scholarly journals Semi-supervised learning for an improved diagnosis of COVID-19 in CT images

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0249450
Author(s):  
Chang Hee Han ◽  
Misuk Kim ◽  
Jin Tae Kwak
Keyword(s):  
Diagnostic Accuracy ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Ct Images ◽  
Diagnostic Tools ◽  
Rt Pcr ◽  
The Public ◽  
Feature Representations ◽  
Polymerase Chain ◽  
And Training

Coronavirus disease 2019 (COVID-19) has been spread out all over the world. Although a real-time reverse-transcription polymerase chain reaction (RT-PCR) test has been used as a primary diagnostic tool for COVID-19, the utility of CT based diagnostic tools have been suggested to improve the diagnostic accuracy and reliability. Herein we propose a semi-supervised deep neural network for an improved detection of COVID-19. The proposed method utilizes CT images in a supervised and unsupervised manner to improve the accuracy and robustness of COVID-19 diagnosis. Both labeled and unlabeled CT images are employed. Labeled CT images are used for supervised leaning. Unlabeled CT images are utilized for unsupervised learning in a way that the feature representations are invariant to perturbations in CT images. To systematically evaluate the proposed method, two COVID-19 CT datasets and three public CT datasets with no COVID-19 CT images are employed. In distinguishing COVID-19 from non-COVID-19 CT images, the proposed method achieves an overall accuracy of 99.83%, sensitivity of 0.9286, specificity of 0.9832, and positive predictive value (PPV) of 0.9192. The results are consistent between the COVID-19 challenge dataset and the public CT datasets. For discriminating between COVID-19 and common pneumonia CT images, the proposed method obtains 97.32% accuracy, 0.9971 sensitivity, 0.9598 specificity, and 0.9326 PPV. Moreover, the comparative experiments with respect to supervised learning and training strategies demonstrate that the proposed method is able to improve the diagnostic accuracy and robustness without exhaustive labeling. The proposed semi-supervised method, exploiting both supervised and unsupervised learning, facilitates an accurate and reliable diagnosis for COVID-19, leading to an improved patient care and management.

scholarly journals A weakly supervised learning method based on attention fusion for Covid-19 segmentation in CT images

2021 ◽  
pp. 1-12
Author(s):  
Hongyu Chen ◽  
Shengsheng Wang
Keyword(s):  
Image Segmentation ◽  
Supervised Learning ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Great Success ◽  
Segmentation Method ◽  
Rt Pcr ◽  
Weakly Supervised Learning ◽  
Polymerase Chain ◽  
Weakly Supervised

Since the end of 2019, the COVID-19, which has swept across the world, has caused serious impacts on public health and economy. Although Reverse Transcription-Polymerase Chain Reaction (RT-PCR) is the gold standard for clinical diagnosis, it is very time-consuming and labor-intensive. At the same time, more and more people have doubted the sensitivity of RT-PCR. Therefore, Computed Tomography (CT) images are used as a substitute for RT-PCR. Powered by the research of the field of artificial intelligence, deep learning, which is a branch of machine learning, has made a great success on medical image segmentation. However, general full supervision methods require pixel-level point-by-point annotations, which is very costly. In this paper, we put forward an image segmentation method based on weakly supervised learning for CT images of COVID-19, which can effectively segment the lung infection area and doesn’t require pixel-level labels. Our method is contrasted with another four weakly supervised learning methods in recent years, and the results have been significantly improved.

scholarly journals Point-of-Care Diagnostics of COVID-19: From Current Work to Future Perspectives

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4289 ◽  
Author(s):  
Heba A. Hussein ◽  
Rabeay Y. A. Hassan ◽  
Marco Chino ◽  
Ferdinando Febbraio
Keyword(s):  
Point Of Care ◽  
Virus Detection ◽  
Diagnostic Tools ◽  
Sample Treatment ◽  
Rt Pcr ◽  
Point Of Care Diagnostics ◽  
Electrochemical Immunosensors ◽  
Global Concern ◽  
Polymerase Chain ◽  
Reliable Methods

Coronaviruses have received global concern since 2003, when an outbreak caused by SARS-CoV emerged in China. Later on, in 2012, the Middle-East respiratory syndrome spread in Saudi Arabia, caused by MERS-CoV. Currently, the global crisis is caused by the pandemic SARS-CoV-2, which belongs to the same lineage of SARS-CoV. In response to the urgent need of diagnostic tools, several lab-based and biosensing techniques have been proposed so far. Five main areas have been individuated and discussed in terms of their strengths and weaknesses. The cell-culture detection and the microneutralization tests are still considered highly reliable methods. The genetic screening, featuring the well-established Real-time polymerase chain reaction (RT-PCR), represents the gold standard for virus detection in nasopharyngeal swabs. On the other side, immunoassays were developed, either by screening/antigen recognition of IgM/IgG or by detecting the whole virus, in blood and sera. Next, proteomic mass-spectrometry (MS)-based methodologies have also been proposed for the analysis of swab samples. Finally, virus-biosensing devices were efficiently designed. Both electrochemical immunosensors and eye-based technologies have been described, showing detection times lower than 10 min after swab introduction. Alternative to swab-based techniques, lateral flow point-of-care immunoassays are already commercially available for the analysis of blood samples. Such biosensing devices hold the advantage of being portable for on-site testing in hospitals, airports, and hotspots, virtually without any sample treatment or complicated lab precautions.

scholarly journals Point-of-Care Diagnostic Tools for Surveillance of SARS-CoV-2 Infections

2021 ◽  
Vol 9 ◽  
Author(s):  
Dhanasekaran Sakthivel ◽  
David Delgado-Diaz ◽  
Laura McArthur ◽  
William Hopper ◽  
Jack S. Richards ◽  
...  
Keyword(s):  
Large Scale ◽  
Clinical Symptoms ◽  
Point Of Care ◽  
Cost Effective ◽  
Nucleic Acid Amplification ◽  
Diagnostic Tools ◽  
Rt Pcr ◽  
Serological Tests ◽  
Polymerase Chain ◽  
Effective Public Health

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) is a recently emerged and highly contagious virus that causes coronavirus disease 2019 (COVID-19). As of August 24, 2021, there were more than 212 million confirmed COVID-19 cases and nearly 4.4 million deaths reported globally. Early diagnosis and isolation of infected individuals remains one of the most effective public health interventions to control SARS-CoV-2 spread and for effective clinical management of COVID-19 cases. Currently, SARS-CoV-2 infection is diagnosed presumptively based on clinical symptoms and confirmed by detecting the viral RNA in respiratory samples using reverse transcription polymerase chain reaction (RT-PCR). Standard RT-PCR protocols are time consuming, expensive, and technically demanding, which makes them a poor choice for large scale and point-of-care screening in resource-poor settings. Recently developed isothermal nucleic acid amplification tests (iNAAT), antigen and/or serological tests are cost-effective to scale COVID-19 testing at the point-of-care (PoC) and for surveillance activities. This review discusses the development of rapid PoC molecular tools for the detection and surveillance of SARS-CoV-2 infections.

scholarly journals High Resolution CHEST CT(HRCT) Evaluation in Patients Hospitalized with COVID-19 Infection

2020 ◽  
Author(s):  
Maulin Patel ◽  
Junad Chowdhury ◽  
Matthew Zheng ◽  
Osheen Abramian ◽  
Steven Verga ◽  
...  
Keyword(s):  
Polymerase Chain Reaction ◽  
High Resolution ◽  
Diagnostic Accuracy ◽  
Reverse Transcriptase ◽  
Retrospective Analysis ◽  
Nasopharyngeal Swab ◽  
Rt Pcr ◽  
Chain Reaction ◽  
Bottom Line ◽  
Polymerase Chain

AbstractIntroductionCurrently the main diagnostic modality for COVID-19 (Coronavirus disease-2019) is reverse transcriptase polymerase chain reaction (RT-PCR) via nasopharyngeal swab which has high false negative rates. We evaluated the performance of high-resolution computed tomography (HRCT) imaging in the diagnosis of suspected COVID-19 infection compared to RT-PCR nasopharyngeal swab alone in patients hospitalized for suspected COVID-19 infection.MethodsThis was a retrospective analysis of 324 consecutive patients admitted to Temple University Hospital. All hospitalized patients who had RT-PCR testing and HRCT were included in the study. HRCTs were classified as Category 1, 2 or 3. Patients were then divided into four groups based on HRCT category and RT-PCR swab results for analysis.ResultsThe average age of patients was 59.4 (±15.2) years and 123 (38.9%) were female. Predominant ethnicity was African American 148 (46.11%). 161 patients tested positive by RT-PCR, while 41 tested positive by HRCT. 167 (52.02%) had category 1 scan, 63 (19.63%) had category 2 scan and 91 (28.35%) had category 3 HRCT scans. There was substantial agreement between our radiologists for HRCT classification (κ = 0.64). Sensitivity and specificity of HRCT classification system was 77.6 and 73.7 respectively. Ferritin, LDH, AST and ALT were higher in Group 1 and D-dimers levels was higher in Group 3; differences however were not statistically significant.ConclusionDue to its high infectivity and asymptomatic transmission, until a highly sensitive and specific COVID-19 test is developed, HRCT should be incorporated into the assessment of patients who are hospitalized with suspected COVID-19.Key PointsKey QuestionCan High Resolution CT chest (HRCT) improve diagnostic accuracy of current Nasopharyngeal swab in suspected COVID-19 patients?Bottom LineIn this retrospective analysis, our novel HRCT classification identified 20% of all COVID-19 patients who had negative nasopharyngeal reverse transcriptase polymerase chain reaction (RT-PCR) tests but had HRCT findings consistent with COVID-19 pneumonia. These patients were ruled out for other infections and laboratory markers were similar to other RT-PCR positive patientsWhy Read onOur new HRCT classification when combined with RT-PCR can improve diagnostic accuracy while promptly improving triaging in COVID-19 patients.

scholarly journals Seeing beyond a Dilated Proventriculus: Diagnostic Tools for Proventricular Dilatation Disease in Psittacine Birds

Animals ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 3558
Author(s):  
Jeann Leal de Araújo ◽  
Raquel Rubia Rech
Keyword(s):  
Molecular Techniques ◽  
Diagnostic Tools ◽  
Enzyme Linked Immunosorbent Assay ◽  
Rt Pcr ◽  
Postmortem Diagnosis ◽  
Concise Review ◽  
Life Threatening ◽  
Polymerase Chain ◽  
Proventricular Dilatation Disease ◽  
Diagnostic Outcomes

Proventricular dilatation disease (PDD) is a life-threatening neurological disease caused by parrot bornaviruses (PaBVs) that affects several species worldwide. PDD can be clinically manifested as either a central nervous system condition or a gastrointestinal condition if the nerves and ganglia of the gastrointestinal tract are compromised. We intend to provide a concise review for veterinary clinicians and diagnosticians with focus on the main tools available for PDD diagnosis, including gross and histopathology, immunohistochemistry, molecular techniques and serology. We suggest that a combination of different strategies can increase the success of diagnostic outcomes, as tools such as reverse transcription polymerase chain reaction (RT-PCR) and enzyme-linked immunosorbent assay (ELISA) can be implemented for identification of bornaviral infections in live patients, and gross pathology, histopathology, immunohistochemistry and RT-PCR can provide reliable results for postmortem diagnosis of PDD.

scholarly journals Competences of Clinical Psychologists

2019 ◽  
Vol 1 (2) ◽  
Author(s):  
Keyword(s):  
Clinical Psychology ◽  
Education And Training ◽  
Clinical Psychologists ◽  
European Countries ◽  
Diagnostic Tools ◽  
Discussion Paper ◽  
The Public ◽  
Competence Profile ◽  
Training Programmes ◽  
And Training

Politicians, societies, stakeholders, health care systems, patients, their relatives, their employers, and the general population need to know what they can expect from clinical psychologists. Even more, for our self-definition as a professional group, we should share a common understanding of the competence profile that characterises our qualifications. This understanding of the competence profile of clinical psychology leads directly to the content that should be taught in university curricula and postgraduate trainings for clinical psychology. The following discussion paper attempts to offer a general European framework for defining the competence profile of clinical psychologists. A group of European specialists developed this discussion paper under the umbrella of the European Association of Clinical Psychology and Psychological Treatment (EACLIPT). Representatives with different treatment orientations, of basic science and clinical applications, and from East to Western European countries, were part of the group. We present a list of competences that should be acquired during regular studies of psychology with a clinical specialisation. Additionally, further competences should be acquired either during studying, or during postgraduate trainings. Clinical psychologists are experts in mental and behavioural disorders, their underlying psychological, social and neurobiological processes, corresponding assessments/diagnostic tools, and evidence-based psychological treatments. While we provide a list with all competences of clinical psychologists, we do not consider this proposal as a final list of criteria, but rather as a living discussion paper that could be updated regularly. Therefore, we invite our colleagues to contribute to this discussion, and to submit comments via email to the corresponding author. People need to know what they can expect from clinical psychologists. We present a list of competences that clinical psychologists acquire during their training. This list of competences was developed by colleagues representing different treatment orientations, different European countries, and basic versus clinical scientists. This competence list can represent a basis for optimising education and training programmes for clinical psychologists, and for informing the public. People need to know what they can expect from clinical psychologists. We present a list of competences that clinical psychologists acquire during their training. This list of competences was developed by colleagues representing different treatment orientations, different European countries, and basic versus clinical scientists. This competence list can represent a basis for optimising education and training programmes for clinical psychologists, and for informing the public.

scholarly journals A systematic review and meta-analysis comparing the diagnostic accuracy of initial RT-PCR and CT scan in suspected COVID-19 patients

2020 ◽  
pp. 20201039
Author(s):  
Manish Devendra Devendra Mair ◽  
Mohammed Hussain ◽  
Saad Siddiqui ◽  
Sudip Das ◽  
Andrew Baker ◽  
...  
Keyword(s):  
Systematic Review ◽  
Diagnostic Accuracy ◽  
Ct Scan ◽  
Meta Analysis ◽  
Final Analysis ◽  
Inclusion Criteria ◽  
Rt Pcr ◽  
History Of ◽  
Accurate Comparison ◽  
Polymerase Chain

Objective: To perform a systematic review and meta-analysis to compare the diagnostic accuracy of Computed tomography (CT) and initial Reverse transcriptase polymerase chain reaction (RT-PCR) for detecting COVID-19 infection. Methods: We searched three databases, PubMed, EMBASE and EMCARE to identify studies reporting diagnostic accuracy of both CT and RT-PCR in detecting COVID-19 infection between December 2019 and May 2020. For accurate comparison, only those studies which had patients undergoing both, CT and RT-PCR were included. Pooled diagnostic accuracy of both the tests was calculated by using a bivariate random effects model. Results: Based on inclusion criteria, only 11 studies consisting of 1834 patients were included in the final analysis that reported diagnostic accuracy of both CT and RT-PCR, in the same set of patients. Sensitivity estimates for CT scan ranged from 0.69 to 1.00 and for RT-PCR varied ranging from 0.47 to 1.00. The pooled estimates of sensitivity for CT and RT-PCR was 0.91 [95% CI (0.84–0.97)] and 0.84 [95% CI (0.71–0.94)] respectively. On subgroup analysis, pooled sensitivity of CT and RT-PCR was 0.95 [95% CI (0.88–0.98)] and 0.91 [95% CI (0.80–0.96), p = o.ooo1]. The pooled specificity of CT and RT-PCR was 0.31 [95% CI (0.035–0.84)] and 1.00 [95% CI (0.96–1.00)]. Conclusion: CT is more sensitive than RT-PCR in detecting COVID-19 infection, but has a very low specificity. Advances in knowledge: Since the results of a CT scan are available quickly, it can be used as an adjunctive initial diagnostic test for patients with a history of positive contact or epidemiological history.

scholarly journals Diagnostic Accuracy of a New Antigen Test for SARS-CoV-2 Detection

2021 ◽  
Vol 18 (12) ◽  
pp. 6310
Author(s):  
Marina Di Domenico ◽  
Alfredo De Rosa ◽  
Francesca Di Gaudio ◽  
Pietro Internicola ◽  
Cinzia Bettini ◽  
...  
Keyword(s):  
Diagnostic Accuracy ◽  
Test Methods ◽  
Lateral Flow ◽  
Diagnostic Tools ◽  
Nasopharyngeal Swab ◽  
Antigen Test ◽  
Rt Pcr ◽  
Promising Tool ◽  
Flow Test ◽  
Lateral Flow Test

Background and aims: Quick and reliable diagnostic tools play an important role in controlling the spread of the SARS-Cov-2 pandemic. The aim of this study was to evaluate the diagnostic accuracy of a new cyto-salivary antigen test aimed at detecting the presence of antigens for SARS-CoV-2, as compared by the gold standard RT-PCR and a lateral flow test. Methods: A total of 433 healthy volunteers were enrolled in the study and the sensitivity and specificity of the new cyto-salivary antigen test were calculated, as compared to the RT-PCR nasopharyngeal swab and to the lateral flow test. Results: A total of 433 samples were collected and tested at the Mediterranean Fair in Palermo from February 2021 until April 2021. The new cyto-salivary antigen had a sensitivity of 100% and a specificity of 94.2%. The sensitivity and the specificity of the lateral flow test were 55% and 100%, respectively. Conclusions: The new cyto-salivary antigen test detected more positive cases than the RT-PCR in a sample of asymptomatic subjects, demonstrating to be a promising tool for a more sensitive diagnosis of COVID-19. Further studies are warranted to better characterize its diagnostic accuracy.

scholarly journals 147 A Meta-Analysis Comparing the Diagnostic Accuracy of Initial RT-PCR And CT Scan in Suspected COVID-19 Patients

2021 ◽  
Vol 108 (Supplement_2) ◽  
Author(s):  
S Siddiqui ◽  
M Mair ◽  
M Hussain ◽  
S Das
Keyword(s):  
Diagnostic Accuracy ◽  
Ct Scan ◽  
Meta Analysis ◽  
Included Study ◽  
Computed Tomography Scan ◽  
Rt Pcr ◽  
Chain Reaction ◽  
Polymerase Chain ◽  
Tomography Scan

Abstract Introduction Reverse transcriptase Polymerase chain reaction(RT-PCR) is considered as the gold standard diagnostic test for COVID-19 infection. It’s accuracy has been doubted and subsequently had effects on planning, performing operations causing. Research has suggested the use of Computed Tomography Scan instead. In this study we performed a meta-analysis comparing the diagnostic accuracy of CT compared to RTPCR. Method Our systematic review and meta-analysis were undertaken as per PRISMA guidelines. The methodological quality of each included study was assessed using the QUADAS-2 tool on RevMan 5.3. We performed data analyses using Stata version 12. Results Sensitivity estimates for CT scan ranged from 0.69 to 1.00 and for RT-PCR varied ranging from 0.47 to 1.00. The pooled estimate of sensitivity for CT was 0.95 (95% CI – 0.88-0.98) and specificity was 0.31 (95% CI – 0.035-0.84). It was found that specificity of initial RT-PCR(100%) was higher than CT(31%). With respect to sensitivity, CT(95%) was superior to RT-PCR(91%) p (0.000) Conclusions Sensitivity of CT is significantly higher than RT-PCR for detecting COVID-19 infection, however as CT findings are not specific. Since CT scans are readily available, protocols can be developed to utilise it to minimalize delay in planning surgery.

Sign in / Sign up

Export Citation Format

Share Document