Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 1.367
Filter
Add filters

Year range
1.
Eur J Med Chem ; 240: 114572, 2022 Jul 03.
Article in English | MEDLINE | ID: covidwho-1966535

ABSTRACT

The newly emerged coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that caused the COVID-19 pandemic, is the closest relative of SARS-CoV with high genetic similarity. The papain-like protease (PLpro) is an important SARS-CoV/SARS-CoV-2 nonstructural protein that plays a critical role in some infection processes such as the generation of the functional replication complex, maturation of crude polyproteins, and regulation of the host antiviral immune responses. Therefore, the research to discover SARS-CoV-2 PLpro inhibitors could be a sensible strategy to obtain therapeutic agents for the treatment of COVID-19. Aiming to find SARS-CoV/SARS-CoV-2 PLpro inhibitors, various high throughput screenings (HTS) have been performed over the past two decades. Interestingly, the result of these efforts is the identification of hit/lead compounds whose structures have one important feature in common, namely having a chalcone-amide (N-benzylbenzamide) backbone. Structure-activity relationship (SAR) studies have shown that placing an (R)-configurated methyl group on the middle carbon adjacent to the amide group creates a unique backbone called (R)-methyl chalcone-amide, which dramatically increases PLpro inhibitory potency. Although this scaffold has not yet been introduced by medicinal chemists as a specific skeleton for the design of PLpro inhibitors, structural considerations show that the most reported PLpro inhibitors have this skeleton. This review suggests the (R)-methyl chalcone-amide scaffold as a key backbone for the design and development of selective SARS-CoV-2 PLpro inhibitors. Understanding the SAR and binding mode of these inhibitors in the active site of SARS-CoV-2 PLpro can aid the future development of anti-COVID-19 agents.

2.
Multimed Tools Appl ; : 1-42, 2022 Aug 01.
Article in English | MEDLINE | ID: covidwho-1966164

ABSTRACT

The outbreak of novel coronavirus (COVID-19) disease has infected more than 135.6 million people globally. For its early diagnosis, researchers consider chest X-ray examinations as a standard screening technique in addition to RT-PCR test. Majority of research work till date focused only on application of deep learning approaches that is relevant but lacking in better pre-processing of CXR images. Towards this direction, this study aims to explore cumulative effects of image denoising and enhancement approaches on the performance of deep learning approaches. Regarding pre-processing, suitable methods for X-ray images, Histogram equalization, CLAHE and gamma correction have been tested individually and along with adaptive median filter, median filter, total variation filter and gaussian denoising filters. Proposed study compared eleven combinations in exploration of most coherent approach in greedy manner. For more robust analysis, we compared ten CNN architectures for performance evaluation with and without enhancement approaches. These models are InceptionV3, InceptionResNetV2, MobileNet, MobileNetV2, Vgg19, NASNetMobile, ResNet101, DenseNet121, DenseNet169, DenseNet201. These models are trained in 4-way (COVID-19 pneumonia vs Viral vs Bacterial pneumonia vs Normal) and 3-way classification scenario (COVID-19 vs Pneumonia vs Normal) on two benchmark datasets. The proposed methodology determines with TVF + Gamma, models achieve higher classification accuracy and sensitivity. In 4-way classification MobileNet with TVF + Gamma achieves top accuracy of 93.25% with 1.91% improvement in accuracy score, COVID-19 sensitivity of 98.72% and F1-score of 92.14%. In 3-way classification our DenseNet201 with TVF + Gamma gains accuracy of 91.10% with improvement of 1.47%, COVID-19 sensitivity of 100% and F1-score of 91.09%. Proposed study concludes that deep learning modes with gamma correction and TVF + Gamma has superior performance compared to state-of-the-art models. This not only minimizes overlapping between COVID-19 and virus pneumonia but advantageous in time required to converge best possible results.

3.
Appl Organomet Chem ; : e6836, 2022 Jul 28.
Article in English | MEDLINE | ID: covidwho-1966024

ABSTRACT

Cobalt (III) complexes with Schiff base ligands derived from hydrazone, (HL1 = (E)-N'-(3,5-Dichloro-2-hydroxybenzylidene)-4-hydroxybenzohydrazide, HL2 = (E)-N'-(3,5-Dichloro-2-hydroxybenzylidene)-4-hydroxybenzohydrazide (3,5-Dibromo-2-hydroxybenzylidene) and HL3 = (E)-4-Hydroxy-N'-(2-hydroxy-3-ethoxybenzylidene)benzohydrazide), were synthesized and characterized by elemental analysis, FT-IR, UV-Vis spectroscopy, and cyclic voltammetry. X-ray diffraction was used to determine the single crystal structure of the complex (1). Co (III) was formed in a distorted, very regular octahedral coordination in this complex; three pyridine moieties complete this geometry. Schiff base complexes' redox behaviors are represented by irreversible (1), quasi-reversible (2), and quasi-reversible (3) voltammograms, respectively. A DFT/B3LYP method was used to optimize cobalt complexes with a base set of 6-311G. Furthermore, fragments occupying the HOMO and LUMO molecular orbitals were investigated at the same theoretical level. QTAIM computations were also done to study the coordination bonds and non-covalent interactions in the investigated structures. Hirshfeld surface analysis was used to investigate the nature and types of intermolecular exchanges in the crystal structure of the complex (1). The capacity of cobalt complexes to bind to the major protease SARS-CoV-2 and the molecular targets of human angiotensin-converting enzyme-2 was investigated using molecular docking (ACE-2). The molecular simulation methods used to assess the probable binding states of cobalt complexes revealed that all three complexes were stabilized in the active envelope of the enzyme by making distinct interactions with critical amino acid residues. Interestingly, compound (2) performed better with both molecular targets and the total energy of the system than the other complexes.

4.
ChemistrySelect ; 7(29):e202201504, 2022.
Article in English | Wiley | ID: covidwho-1966112

ABSTRACT

Three new compounds of amidophosphoric acid esters with a [OCH2C(CH3)2CH2O]P(O)[X] segment (where X=cyclopentylamido (1), 2-aminopyridinyl (2) and pyrrolidinyl (3)) were synthesized and studied using FT-IR and 31P/13C/1H?NMR spectroscopies and single-crystal X-ray diffraction analysis. The compounds crystallize in the triclinic space groups P for 1 and 3 and in the orthorhombic space group Pca21 for 2, where the asymmetric unit consists of three symmetrically-independent molecules for 1 and one molecule for 2 and 3. The intermolecular interactions and supramolecular assemblies are assessed by Hirshfeld surface analysis and enrichment ratios. The results reveal that the substituent effect plays an important role in directing the supramolecular structures. The presence of the aromatic substituent aminopyridine in 2 providing the C?H?π interactions leads to a larger variety in interactions including H?H, H?O/O?H, H?C/C?H and H?N/N?H contacts, whereas the packings of the compounds 1 and 3 bearing aliphatic substituents only include H?H and H?O/O?H contacts. The enrichment ratios affirm the importance of O?H/H?O contacts reflecting the hydrogen bond N?H?O interactions to be the enriched contacts. Compounds 1?3 were also investigated along with five similar reported structures with a [OCH2C(CH3)2CH2O]P(O) segment for their inhibitory behavior against SARS-CoV-2. The molecular docking results illustrate that the presence of the aromatic amido substituent versus the aliphatic type provides a more favorable condition for their biological activities.

5.
International Journal of Advanced Technology and Engineering Exploration ; 9(90):623-643, 2022.
Article in English | ProQuest Central | ID: covidwho-1964885

ABSTRACT

A rapid diagnostic system is a primary role in the healthcare system exclusively during a pandemic situation to control contagious diseases like coronavirus disease-2019 (COVID-19). Many countries remain lacking to spot COVID cases by the reverse transcription-polymerase chain reaction (RT-PCR) test. On this stretch, deep learning algorithms have been strengthened the medical image processing system to analyze the infection, categorization, and further diagnosis. It is motivated to discover the alternate way to identify the disease using existing medical implications. Hence, this review narrated the character and attainment of deep learning algorithms at each juncture from origin to COVID-19. This literature highlights the importance of deep learning and further focused the medical image processing research on handling the data of magnetic resonance imaging (MRI), computed tomography (CT) scan, and electromagnetic radiation (X-ray) images. Additionally, this systematic review tabulates the popular deep learning networks with operational parameters, peer-reviewed research with their outcomes, popular nets, and prevalent datasets, and highlighted the facts to stimulate future research. The consequence of this literature ascertains convolutional neural network-based deep learning approaches work better in the medical image processing system, and especially it is very supportive of sorting out the COVID-19 complications.

6.
Quantitative Biology ; 10(2):208-220, 2022.
Article in English | Scopus | ID: covidwho-1964760

ABSTRACT

Background: Coronavirus disease (COVID-19) is a contagious infection caused by severe acute respiratory syndrome coronavirus-2 (SARS-COV-2) and it has infected and killed millions of people across the globe. Objective: In the absence or inadequate provision of therapeutic treatments of COVID-19 and the limited convenience of diagnostic techniques, there is a necessity for some alternate spontaneous screening systems that can easily be used by the physicians to rapidly recognize and isolate the infected patients to circumvent onward surge. A chest X-ray (CXR) image can effortlessly be used as a substitute modality to diagnose the COVID-19. Method: In this study, we present an automatic COVID-19 diagnostic and severity prediction system (COVIDX) that uses deep feature maps of CXR images along with classical machine learning algorithms to identify COVID-19 and forecast its severity. The proposed system uses a three-phase classification approach (healthy vs unhealthy, COVID-19 vs pneumonia, and COVID-19 severity) using different conventional supervised classification algorithms. Results: We evaluated COVIDX through 10-fold cross-validation, by using an external validation dataset, and also in a real setting by involving an experienced radiologist. In all the adopted evaluation settings, COVIDX showed strong generalization power and outperforms all the prevailing state-of-the-art methods designed for this purpose. Conclusions: Our proposed method (COVIDX), with vivid performance in COVID-19 diagnosis and its severity prediction, can be used as an aiding tool for clinical physicians and radiologists in the diagnosis and follow-up studies of COVID-19 infected patients. © The Author(s) 2022. Published by Higher Education Press.

7.
AIMS Biophysics ; 8(4):346-371, 2021.
Article in English | Scopus | ID: covidwho-1964164

ABSTRACT

The use of Artificial Intelligence (AI) in combination with Internet of Things (IoT) drastically reduces the need to test the COVID samples manually, saving not only time but money and ultimately lives. In this paper, the authors have proposed a novel methodology to identify the COVID-19 patients with an annotated stage to enable the medical staff to manually activate a geo-fence around the subject thus ensuring early detection and isolation. The use of radiography images with pathology data used for COVID-19 identification forms the first-ever contribution by any research group globally. The novelty lies in the correct stage classification of COVID-19 subjects as well. The present analysis would bring this AI Model on the edge to make the facility an IoT-enabled unit. The developed system has been compared and extensively verified thoroughly with those of clinical observations. The significance of radiography imaging for detecting and identification of COVID-19 subjects with severity score tag for stage classification is mathematically established. In a Nutshell, this entire algorithmic workflow can be used not only for predictive analytics but also for prescriptive analytics to complete the entire pipeline from the diagnostic viewpoint of a doctor. As a matter of fact, the authors have used a supervised based learning approach aided by a multiple hypothesis based decision fusion based technique to increase the overall system’s accuracy and prediction. The end to end value chain has been put under an IoT based ecosystem to leverage the combined power of AI and IoT to not only detect but also to isolate the coronavirus affected individuals. To emphasize further, the developed AI model predicts the respective categories of a coronavirus affected patients and the IoT system helps the point of care facilities to isolate and prescribe the need of hospitalization for the COVID patients © 2021. the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)

8.
Data ; 7(7):95, 2022.
Article in English | ProQuest Central | ID: covidwho-1963771

ABSTRACT

Developments in deep learning techniques have led to significant advances in automated abnormality detection in radiological images and paved the way for their potential use in computer-aided diagnosis (CAD) systems. However, the development of CAD systems for pulmonary tuberculosis (TB) diagnosis is hampered by the lack of training data that is of good visual and diagnostic quality, of sufficient size, variety, and, where relevant, containing fine-region annotations. This study presents a collection of annotations/segmentations of pulmonary radiological manifestations that are consistent with TB in the publicly available and widely used Shenzhen chest X-ray (CXR) dataset made available by the U.S. National Library of Medicine and obtained via a research collaboration with No. 3. People’s Hospital Shenzhen, China. The goal of releasing these annotations is to advance the state of the art for image segmentation methods toward improving the performance of the fine-grained segmentation of TB-consistent findings in digital chest X-ray images. The annotation collection comprises the following: (1) annotation files in JavaScript Object Notation (JSON) format that indicate locations and shapes of 19 lung pattern abnormalities for 336 TB patients;(2) mask files saved in PNG format for each abnormality per TB patient;and (3) a comma-separated values (CSV) file that summarizes lung abnormality types and numbers per TB patient. To the best of our knowledge, this is the first collection of pixel-level annotations of TB-consistent findings in CXRs.Dataset:https://data.lhncbc.nlm.nih.gov/public/Tuberculosis-Chest-X-ray-Datasets/Shenzhen-Hospital-CXR-Set/Annotations/index.html.Dataset License: Attribution 4.0 International—CC BY-4.0

9.
2022 International Conference on IoT and Blockchain Technology, ICIBT 2022 ; 2022.
Article in English | Scopus | ID: covidwho-1961395

ABSTRACT

Proper assessment of COVID-19 patients has become critical to mitigating and halting the disease's rapid expansion during the present COVID-19 epidemic across the nations. Due to the presence of chronic lung/pulmonary diseases, the intensity and demise rates of COVID-19 patients were increased. This study will analyze radiography utilizing chest X-ray images (CXI), one of the most successful testing methods for COVID-19 case identification. Given that deep learning (DL) is a useful method and technique for image processing, there have been several research on COVID-19 case identification using CXI to train DL models. While few of the study claims outstanding predictive outcomes, their suggested models may struggle with overfitting, excessive variance, and generalization mistakes due to noise, a limited number of datasets and could not be deployed to IoT devices due to heavy network size. Considering deep Convolutional Neural Network (CNN) can conquer the weaknesses by getting predictions with several diseases using a single model deployed on a real-time IoT device. We propose a lightweight Deep Learning model (LDC-Net) that has spearheaded an open-sourced COVID-19 case identification technique using CNN-generated CXI by utilizing a suggested strategy aware of distinct features learning of different classes. Experimental results on Raspberry Pi show that LDC-Net provides encouraging outputs for detecting COVID-19 cases with an overall 96.86% precision, 96.78% recall, 96.77% F1-score, and 99.28% accuracy, better than other state-of-the-art models. By empowering the Internet of Things-IoT and IoMT devices, this suggested framework can identify COVID-19 from CXI and other seven lung diseases with healthy labels. © 2022 IEEE.

10.
2nd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2022 ; 2022.
Article in English | Scopus | ID: covidwho-1961381

ABSTRACT

The COVID-19 epidemic has claimed many lives throughout the world and constitutes an unprecedented public health concern. The key challenge in early detection of the corona virus is early detection. And the main obstacle was the similarity of COVID-19 symptoms to flu symptoms. With the goal of saving human lives and stemming the spread of a worldwide pandemic, an accurate and speedy analysis of COVID-19-induced pneumonia has now taken centre stage. Responding this urgent concern and to reduce the burden as well as chances of faulty manual diagnosis, several deep learning approaches are developed to conduct early diagnosis. Based on the availability of reliable patient's records, an accepted technique is pre-trained deep learning prediction approach through patient's chest X-Rays. Convenience of this approach led development of a number of novel deep learning-based lung screening technologies. However, little emphasis is placed on ensuring the quality of their output. Pre-trained deep learning systems will be used in this project to evaluate their ability to recognise and diagnose disorders. To categorise COVID and normal pictures, a neural network-based ResNet50 architecture is presented. The implementation is based on the normal, COVID, and lung opacity datasets. For data pre-processing, ImageDataGenerator is used, which rescales, flips, and modifies the range to meet the model. To categorise the x- ray images, the suggested method ResNet50 architecture is used. Performance matrices like precision, accuracy, recall, as well as F1-score are examined to verify the algorithm's usefulness. The suggested technique has an accuracy of 80%, indicating that the proposed model is quite good in classifying COVID and normal x-ray pictures. This research will have a significant influence on real-time since it will accurately diagnose COVID in less time, perhaps lowering the mortality rate. © 2022 IEEE.

11.
4th International Conference on Computational Intelligence in Pattern Recognition, CIPR 2022 ; 480 LNNS:313-325, 2022.
Article in English | Scopus | ID: covidwho-1958950

ABSTRACT

Humanity has faced the greatest difficulties in recent years in COVID-19. These diseases are caused by significant alveolar damage and progressive respiratory failure. To address this issue, healthcare facilities needed rapid testing methods to identify COVID-19 patients and treat them immediately. In this paper, we developed a rapid testing strategy using machine and deep learning architecture with three different categories of chest x-ray images, such as COVID-19, normal, and pneumonia, were considered to identify the COVID-19 affected images. It is very difficult to diagnose COVID-19 from the pool of chest x-ray images, as pneumonia and COVID-19 affected x-ray images closely resemble each other. For this issue, feature extraction plays an important role. Here we considered deep features which were extracted from deep learning models such as VGG19 and InceptionResnetV2. These deep features were classified using different machine learning algorithms. It was observed that 96.81% accuracy was obtained after classification using MLP. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

12.
4th International Conference on Computational Intelligence in Pattern Recognition, CIPR 2022 ; 480 LNNS:1-10, 2022.
Article in English | Scopus | ID: covidwho-1958943

ABSTRACT

Lung abnormality is a prevalent condition that affects people of all ages, and it can be caused by a variety of factors. The lung illness caused by SARS-CoV-2 has recently spread across the globe, and the World Health Organization (WHO) has labelled it a pandemic disease owing to its quickness. Covid-19 mainly attacks the lungs of those infected, resulting in mortality from ARDS and pneumonia in extreme instances. Internal body organ disorders are thought to be more acute, making diagnosis more complex and time-consuming. The source of any illness, location and severity are determined by a pulmonologist basing upon a good number of tests taken in the laboratories or even outside these after the hospitalization of a patient. In between a lot of time is taken to carry out these tests and prediction of COVID 19 is done. The purpose of this work is to propose a model based on CNN and finding out the best fit segmentation algorithm to apply to the chest X-ray scans in order to predict the test result. Most importantly the result is instantaneous. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

13.
2nd International Conference on Electronics, Biomedical Engineering, and Health Informatics, ICEBEHI 2021 ; 898:237-251, 2022.
Article in English | Scopus | ID: covidwho-1958938

ABSTRACT

The COVID 2019 outbreak has been designated by WHO as a pandemic since 2020. Various methods of diagnosis of COVID 19 have been developed by several researchers to cope with COVID 19. A proper and accurate diagnosis is crucial for the next treatment step. Deep learning has been widely applied in the image classification process with high accuracy. However, the selection of the right deep learning model for the detection of lung disorders caused by COVID-19 based on x-ray images of the chest has not been widely reviewed by several reference sources. Therefore, the purpose of this study is to do a paper review that reviews a deep learning approach to detect COVID 19 through chest X-ray images. The reference sources used in the preparation of this review paper are from various databases such as PubMed, IEEE-explore, and ScienceDirect in the period of 2020–2021. The results of the review and discussion show that deep learning with the convolution neural network (CNN) algorithm is more widely applied in the process of recognizing patterns of lung abnormalities caused by COVID 19. However, deep learning with transfer learning has the potential for better accuracy because it applies the architecture that has been used to solve the same previous problem. The conclusion that can be drawn from this study is that CNN is still the right method for diagnosing lung disorders caused by COVID 10 compared to conventional machine learning. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

14.
2nd International Conference on Electronics, Biomedical Engineering, and Health Informatics, ICEBEHI 2021 ; 898:35-57, 2022.
Article in English | Scopus | ID: covidwho-1958936

ABSTRACT

New Coronavirus 2019 (COVID-19) is a virus that causes severe pneumonia and affects many organs of the body. This infection was initially discovered in one of the cities in the Republic of China, Wuhan, in December 2019 and since then has been spread throughout the globe as a global pandemic. To prevent the virus from spreading, positive cases must be identified early and infected persons must be treated as soon as possible. As new instances emerge regularly, many developing countries are experiencing COVID-19 testing kit scarcity because the demand for testing kits has soared. As an alternative, radiological imaging techniques such as X-ray images have been proven to help in COVID-19 diagnosis because images from X-ray provide valuable information about the COVID-19 virus disease. This paper presents a survey of Deep learning-based methods in identifying COVID-19 with X-ray input images, and classifies these images into several categories, namely: no findings, normal, COVID, and pneumonia. Several studies have been included with details about their datasets, methodologies, and findings. A total of thirteen popular datasets and fifteen articles are reviewed in this paper. Research challenges and recommendations for future research directions are also provided as an evaluation of previous research. Search for research articles in well-known digital libraries, namely Scopus, IEEE Xplore, Springer, and ScienceDirect, was carried out to obtain a list of studies relevant to the scope of research. Related articles that have a high impact are considered in the list of studies. Also, in selecting studies related to the research scope, we apply some inclusion and exclusion criteria. The list of studies used in subsequent research is imported to the library. Then, studies that did not match the criteria for inclusion were eliminated. The clinical application of artificial intelligence, i.e., DL in diagnosing COVID-19, is promising, and further research is needed. Convolutional Neural Network (CNN) approaches could be used in collaboration through X-ray pictures to identify diseases quickly and accurately, reducing the shortage of testing equipment and their restrictions. It is expected that this work can help researchers understand the general picture and existing research gaps to decide on the appropriate architecture and approach in developing deep learning-based covid identification research. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

15.
International Conference on Advances in Electrical and Computer Technologies, ICAECT 2021 ; 881:727-738, 2022.
Article in English | Scopus | ID: covidwho-1958934

ABSTRACT

COVID-19 is one of the most dangerous virus that has been separated among the entire world. At the beginning stage of COVID-19 virus, the RT-PCR is the only testing method to detect the virus. Later, the medical professions analyze the different medical scanning approaches for the detecting of COVID-19. The computer tomography (CT) and chest X-ray (CXR) images are well-suited for detecting the virus. In image processing algorithms, there is lots of deep learning (DL) algorithms are employed for identifying the diseases which are affected in the human body. Hence, the paper presents the deep learning approach of COVID-19 detection by using the CT/CXR medical images. Here, the pre-trained MobileNetV2 is fully loaded with training dataset of COVID-19 images. Initially, the testing medical images are preprocessed by DnCNN algorithm to get the residual image of the corresponding medical image and forwarded to the feature extraction unit, and finally, the classifier finds the COVID-19, non-COVID-19, and pneumonia from the testing dataset. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

16.
3rd International Conference on Machine Intelligence and Signal Processing, MISP 2021 ; 858:19-33, 2022.
Article in English | Scopus | ID: covidwho-1958922

ABSTRACT

The COVID-19 pandemic has caused economic, physiological, and psychological harm to the world. A crucial step, hence, in the fight against covid is the highly efficient screening of patient cases. Conventional RT-PCR testing, even though more reliable, cannot be done on every patient as the virus has spread way faster than the world’s resources could afford. One very important screening approach that is being used across the globe is chest X-ray imaging. Since X-ray facilities are readily obtainable in healthcare systems of most countries across the globe, and with more and more X-ray systems being digitized, the cost and time of transportation are cut as well. Hence, if the detection of the virus in a CXR image can be automated using AI techniques, it will save a lot of time and effort of radiologists to have to go through hundreds of such images, and in some cases will also spare the need of doing RT-PCR testing, and since saving resources in this time is vital, automated detection can be very effective. In this work, we will explore, analytically discuss, and do a comparative study of many ML and deep learning techniques that have been taken for automated COVID-19 detection through chest X-rays (CXR). We carefully analyze the papers and derive a set of key factors for discriminating the methodologies, classification techniques, approaches, and the results that yielded. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

17.
22nd Annual International Conference on Computational Science, ICCS 2022 ; 13351 LNCS:441-454, 2022.
Article in English | Scopus | ID: covidwho-1958885

ABSTRACT

A critical step in the fight against COVID-19, which continues to have a catastrophic impact on peoples lives, is the effective screening of patients presented in the clinics with severe COVID-19 symptoms. Chest radiography is one of the promising screening approaches. Many studies reported detecting COVID-19 in chest X-rays accurately using deep learning. A serious limitation of many published approaches is insufficient attention paid to explaining decisions made by deep learning models. Using explainable artificial intelligence methods, we demonstrate that model decisions may rely on confounding factors rather than medical pathology. After an analysis of potential confounding factors found on chest X-ray images, we propose a novel method to minimise their negative impact. We show that our proposed method is more robust than previous attempts to counter confounding factors such as ECG leads in chest X-rays that often influence model classification decisions. In addition to being robust, our method achieves results comparable to the state-of-the-art. The source code and pre-trained weights are publicly available at (https://github.com/tomek1911/POTHER ). © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

18.
Jpn J Radiol ; 2022 Jul 26.
Article in English | MEDLINE | ID: covidwho-1959094

ABSTRACT

PURPOSE: We aimed to characterize novel coronavirus infections based on imaging [chest X-ray and chest computed tomography (CT)] at the time of admission. MATERIALS AND METHODS: We extracted data from 396 patients with laboratory-confirmed COVID-19 who were managed at 68 hospitals in Japan from January 25 to September 2, 2020. Case patients were categorized as severe (death or treatment with invasive ventilation during hospitalization) and non-severe groups. The imaging findings of the groups were compared by calculating odds ratios (ORs) and 95% confidence intervals (95% CIs), adjusted for sex, age, and hospital size (and radiographic patient positioning for cardiomegaly). Chest X-ray and CT scores ranged from 0 to 72 and 0 to 20, respectively. Optimal cut-off values for these scores were determined by a receiver-operating characteristic (ROC) curve analysis. RESULTS: The median age of the 396 patients was 48 years (interquartile range 28-65) and 211 (53.3%) patients were male. Thirty-two severe cases were compared to 364 non-severe cases. At the time of admission, abnormal lesions on chest X-ray and CT were mainly observed in the lower zone/lobe. Among severe cases, abnormal lesions were also seen in the upper zone/lobe. After adjustment, the total chest X-ray and CT score values showed a dose-dependent association with severe disease. For chest X-ray scores, the area under the ROC curve (AUC) was 0.91 (95% CI = 0.86-0.97) and an optimal cut-off value of 9 points predicted severe disease with 83.3% sensitivity and 84.7% specificity. For chest CT scores, the AUC was 0.94 (95% CI = 0.89-0.98) and an optimal cut-off value of 11 points predicted severe disease with 90.9% sensitivity and 82.2% specificity. Cardiomegaly was strongly associated with severe disease [adjusted OR = 24.6 (95% CI = 3.7-166.0)]. CONCLUSION: Chest CT and X-ray scores and the identification of cardiomegaly could be useful for classifying severe COVID-19 on admission.

19.
Indian Journal of Forensic Medicine and Toxicology ; 16(2):326-333, 2022.
Article in English | EMBASE | ID: covidwho-1957671

ABSTRACT

Coronavirus disease 2019 discovered in December 2019, Wuhan, China. It was transmitted globally producing the present COVID-19 pandemic. Concerns have been raised about the potential impact of COVID-19 on male reproductive organs and male fertility as the number of infections in the male community has increased. The objectives of current study are studying the relationship between the plasma levels of testosterone and the markers of immune reaction with the severity and mortality in a sample of COVID-19 patients. A cross section study included NO= 103 male patients affected by SARS-CoV-2 pneumonia, diagnosed by PCR and chest CT scan, (≥ 18 years old), and recovered in the respiratory intensive care unit (RICU). Several biochemical risk factors were determined Free Testosterone, sex hormone binding globulin (SHBG) were measured by Enzyme-Linked Immunosorbent Assay(ELISA), D-dimer, Ferritin, CRP, Urea, Creatinine were measured by automated method by using Abbott Architect c4000 and Complete Blood Count(CBC). The results show that the serum free testosterone and SHBG levels a significant lower in non-survivor patients than survivor patients with COVID-19. While the other biomarkers (D-dimer, Ferritin, Urea, Creatinine) were significant higher in non-survivor patients than survivor patients. The CRP, WBC and lymphocyte showed that no significant between the both group of patients. In conclusion the study showed that lower free testosterone and SHBG levels enable significant role in increasing risk of COVID-19 mortality amongst adult male patients.

20.
Journal of Clinical Periodontology ; 49:62, 2022.
Article in English | EMBASE | ID: covidwho-1956754

ABSTRACT

Background & Aim: Assessment and acceptance of phantom based periodontal education due to COVID-related restrictions in undergraduate treatment courses. Methods: 48 undergraduate students (mean age: 24 ± 2 years) in semester 7 (n = 20) and 9 (n = 24) were asked to evaluated case based education under simulated conditions as a partial substitute in times of Covid-19. Four complex periodontal scenarios were [MW1] simulated based on the four quadrants of the Frasaco AP-Z model. The following information was provided: medical and dental history, primary concern, X-ray and oral hygiene findings. Periodontal examination and subgingival instrumentation were performed in the AP-Z model. The evaluation form consisted of nine questions of the ADEE criteria domain III (Likert scale) and additionally, a global score from one to six (German school grade equivalent) should be given. [MW1] Hier würde ich Stichworte der vier Fälle nennen, damit man das versteht. Results: 44 of 48 students (92%) completed the questionnaire. 91% rated integration of the simulated cases as a valuable addition to their daily clinical routine and 71% reported being more confident in clinical treatment. The learning effect in the following competences was found to be higher in simulated cases than in clinical situations: Diagnosis finding, risk analysis and treatment planning. Diagnostic assessment and subgingival instrumentation were reported to be superior in clinical patients, although there were differences between 7th and 9th semester students (p < .05). Students in the 9thsemester rated the usefulness of psychomotoric training lower, whereas both groups rated the simulated periodontal education superior to clinical treatments. Overall, adjunctive simulated periodontal education was rated as “good” (1.9).7 Conclusions: The adjunctive use of simulated periodontal cases was highly valued by undergraduate students. In this simulated setting, case discussions of more complex periodontal cases with defined learning goals are a valuable and accepted supplement in the periodontal curriculum especially under pandemic situations with restrictive patient treatment.

SELECTION OF CITATIONS
SEARCH DETAIL