Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 2.790
Filter
Add filters

Year range
1.
Eur J Med Chem ; 244: 114803, 2022 Dec 15.
Article in English | MEDLINE | ID: covidwho-2104848

ABSTRACT

SARS-CoV-2 3CL protease is one of the key targets for drug development against COVID-19. Most known SARS-CoV-2 3CL protease inhibitors act by covalently binding to the active site cysteine. Yet, computational screens against this enzyme were mainly focused on non-covalent inhibitor discovery. Here, we developed a deep learning-based stepwise strategy for selective covalent inhibitor screen. We used a deep learning framework that integrated a directed message passing neural network with a feed-forward neural network to construct two different classifiers for either covalent or non-covalent inhibition activity prediction. These two classifiers were trained on the covalent and non-covalent 3CL protease inhibitors dataset, respectively, which achieved high prediction accuracy. We then successively applied the covalent inhibitor model and the non-covalent inhibitor model to screen a chemical library containing compounds with covalent warheads of cysteine. We experimentally tested the inhibition activity of 32 top-ranking compounds and 12 of them were active, among which 6 showed IC50 values less than 12 µM and the strongest one inhibited SARS-CoV-2 3CL protease with an IC50 of 1.4 µM. Further investigation demonstrated that 5 of the 6 active compounds showed typical covalent inhibition behavior with time-dependent activity. These new covalent inhibitors provide novel scaffolds for developing highly active SARS-CoV-2 3CL covalent inhibitors.

2.
Computers and Electrical Engineering ; JOUR: 108479,
Article in English | ScienceDirect | ID: covidwho-2104658

ABSTRACT

Recent studies have shown that computed tomography (CT) scan images can characterize COVID-19 disease in patients. Several deep learning (DL) methods have been proposed for diagnosis in the literature, including convolutional neural networks (CNN). But, with inefficient patient classification models, the number of 'False Negatives' can put lives at risk. The primary objective is to improve the model so that it does not reveal 'Covid' as 'Non-Covid'. This study uses Dense-CNN to categorize patients efficiently. A novel loss function based on cross-entropy has also been used to improve the CNN algorithm's convergence. The proposed model is built and tested on a recently published large dataset. Extensive study and comparison with well-known models reveal the effectiveness of the proposed method over known methods. The proposed model achieved a prediction accuracy of 93.78%, while false-negative is only 6.5%. This approach's significant advantage is accelerating the diagnosis and treatment of COVID-19.

3.
BMC Med Inform Decis Mak ; 22(1): 284, 2022 11 02.
Article in English | MEDLINE | ID: covidwho-2098335

ABSTRACT

BACKGROUND: The sensitivity of RT-PCR in diagnosing COVID-19 is only 60-70%, and chest CT plays an indispensable role in the auxiliary diagnosis of COVID-19 pneumonia, but the results of CT imaging are highly dependent on professional radiologists. AIMS: This study aimed to develop a deep learning model to assist radiologists in detecting COVID-19 pneumonia. METHODS: The total study population was 437. The training dataset contained 26,477, 2468, and 8104 CT images of normal, CAP, and COVID-19, respectively. The validation dataset contained 14,076, 1028, and 3376 CT images of normal, CAP, and COVID-19 patients, respectively. The test set included 51 normal cases, 28 CAP patients, and 51 COVID-19 patients. We designed and trained a deep learning model to recognize normal, CAP, and COVID-19 patients based on U-Net and ResNet-50. Moreover, the diagnoses of the deep learning model were compared with different levels of radiologists. RESULTS: In the test set, the sensitivity of the deep learning model in diagnosing normal cases, CAP, and COVID-19 patients was 98.03%, 89.28%, and 92.15%, respectively. The diagnostic accuracy of the deep learning model was 93.84%. In the validation set, the accuracy was 92.86%, which was better than that of two novice doctors (86.73% and 87.75%) and almost equal to that of two experts (94.90% and 93.88%). The AI model performed significantly better than all four radiologists in terms of time consumption (35 min vs. 75 min, 93 min, 79 min, and 82 min). CONCLUSION: The AI model we obtained had strong decision-making ability, which could potentially assist doctors in detecting COVID-19 pneumonia.


Subject(s)
COVID-19 , Deep Learning , Humans , COVID-19/diagnostic imaging , SARS-CoV-2 , Tomography, X-Ray Computed/methods , Research Design
4.
37th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2022 ; JOUR: 272-274,
Article in English | Scopus | ID: covidwho-2097627

ABSTRACT

Recently, COVID-19 has accelerated the non-contact culture. Many presentations, such as workshops and conferences, are conducted in an online and offline hybrid mode in a conference room. In presentations, a screen of the slide is particularly important. Therefore, we propose an algorithm that detects the screen in an image. Firstly, a screen region is extracted using a deep learning-based instance segmentation method. However, this extracted region has a noisy boundary. We designed an image processing algorithm composed of 7 main steps to solve this noise and detect the screen. To validate the proposed method, a real dataset was qualitatively evaluated, and the result images show that only meaningful screen regions in the test image can be extracted. © 2022 IEEE.

5.
Scand J Trauma Resusc Emerg Med ; 29(1): 145, 2021 Oct 03.
Article in English | MEDLINE | ID: covidwho-2098399

ABSTRACT

BACKGROUND: Sepsis is a life-threatening organ dysfunction and a major healthcare burden worldwide. Although sepsis is a medical emergency that requires immediate management, screening for the occurrence of sepsis is difficult. Herein, we propose a deep learning-based model (DLM) for screening sepsis using electrocardiography (ECG). METHODS: This retrospective cohort study included 46,017 patients who were admitted to two hospitals. A total of 1,548 and 639 patients had sepsis and septic shock, respectively. The DLM was developed using 73,727 ECGs from 18,142 patients, and internal validation was conducted using 7774 ECGs from 7,774 patients. Furthermore, we conducted an external validation with 20,101 ECGs from 20,101 patients from another hospital to verify the applicability of the DLM across centers. RESULTS: During the internal and external validations, the area under the receiver operating characteristic curve (AUC) of the DLM using 12-lead ECG was 0.901 (95% confidence interval, 0.882-0.920) and 0.863 (0.846-0.879), respectively, for screening sepsis and 0.906 (95% confidence interval (CI), 0.877-0.936) and 0.899 (95% CI, 0.872-0.925), respectively, for detecting septic shock. The AUC of the DLM for detecting sepsis using 6-lead and single-lead ECGs was 0.845-0.882. A sensitivity map revealed that the QRS complex and T waves were associated with sepsis. Subgroup analysis was conducted using ECGs from 4,609 patients who were admitted with an infectious disease, and the AUC of the DLM for predicting in-hospital mortality was 0.817 (0.793-0.840). There was a significant difference in the prediction score of DLM using ECG according to the presence of infection in the validation dataset (0.277 vs. 0.574, p < 0.001), including severe acute respiratory syndrome coronavirus 2 (0.260 vs. 0.725, p = 0.018). CONCLUSIONS: The DLM delivered reasonable performance for sepsis screening using 12-, 6-, and single-lead ECGs. The results suggest that sepsis can be screened using not only conventional ECG devices but also diverse life-type ECG machines employing the DLM, thereby preventing irreversible disease progression and mortality.


Subject(s)
COVID-19 , Deep Learning , Sepsis , Electrocardiography , Humans , Retrospective Studies , SARS-CoV-2 , Sepsis/diagnosis
6.
Environmental Engineering and Management Journal ; JOUR(7):1171-1183, 21.
Article in English | Web of Science | ID: covidwho-2092222

ABSTRACT

A worldwide pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), known as coronavirus disease 2019 (COVID-19), has killed many people. More than 31.6 million cases have been recorded in India alone till 2021. The main aim of this study is to identify the relationship between COVID-19 and air pollution concerning geographical location. Considerably air pollution also increases the cases, and COVID-19 disease causes damage to the respiratory system. Applying the Long short-term memory (LSTM) and Bidirectional Long short-term memory (BiLSTM) deep Learning model, this work attempts at giving insight into the connection between the various factors impacting COVID-19 mortality rates, i.e., the dispersion between the confirmed number of cases and the air pollution levels in major urban centres, namely Delhi, Bengaluru, Chennai, Mumbai, and Kolkata in India COVID-19 infections discovered that there is an association between high PM10 and PM2.5 pollution levels and having confirmed diseases are high. There is a concrete relationship between PM2.5 and COVID-19 mortality, which confirmed by the developed deep learning model that uses multiple regression analysis. The research model estimate, forecast and track COVID-19 case infections effects on air pollution, particularly in metropolitan cities. The BiLSTM model gives better score values between 0.903 and 0.951, whereas the LSTM model scores between 0.754 and 0.829. This research reveals a link between health and air pollutions parameters during this pandemic period. The results obtained from the research show a constructive co-relationship between the level of air pollution and diffusion of coronavirus.

7.
J Biomol Struct Dyn ; : 1-16, 2022 Oct 28.
Article in English | MEDLINE | ID: covidwho-2087508

ABSTRACT

Artificial intelligence (AI) development imitates the workings of the human brain to comprehend modern problems. The traditional approaches such as high throughput screening (HTS) and combinatorial chemistry are lengthy and expensive to the pharmaceutical industry as they can only handle a smaller dataset. Deep learning (DL) is a sophisticated AI method that uses a thorough comprehension of particular systems. The pharmaceutical industry is now adopting DL techniques to enhance the research and development process. Multi-oriented algorithms play a crucial role in the processing of QSAR analysis, de novo drug design, ADME evaluation, physicochemical analysis, preclinical development, followed by clinical trial data precision. In this study, we investigated the performance of several algorithms, including deep neural networks (DNN), convolutional neural networks (CNN) and multi-task learning (MTL), with the aim of generating high-quality, interpretable big and diverse databases for drug design and development. Studies have demonstrated that CNN, recurrent neural network and deep belief network are compatible, accurate and effective for the molecular description of pharmacodynamic properties. In Covid-19, existing pharmacological compounds has also been repurposed using DL models. In the absence of the Covid-19 vaccine, remdesivir and oseltamivir have been widely employed to treat severe SARS-CoV-2 infections. In conclusion, the results indicate the potential benefits of employing the DL strategies in the drug discovery process.Communicated by Ramaswamy H. Sarma.

8.
Korean J Radiol ; 21(10): 1150-1160, 2020 10.
Article in English | MEDLINE | ID: covidwho-2089785

ABSTRACT

OBJECTIVE: To describe the experience of implementing a deep learning-based computer-aided detection (CAD) system for the interpretation of chest X-ray radiographs (CXR) of suspected coronavirus disease (COVID-19) patients and investigate the diagnostic performance of CXR interpretation with CAD assistance. MATERIALS AND METHODS: In this single-center retrospective study, initial CXR of patients with suspected or confirmed COVID-19 were investigated. A commercialized deep learning-based CAD system that can identify various abnormalities on CXR was implemented for the interpretation of CXR in daily practice. The diagnostic performance of radiologists with CAD assistance were evaluated based on two different reference standards: 1) real-time reverse transcriptase-polymerase chain reaction (rRT-PCR) results for COVID-19 and 2) pulmonary abnormality suggesting pneumonia on chest CT. The turnaround times (TATs) of radiology reports for CXR and rRT-PCR results were also evaluated. RESULTS: Among 332 patients (male:female, 173:159; mean age, 57 years) with available rRT-PCR results, 16 patients (4.8%) were diagnosed with COVID-19. Using CXR, radiologists with CAD assistance identified rRT-PCR positive COVID-19 patients with sensitivity and specificity of 68.8% and 66.7%, respectively. Among 119 patients (male:female, 75:44; mean age, 69 years) with available chest CTs, radiologists assisted by CAD reported pneumonia on CXR with a sensitivity of 81.5% and a specificity of 72.3%. The TATs of CXR reports were significantly shorter than those of rRT-PCR results (median 51 vs. 507 minutes; p < 0.001). CONCLUSION: Radiologists with CAD assistance could identify patients with rRT-PCR-positive COVID-19 or pneumonia on CXR with a reasonably acceptable performance. In patients suspected with COVID-19, CXR had much faster TATs than rRT-PCRs.


Subject(s)
Betacoronavirus , Coronavirus Infections/diagnostic imaging , Deep Learning , Pneumonia, Viral/diagnostic imaging , Radiography, Thoracic , Adult , Aged , COVID-19 , Female , Humans , Male , Middle Aged , Pandemics , Radiography, Thoracic/methods , Retrospective Studies , SARS-CoV-2 , Tomography, X-Ray Computed/methods
9.
Chaos Solitons Fractals ; 165: 112818, 2022 Dec.
Article in English | MEDLINE | ID: covidwho-2086015

ABSTRACT

In this work, we propose a new mathematical modeling of the spread of COVID-19 infection in an arbitrary population, by modifying the SIQRD model as m-SIQRD model, while taking into consideration the eight governmental interventions such as cancellation of events, closure of public places etc., as well as the influence of the asymptomatic cases on the states of the model. We introduce robustness and improved accuracy in predictions of these models by utilizing a novel deep learning scheme. This scheme comprises of attention based architecture, alongside with Generative Adversarial Network (GAN) based data augmentation, for robust estimation of time varying parameters of m-SIQRD model. In this regard, we also utilized a novel feature extraction methodology by employing noise removal operation by Spline interpolation and Savitzky-Golay filter, followed by Principal Component Analysis (PCA). These parameters are later directed towards two main tasks: forecasting of states to the next 15 days, and estimation of best policy encodings to control the infected and deceased number within the framework of data driven synergetic control theory. We validated the superiority of the forecasting performance of the proposed scheme over countries of South Korea and Germany and compared this performance with 7 benchmark forecasting models. We also showed the potential of this scheme to determine best policy encodings in South Korea for 15 day forecast horizon.

10.
Multimed Tools Appl ; : 1-19, 2022 Oct 21.
Article in English | MEDLINE | ID: covidwho-2085469

ABSTRACT

COVID-19 is an ongoing pandemic and the WHO recommends at least one-meter social distance, and the use of medical face masks to slow the disease's transmission. This paper proposes an automated approach for detecting social distance and face masks. Thus, it aims to help the reduction of diseases transferred by respiratory droplets such as COVID-19. For this system, a two-cascaded YOLO is used. The first cascade detects humans in the environment and computes the social distance between them. Then, the second cascade detects human faces with or without a mask. Finally, red bounding boxes encircle the people's images that did not follow the rules. Also, in this paper, we propose a two-part feature extraction approach used with YOLO. The first part of the proposed feature extraction method extracts general features using the transfer learning approach. The second part extracts better features specific to the current task using the LBP layer and classification layers. The best average precision for the human detection task was obtained as 66% using Resnet50 in YOLO. The best average precision for the mask detection was obtained as 95% using Darknet19+LBP with YOLO. Also, another popular object detection network, Faster R-CNN, have been used for comparison purpose. The proposed system performed better than the literature in human and mask detection tasks.

11.
Information Fusion ; JOUR:53-65, 89.
Article in English | Web of Science | ID: covidwho-2084435

ABSTRACT

The use of automatic systems for medical image classification has revolutionized the diagnosis of a high number of diseases. These alternatives, which are usually based on artificial intelligence (AI), provide a helpful tool for clinicians, eliminating the inter and intra-observer variability that the diagnostic process entails. Convolutional Neural Network (CNNs) have proved to be an excellent option for this purpose, demonstrating a large performance in a wide range of contexts. However, it is also extremely important to quantify the reliability of the model's predictions in order to guarantee the confidence in the classification. In this work, we propose a multi-level ensemble classification system based on a Bayesian Deep Learning approach in order to maximize performance while providing the uncertainty of each classification decision. This tool combines the information extracted from different architectures by weighting their results according to the uncertainty of their predictions. Performance is evaluated in a wide range of real scenarios: in the first one, the aim is to differentiate between different pulmonary pathologies: controls vs bacterial pneumonia vs viral pneumonia. A two-level decision tree is employed to divide the 3-class classification into two binary classifications, yielding an accuracy of 98.19%. In the second context, performance is assessed for the diagnosis of Parkinson's disease, leading to an accuracy of 95.31%. The reduced preprocessing needed for obtaining this high performance, in addition to the information provided about the reliability of the predictions evidence the applicability of the system to be used as an aid for clinicians.

12.
Radiography (Lond) ; 29(1): 109-118, 2022 Oct 24.
Article in English | MEDLINE | ID: covidwho-2082574

ABSTRACT

INTRODUCTION: With the increasing number of Covid-19 cases as well as care costs, chest diseases have gained increasing interest in several communities, particularly in medical and computer vision. Clinical and analytical exams are widely recognized techniques for diagnosing and handling Covid-19 cases. However, strong detection tools can help avoid damage to chest tissues. The proposed method provides an important way to enhance the semantic segmentation process using combined potential deep learning (DL) modules to increase consistency. Based on Covid-19 CT images, this work hypothesized that a novel model for semantic segmentation might be able to extract definite graphical features of Covid-19 and afford an accurate clinical diagnosis while optimizing the classical test and saving time. METHODS: CT images were collected considering different cases (normal chest CT, pneumonia, typical viral causes, and Covid-19 cases). The study presents an advanced DL method to deal with chest semantic segmentation issues. The approach employs a modified version of the U-net to enable and support Covid-19 detection from the studied images. RESULTS: The validation tests demonstrated competitive results with important performance rates: Precision (90.96% ± 2.5) with an F-score of (91.08% ± 3.2), an accuracy of (93.37% ± 1.2), a sensitivity of (96.88% ± 2.8) and a specificity of (96.91% ± 2.3). In addition, the visual segmentation results are very close to the Ground truth. CONCLUSION: The findings of this study reveal the proof-of-principle for using cooperative components to strengthen the semantic segmentation modules for effective and truthful Covid-19 diagnosis. IMPLICATIONS FOR PRACTICE: This paper has highlighted that DL based approach, with several modules, may be contributing to provide strong support for radiographers and physicians, and that further use of DL is required to design and implement performant automated vision systems to detect chest diseases.

13.
Sensors (Basel) ; 22(20)2022 Oct 19.
Article in English | MEDLINE | ID: covidwho-2082155

ABSTRACT

COVID-19 has infected millions of people worldwide over the past few years. The main technique used for COVID-19 detection is reverse transcription, which is expensive, sensitive, and requires medical expertise. X-ray imaging is an alternative and more accessible technique. This study aimed to improve detection accuracy to create a computer-aided diagnostic tool. Combining other artificial intelligence applications techniques with radiological imaging can help detect different diseases. This study proposes a technique for the automatic detection of COVID-19 and other chest-related diseases using digital chest X-ray images of suspected patients by applying transfer learning (TL) algorithms. For this purpose, two balanced datasets, Dataset-1 and Dataset-2, were created by combining four public databases and collecting images from recently published articles. Dataset-1 consisted of 6000 chest X-ray images with 1500 for each class. Dataset-2 consisted of 7200 images with 1200 for each class. To train and test the model, TL with nine pretrained convolutional neural networks (CNNs) was used with augmentation as a preprocessing method. The network was trained to classify using five classifiers: two-class classifier (normal and COVID-19); three-class classifier (normal, COVID-19, and viral pneumonia), four-class classifier (normal, viral pneumonia, COVID-19, and tuberculosis (Tb)), five-class classifier (normal, bacterial pneumonia, COVID-19, Tb, and pneumothorax), and six-class classifier (normal, bacterial pneumonia, COVID-19, viral pneumonia, Tb, and pneumothorax). For two, three, four, five, and six classes, our model achieved a maximum accuracy of 99.83, 98.11, 97.00, 94.66, and 87.29%, respectively.


Subject(s)
COVID-19 , Deep Learning , Pneumonia, Bacterial , Pneumonia, Viral , Pneumothorax , Humans , COVID-19/diagnosis , SARS-CoV-2 , Artificial Intelligence
14.
2021 Ieee Virtual Ieee International Symposium on Technologies for Homeland Security ; JOUR
Article in English | Web of Science | ID: covidwho-2082833

ABSTRACT

Face recognition is a widely adopted technology in surveillance, border control, healthcare, banking services, and consumer product. Recent studies suggested that the performance of face recognition system is severely degraded in the presence of facial mask worn during COVID-19 pandemic. This work propose a mask-aware face recognition system that can identify subjects with and without facial mask presence. To this end, the two-fold contributions of this study are: (a) evaluation of the three hand-crafted descriptors, namely, Local Binary Pattern (LBP), Histogram of Oriented Gradients (HOG), and Local Directional Order Pattern (LDOP) along with Support Vector Machine (SVM) for facial mask detection, and (b) deep learning based mask-aware dynamic ensemble model that can recognize subjects in facial mask presence and absence. Experimental evaluation are conducted on the Real-World Masked Face Recognition Dataset (RMFRD) consisting of 426 subjects with 1945 and 88500 images with and without facial mask, respectively. Results suggest highest accuracy of 99:60% in facial mask detection using LDOP-based descriptor. The performance degradation of up to 24% was reported for deep learning based ResNet-50 face recognition model in the presence of facial mask. Performance due to our proposed dynamic ensemble model (in the presence and absence of mask) is at par with the performance of the baseline face recognition system in the absence of facial mask. For instance, Equal Error Rate (EER) of the proposed dynamic ensemble (mask-aware face recognition) in the presence of facial mask is 6.59% and that of the deep-learning based face recognition system is 6.42% in the absence of facial mask.

15.
Advances in Engineering Software ; JOUR: 103317,
Article in English | ScienceDirect | ID: covidwho-2082582

ABSTRACT

The Coronavirus (COVID-19) has become a critical and extreme epidemic because of its international dissemination. COVID-19 is the world's most serious health, economic, and survival danger. This disease affects not only a single country but the entire planet due to this infectious disease. Illnesses of Covid-19 spread at a much faster rate than usual influenza cases. Because of its high transmissibility and early diagnosis, it isn't easy to manage COVID-19. The popularly used RT-PCR method for COVID-19 disease diagnosis may provide false negatives. COVID-19 can be detected non-invasively using medical imaging procedures such as chest CT and chest x-ray. Deep learning is the most effective machine learning approach for examining a considerable quantity of chest computed tomography (CT) pictures that can significantly affect Covid-19 screening. Convolutional neural network (CNN) is one of the most popular deep learning techniques right now, and its gaining traction due to its potential to transform several spheres of human life. This research aims to develop conceptual transfer learning enhanced CNN framework models for detecting COVID-19 with CT scan images. Though with minimal datasets, these techniques were demonstrated to be effective in detecting the presence of COVID-19. This proposed research looks into several deep transfer learning-based CNN approaches for detecting the presence of COVID-19 in chest CT images.VGG16, VGG19, Densenet121, InceptionV3, Xception, and Resnet50 are the foundation models used in this work. Each model's performance was evaluated using a confusion matrix and various performance measures such as accuracy, recall, precision, f1-score, loss, and ROC. The VGG16 model performed much better than the other models in this study (98.00 % accuracy). Promising outcomes from experiments have revealed the merits of the proposed model for detecting and monitoring COVID-19 patients. This could help practitioners and academics create a tool to help minimal health professionals decide on the best course of therapy.

16.
Concurrency and Computation: Practice and Experience ; JOUR
Article in English | Web of Science | ID: covidwho-2082435

ABSTRACT

Many researchers in various disciplines have focused on extracting meaningful information from social media platforms in recent years. Identification of behaviors and emotions from user posts is examined under the heading of sentiment analysis (SA) studies using the natural language processing (NLP) techniques. In this study, a novel TCNN-Bi-LSTM model using the two-stage convolutional neural network (TCNN) and bidirectional long short-term memory (Bi-LSTM) architectures was proposed. While TCNN layers enable the extraction of strong local features, the output of these layers feeds the Bi-LSTM model that remembers forward-looking information and capture long-term dependencies. In this study, first, preprocessing steps were applied to the raw dataset. Thus, strong features were extracted from the obtained quality dataset using the FastText word embedding technique that pre-trained with location-based and sub-word information features. The experimental results of the proposed method are promising compared to the baseline deep learning and machine learning models. Also, experimental results show that while the FastText data embedding technique achieves the best performance compared to other word embedding techniques in all deep learning classification models, it has not had the same outstanding success in machine learning models. This study aims to investigate the sentiments of tweets about the COVID-19 vaccines and comments on these tweets among Twitter users by using the power of Twitter data. A new dataset collected from Twitter was constructed to be used in experimental results. This study will facilitate detecting inappropriate, incomplete, and erroneous information about vaccination. The results of this study will enable society to broaden its perspective on the administered vaccines. It can also assist the government and healthcare agencies in planning and implementing the vaccination's promotion on time to achieve the herd immunity provided by the vaccination.

17.
International Journal of Imaging Systems and Technology ; JOUR
Article in English | Web of Science | ID: covidwho-2082409

ABSTRACT

Coronavirus disease 2019 (COVID-19) epidemic has devastating effects on personal health around the world. It is significant to achieve accurate segmentation of pulmonary infection regions, which is an early indicator of disease. To solve this problem, a deep learning model, namely, the content-aware pre-activated residual UNet (CAPA-ResUNet), was proposed for segmenting COVID-19 lesions from CT slices. In this network, the pre-activated residual block was used for down-sampling to solve the problems of complex foreground and large fluctuations of distribution in datasets during training and to avoid gradient disappearance. The area loss function based on the false segmentation regions was proposed to solve the problem of fuzzy boundary of the lesion area. This model was evaluated by the public dataset (COVID-19 Lung CT Lesion Segmentation Challenge-2020) and compared its performance with those of classical models. Our method gains an advantage over other models in multiple metrics. Such as the Dice coefficient, specificity (Spe), and intersection over union (IoU), our CAPA-ResUNet obtained 0.775 points, 0.972 points, and 0.646 points, respectively. The Dice coefficient of our model was 2.51% higher than Content-aware residual UNet (CARes-UNet). The code is available at .

18.
PeerJ Comput Sci ; 8: e1082, 2022.
Article in English | MEDLINE | ID: covidwho-2080856

ABSTRACT

COVID-19 is a widespread deadly virus that directly affects the human lungs. The spread of COVID-19 did not stop at humans but also reached animals, so it was necessary to limit it is spread and diagnose cases quickly by applying a quarantine to the infected people. Recently x-ray lung images are used to determine the infection and from here the idea of this research came to use deep learning techniques to analyze x-ray lung images publicly available on Kaggle to possibly detect COVID-19 infection. In this article, we have proposed a method to possibly detect the COVID-19 by analyzing the X-ray images and applying a number of deep learning pre-trained models such as InceptionV3, DenseNet121, ResNet50, and VGG16, and the results are compared to determine the best performance model and accuracy with the least loss for our dataset. Our evaluation results showed that the best performing model for our dataset is ResNet50 with accuracies of 99.99%, 99.50%, and 99.44% for training, validation, and testing respectively followed by DenseNet121, InceptionV3, and finally VGG16.

19.
Journal of Logistics, Informatics and Service Science ; 9(3):97-111, 2022.
Article in English | Scopus | ID: covidwho-2081527

ABSTRACT

The COVID-19 pandemic has brought unimaginable damage to the globe;It had brought people we love away and forced the government to lock down the cities to prevent the infection of COVID-19 from spreading. This stopped various industries from working, especially the engineering and construction industries. Fortunately, the effectiveness of the COVID-19 vaccine had enabled the industries to resume their operation back to normal. However, the mask now is an essential equipment to be worn by all workers while on site, they also required to wear helmet for safety reasons. Therefore, the aim of research is to detect the helmets and masks worn by workers, if there the workers were found not for not wearing the mask properly an alert will be triggered. Five classes were determined namely 'Head,’ 'Helmet,’ 'Incorrect Mask,’ 'No Wearing Mask', and 'Wearing Mask'. A total of 1711 images of construction workers scenes were collected, and augmentation was applied on these images to generate 4733 images. All images were annotated corresponding to the defined classes. The experiments have split the training and validation dataset into a ratio of 9:1. The result obtain a 65.235% Mean Average Precision (mAP) as a result. © 2022, Success Culture Press. All rights reserved.

20.
Crit Care ; 26(1): 311, 2022 10 14.
Article in English | MEDLINE | ID: covidwho-2079529

ABSTRACT

BACKGROUND: The sublingual microcirculation presumably exhibits disease-specific changes in function and morphology. Algorithm-based quantification of functional microcirculatory hemodynamic variables in handheld vital microscopy (HVM) has recently allowed identification of hemodynamic alterations in the microcirculation associated with COVID-19. In the present study we hypothesized that supervised deep machine learning could be used to identify previously unknown microcirculatory alterations, and combination with algorithmically quantified functional variables increases the model's performance to differentiate critically ill COVID-19 patients from healthy volunteers. METHODS: Four international, multi-central cohorts of critically ill COVID-19 patients and healthy volunteers (n = 59/n = 40) were used for neuronal network training and internal validation, alongside quantification of functional microcirculatory hemodynamic variables. Independent verification of the models was performed in a second cohort (n = 25/n = 33). RESULTS: Six thousand ninety-two image sequences in 157 individuals were included. Bootstrapped internal validation yielded AUROC(CI) for detection of COVID-19 status of 0.75 (0.69-0.79), 0.74 (0.69-0.79) and 0.84 (0.80-0.89) for the algorithm-based, deep learning-based and combined models. Individual model performance in external validation was 0.73 (0.71-0.76) and 0.61 (0.58-0.63). Combined neuronal network and algorithm-based identification yielded the highest externally validated AUROC of 0.75 (0.73-0.78) (P < 0.0001 versus internal validation and individual models). CONCLUSIONS: We successfully trained a deep learning-based model to differentiate critically ill COVID-19 patients from heathy volunteers in sublingual HVM image sequences. Internally validated, deep learning was superior to the algorithmic approach. However, combining the deep learning method with an algorithm-based approach to quantify the functional state of the microcirculation markedly increased the sensitivity and specificity as compared to either approach alone, and enabled successful external validation of the identification of the presence of microcirculatory alterations associated with COVID-19 status.


Subject(s)
COVID-19 , Critical Illness , Artificial Intelligence , Humans , Microcirculation/physiology , Sensitivity and Specificity
SELECTION OF CITATIONS
SEARCH DETAIL