering & Computing, Journal Year: 2023, Volume and Issue: 61(6), P. 1395 - 1408

Published: Jan. 31, 2023

Language: Английский

---