1
|
Mahmoudi F, Jafari D, Esfahani SMM, Hoseini A, Barati M, Saraygord-Afshari N. Development and Validation of a Highly Sensitive RT-qLAMP Assay for Rapid Detection of SARS-CoV-2: Methodological Aspects. Mol Biotechnol 2024:10.1007/s12033-024-01275-7. [PMID: 39316362 DOI: 10.1007/s12033-024-01275-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2023] [Accepted: 08/27/2024] [Indexed: 09/25/2024]
Abstract
Specific and reliable diagnostic methods are becoming increasingly essential to identify patients in light of the high transmission rate and the recent appearance of the new variants of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). For the specific detection of SARS-CoV-2, our quantitative reverse transcription loop-mediated isothermal amplification (RT-qLAMP) assay implementation demonstrates how flexible it can be with two readouts: visualized colorimetric and real-time fluorescence. Different factors were optimized to improve the reaction conditions, including temperature (60 °C), assay runtime (60 min), primers, MgSO4 (6 mM), dNTPs (1 mM), LAMP Buffer (1.2 mM Tris-HCl), KCl (50 mM), pH (8), and phenol red (10 mM) concentrations. Regarding analytical sensitivity, the colorimetric RT-LAMP method detected samples with Ct values up to 29, while the RT-qLAMP assay identified up to Ct = 31. RT-qLAMP was evaluated on 40 clinical samples (25 positives and 15 negatives) for viral RNA detection. All negative samples were found negative through fluorescent reading in RT-qLAMP and quantitative reverse transcription PCR (RT-qPCR) assays. Twenty-three clinically positive samples demonstrated a positive RT-qLAMP reaction (up to Ct ≤ 31) with 92% clinical sensitivity, 100% clinical specificity, 100% positive predictive value (PPV), 88.24% negative predictive values (NPV), and 95% accuracy.
Collapse
Affiliation(s)
- Faezeh Mahmoudi
- Department of Medical Biotechnology, Faculty of Allied Medical Sciences, Iran University of Medical Sciences, Tehran, 14496114535, Iran
| | - Davod Jafari
- Department of Medical Biotechnology, Faculty of Allied Medical Sciences, Iran University of Medical Sciences, Tehran, 14496114535, Iran
| | - Seyedeh Mona Mousavi Esfahani
- Department of Medical Biotechnology, Faculty of Allied Medical Sciences, Iran University of Medical Sciences, Tehran, 14496114535, Iran
| | - Arshad Hoseini
- Department of Medical Biotechnology, Faculty of Allied Medical Sciences, Iran University of Medical Sciences, Tehran, 14496114535, Iran
| | - Mahmood Barati
- Department of Medical Biotechnology, Faculty of Allied Medical Sciences, Iran University of Medical Sciences, Tehran, 14496114535, Iran.
| | - Neda Saraygord-Afshari
- Department of Medical Biotechnology, Faculty of Allied Medical Sciences, Iran University of Medical Sciences, Tehran, 14496114535, Iran.
| |
Collapse
|
2
|
Olawade DB, Teke J, Fapohunda O, Weerasinghe K, Usman SO, Ige AO, Clement David-Olawade A. Leveraging artificial intelligence in vaccine development: A narrative review. J Microbiol Methods 2024; 224:106998. [PMID: 39019262 DOI: 10.1016/j.mimet.2024.106998] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2024] [Revised: 07/12/2024] [Accepted: 07/12/2024] [Indexed: 07/19/2024]
Abstract
Vaccine development stands as a cornerstone of public health efforts, pivotal in curbing infectious diseases and reducing global morbidity and mortality. However, traditional vaccine development methods are often time-consuming, costly, and inefficient. The advent of artificial intelligence (AI) has ushered in a new era in vaccine design, offering unprecedented opportunities to expedite the process. This narrative review explores the role of AI in vaccine development, focusing on antigen selection, epitope prediction, adjuvant identification, and optimization strategies. AI algorithms, including machine learning and deep learning, leverage genomic data, protein structures, and immune system interactions to predict antigenic epitopes, assess immunogenicity, and prioritize antigens for experimentation. Furthermore, AI-driven approaches facilitate the rational design of immunogens and the identification of novel adjuvant candidates with optimal safety and efficacy profiles. Challenges such as data heterogeneity, model interpretability, and regulatory considerations must be addressed to realize the full potential of AI in vaccine development. Integrating emerging technologies, such as single-cell omics and synthetic biology, promises to enhance vaccine design precision and scalability. This review underscores the transformative impact of AI on vaccine development and highlights the need for interdisciplinary collaborations and regulatory harmonization to accelerate the delivery of safe and effective vaccines against infectious diseases.
Collapse
Affiliation(s)
- David B Olawade
- Department of Allied and Public Health, School of Health, Sport and Bioscience, University of East London, London, United Kingdom; Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom.
| | - Jennifer Teke
- Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom; Faculty of Medicine, Health and Social Care, Canterbury Christ Church University, United Kingdom
| | | | - Kusal Weerasinghe
- Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom
| | - Sunday O Usman
- Department of Systems and Industrial Engineering, University of Arizona, USA
| | - Abimbola O Ige
- Department of Chemistry, Faculty of Science, University of Ibadan, Ibadan, Nigeria
| | | |
Collapse
|
3
|
Hu WC, Chiu SK, Yang YF, Singh S. COVID-19 Vaccination Reporting and Adverse Event Analysis in Taiwan. Vaccines (Basel) 2024; 12:591. [PMID: 38932320 PMCID: PMC11209125 DOI: 10.3390/vaccines12060591] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2024] [Revised: 05/20/2024] [Accepted: 05/27/2024] [Indexed: 06/28/2024] Open
Abstract
The COVID-19 pandemic necessitated an urgent global response in vaccine deployment, achieving over 70.6% global vaccination coverage with at least one dose. This study focuses on Taiwan's vaccine administration and adverse event reporting, set against a global backdrop. Using data from Taiwan's Vaccine Adverse Event Reporting System (VAERS) and global vaccination data, this study investigates vaccine safety and the public health implications of vaccination strategies from local and global perspectives. Taiwan's proactive approach, resulting in high vaccination rates, provides a case study for the monitoring and management of vaccine-related adverse events. This study offers insights into the safety profiles of various COVID-19 vaccines and further explores the implications of adverse event reporting rates for vaccine policy and public health strategies. The comparative analysis reveals that, while vaccination has been effective in controlling the virus's spread, safety monitoring remains critical for maintaining public trust. It underscores the necessity of enhanced surveillance and the importance of transparent and tailored risk communication to support informed public health decisions. The findings aim to contribute to the global dialogue on vaccine safety, equitable distribution, evidence-based policy-making, and development of mitigation measures with consideration of local demographics in the ongoing fight against COVID-19.
Collapse
Affiliation(s)
- Wan-Chung Hu
- Department of Clinical Pathology, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City 231, Taiwan;
- Department of Medical Research, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City 231, Taiwan
- Department of Biotechnology, Ming Chuan University, Taoyuan 333, Taiwan
| | - Sheng-Kang Chiu
- Division of Infection Diseases, Department of Medicine, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City 231, Taiwan;
- School of Medicine, Tzu Chi University, Hualien 970, Taiwan
- Division of Infectious Diseases and Tropical Medicine, Department of Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan
| | - Ying-Fei Yang
- Department of Bioenvironmental Systems Engineering, National Taiwan University, Taipei 10617, Taiwan
| | - Sher Singh
- Department of Life Science, School of Life Science, College of Science, National Taiwan Normal University, Taipei 11677, Taiwan
| |
Collapse
|
4
|
Seder I, Coronel-Tellez R, Helalat SH, Sun Y. Fully integrated sample-in-answer-out platform for viral detection using digital reverse transcription recombinase polymerase amplification (dRT-RPA). Biosens Bioelectron 2023; 237:115487. [PMID: 37352758 DOI: 10.1016/j.bios.2023.115487] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2023] [Revised: 06/02/2023] [Accepted: 06/15/2023] [Indexed: 06/25/2023]
Abstract
Recombinase polymerase amplification (RPA) is one of the most promising diagnostic methods for pathogen detection, owing to the simplified isothermal amplification technique. Using one-step digital reverse transcription RPA (dRT-RPA) to detect viral RNA provides a fast diagnosis and absolute quantification. Here, we present a chip that purifies, digitalizes, and detects viral RNA of SARS-CoV-2 in a fully automated and sensitive manner. The chip purifies the RNA using the surface charge concept of magnet bead-RNA binding, then mixes the RNA with the amplification reagents, digitalizes the amplification mixture, and performs dRT-RPA. RNA-bead complex is transported among purification buffers that are separated by an oil phase. For reagent manipulation and mixing, a magnetic valve system is integrated on the chip, where an external magnet controls the reagent direction and time of addition. Besides, a novel vacuum system is suggested to drive and regulate the reagents into two fluid systems simultaneously in ∼2 min. We also developed a cost-effective way to perform fluorescent detection for dRT-RPA on chip by using EvaGreen® dye. With integrated heating and optical detection system, the on-chip dRT-RPA presents a sample-to-answer detection platform for absolute viral RNA quantitation in 37 min and a sensitivity as low as 10 RNA copies/μL. Hence, this platform is expected to be a useful tool for accurate and automated diagnosis of infectious diseases.
Collapse
Affiliation(s)
- Islam Seder
- Department of Health Technology, Technical University of Denmark, Ørsteds Plads, DK-2800, Kgs. Lyngby, Denmark
| | - Rodrigo Coronel-Tellez
- Department of Health Technology, Technical University of Denmark, Ørsteds Plads, DK-2800, Kgs. Lyngby, Denmark
| | - Seyed Hossein Helalat
- Department of Health Technology, Technical University of Denmark, Ørsteds Plads, DK-2800, Kgs. Lyngby, Denmark
| | - Yi Sun
- Department of Health Technology, Technical University of Denmark, Ørsteds Plads, DK-2800, Kgs. Lyngby, Denmark.
| |
Collapse
|
5
|
Firouzabadi N, Ghasemiyeh P, Moradishooli F, Mohammadi-Samani S. Update on the effectiveness of COVID-19 vaccines on different variants of SARS-CoV-2. Int Immunopharmacol 2023; 117:109968. [PMID: 37012880 PMCID: PMC9977625 DOI: 10.1016/j.intimp.2023.109968] [Citation(s) in RCA: 23] [Impact Index Per Article: 23.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2023] [Revised: 02/27/2023] [Accepted: 02/27/2023] [Indexed: 03/06/2023]
Abstract
It has been more than three years since the first emergence of coronavirus disease 2019 (COVID-19) and millions of lives have been taken to date. Like most pandemics caused by viral infections, massive public vaccination is the most promising approach to cease COVID-19 infection. In this regard, several vaccine platforms including inactivated virus, nucleic acid-based (mRNA and DNA vaccines), adenovirus-based, and protein-based vaccines have been designed and developed for COVID-19 prevention and many of them have received FDA or WHO approval. Fortunately, after global vaccination, the transmission rate, disease severity, and mortality rate of COVID-19 infection have diminished significantly. However, a rapid increase in COVID-19 cases due to the omicron variant in vaccinated countries has raised concerns about the effectiveness of these vaccines. In this review, articles published between January 2020 and January 2023 were reviewed using PubMed, Google Scholar, and Web of Science search engines with appropriate related keywords. The related papers were selected and discussed in detail. The current review mainly focuses on the effectiveness and safety of COVID-19 vaccines against SARS-CoV-2 variants. Along with discussing the available and approved vaccines, characteristics of different variants of COVID-19 have also been discussed in brief. Finally, the currently circulating COVID-19 variant i.e Omicron, along with the effectiveness of available COVID-19 vaccines against these new variants are discussed in detail. In conclusion, based on the available data, administration of newly developed bivalent mRNA COVID-19 vaccines, as booster shots, would be crucial to prevent further circulation of the newly developed variants.
Collapse
Affiliation(s)
- Negar Firouzabadi
- Department of Pharmacology and Toxicology, School of Pharmacy, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Parisa Ghasemiyeh
- Pharmaceutical Sciences Research Center, Shiraz University of Medical Sciences, Shiraz, Iran; Department of Clinical Pharmacy, School of Pharmacy, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Fatemeh Moradishooli
- Pharmaceutical Sciences Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Soliman Mohammadi-Samani
- Pharmaceutical Sciences Research Center, Shiraz University of Medical Sciences, Shiraz, Iran; Department of Pharmaceutics, School of Pharmacy, Shiraz University of Medical Sciences, Shiraz, Iran.
| |
Collapse
|
6
|
Computational Portable Microscopes for Point-of-Care-Test and Tele-Diagnosis. Cells 2022; 11:cells11223670. [PMID: 36429102 PMCID: PMC9688637 DOI: 10.3390/cells11223670] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2022] [Revised: 11/11/2022] [Accepted: 11/16/2022] [Indexed: 11/22/2022] Open
Abstract
In bio-medical mobile workstations, e.g., the prevention of epidemic viruses/bacteria, outdoor field medical treatment and bio-chemical pollution monitoring, the conventional bench-top microscopic imaging equipment is limited. The comprehensive multi-mode (bright/dark field imaging, fluorescence excitation imaging, polarized light imaging, and differential interference microscopy imaging, etc.) biomedical microscopy imaging systems are generally large in size and expensive. They also require professional operation, which means high labor-cost, money-cost and time-cost. These characteristics prevent them from being applied in bio-medical mobile workstations. The bio-medical mobile workstations need microscopy systems which are inexpensive and able to handle fast, timely and large-scale deployment. The development of lightweight, low-cost and portable microscopic imaging devices can meet these demands. Presently, for the increasing needs of point-of-care-test and tele-diagnosis, high-performance computational portable microscopes are widely developed. Bluetooth modules, WLAN modules and 3G/4G/5G modules generally feature very small sizes and low prices. And industrial imaging lens, microscopy objective lens, and CMOS/CCD photoelectric image sensors are also available in small sizes and at low prices. Here we review and discuss these typical computational, portable and low-cost microscopes by refined specifications and schematics, from the aspect of optics, electronic, algorithms principle and typical bio-medical applications.
Collapse
|
7
|
Colorimetric and fluorometric reverse transcription loop-mediated isothermal amplification (RT-LAMP) assay for diagnosis of SARS-CoV-2. Funct Integr Genomics 2022; 22:1391-1401. [PMID: 36089609 PMCID: PMC9464610 DOI: 10.1007/s10142-022-00900-5] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Revised: 07/19/2022] [Accepted: 09/04/2022] [Indexed: 11/04/2022]
Abstract
The coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has caused millions of infections and deaths worldwide since it infected humans almost 3 years ago. Improvements of current assays and the development of new rapid tests or to diagnose SARS-CoV-2 are urgent. Reverse transcription loop-mediated isothermal amplification (RT-LAMP) is a rapid and propitious assay, allowing to detect both colorimetric and/or fluorometric nucleic acid amplifications. This study describes the analytical and clinical evaluation of RT-LAMP assay for detection of SARS-CoV-2, by designing LAMP primers targeting N (nucleocapsid phosphoprotein), RdRp (polyprotein), S (surface glycoprotein), and E (envelope protein) genes. The assay’s performance was compared with the gold standard RT-PCR, yielding 94.6% sensitivity and 92.9% specificity. Among the tested primer sets, the ones for S and N genes had the highest analytical sensitivity, showing results in about 20 min. The colorimetric and fluorometric comparisons revealed that the latter is faster than the former. The limit of detection (LoD) of RT-LAMP reaction in both assays is 50 copies/µl of the reaction mixture. However, the simple eye-observation advantage of the colorimetric assay (with a color change from yellow to red) serves a promising on-site point-of-care testing method anywhere, including, for instance, laboratory and in-house applications.
Collapse
|
8
|
Ning L, Liu M, Gou Y, Yang Y, He B, Huang J. Development and application of ribonucleic acid therapy strategies against COVID-19. Int J Biol Sci 2022; 18:5070-5085. [PMID: 35982905 PMCID: PMC9379410 DOI: 10.7150/ijbs.72706] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Accepted: 07/16/2022] [Indexed: 11/17/2022] Open
Abstract
The Coronavirus disease 2019 (COVID-19) pandemic is caused by the severe acute respiratory syndrome 2 coronavirus (SARS-CoV-2), remaining a global health crisis since its outbreak until now. Advanced biotechnology and research findings have revealed many suitable viral and host targets for a wide range of therapeutic strategies. The emerging ribonucleic acid therapy can modulate gene expression by post-transcriptional gene silencing (PTGS) based on Watson-Crick base pairing. RNA therapies, including antisense oligonucleotides (ASO), ribozymes, RNA interference (RNAi), aptamers, etc., were used to treat SARS-CoV whose genome is similar to SARV-CoV-2, and the past experience also applies for the treatment of COVID-19. Several studies against SARS-CoV-2 based on RNA therapeutic strategy have been reported, and a dozen of relevant preclinical or clinical trials are in process globally. RNA therapy has been a very active and important part of COVID-19 treatment. In this review, we focus on the progress of ribonucleic acid therapeutic strategies development and application, discuss corresponding problems and challenges, and suggest new strategies and solutions.
Collapse
Affiliation(s)
- Lin Ning
- School of Healthcare Technology, Chengdu Neusoft University, Sichuan, China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Sichuan, China
| | - Mujiexin Liu
- Ineye Hospital of Chengdu University of TCM, Sichuan, China
| | - Yushu Gou
- School of Life Science and Technology, University of Electronic Science and Technology of China, Sichuan, China
| | - Yue Yang
- School of Life Science and Technology, University of Electronic Science and Technology of China, Sichuan, China
| | - Bifang He
- Medical College, Guizhou University, Guizhou, China
| | - Jian Huang
- School of Life Science and Technology, University of Electronic Science and Technology of China, Sichuan, China
| |
Collapse
|
9
|
Saberiyan M, Karimi E, Khademi Z, Movahhed P, Safi A, Mehri-Ghahfarrokhi A. SARS-CoV-2: phenotype, genotype, and characterization of different variants. Cell Mol Biol Lett 2022; 27:50. [PMID: 35715738 PMCID: PMC9204680 DOI: 10.1186/s11658-022-00352-6] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2022] [Accepted: 05/31/2022] [Indexed: 12/31/2022] Open
Abstract
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the cause of coronavirus disease 2019 (COVID-19), a major international public health concern. Because of very similar amino acid sequences of the seven domain names, SARS-CoV-2 belongs to the Coronavirinae subfamily of the family Coronaviridae, order Nidovirales, and realm Riboviria, placed in exceptional clusters, but categorized as a SARS-like species. As the RNA virus family with the longest genome, the Coronaviridae genome consists of a single strand of positive RNA (25-32 kb in length). Four major structural proteins of this genome include the spike (S), membrane (M), envelope (E), and the nucleocapsid (N) protein, all of which are encoded within the 3' end of the genome. By engaging with its receptor, angiotensin-converting enzyme 2 (ACE2), SARS-CoV-2 infects host cells. According to the most recent epidemiological data, as the illness spread globally, several genetic variations of SARS-CoV-2 appeared quickly, with the World Health Organization (WHO) naming 11 of them. Among these, seven SARS-CoV-2 subtypes have received the most attention. Alpha (B.1.1.7), Beta (B.1.351), Gamma (P.1), Delta (B.1.617.2), and Omicron (B.1.617.2) are now designated as variations of concern (VOC) (B.1.1.529). Lambda (C.37) and Mu are variations of interest (VOI) (B.1.621). The remaining six are either being monitored or are no longer considered a threat. On the basis of studies done so far, antiviral drugs, antibiotics, glucocorticoids, recombinant intravenous immunoglobulin, plasma therapy, and IFN-α2b have been used to treat patients. Moreover, full vaccination is associated with lower infection and helps prevent transmission, but the risk of infection cannot be eliminated completely in vaccinated people.
Collapse
Affiliation(s)
- Mohammadreza Saberiyan
- Cellular and Molecular Research Center, Basic Health Sciences Institute, Shahrekord University of Medical Sciences, Shahrekord, Iran
| | - Elham Karimi
- Department of Medical Genetics, School of Medicine, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
| | - Zahra Khademi
- Department of Genetics, Faculty of Basic Sciences, Shahrekord University, Shahrekord, Iran
| | - Parvaneh Movahhed
- Department of Medical Laboratory Sciences, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Amir Safi
- Clinical Biochemistry Research Center, Basic Health Sciences Institute, Shahrekord University of Medical Sciences, Shahrekord, Iran
| | - Ameneh Mehri-Ghahfarrokhi
- Clinical Research Development Unit, Hajar Hospital, Shahrekord University of Medical Sciences, Shahrekord, Iran.
| |
Collapse
|
10
|
Abstract
Healthcare is one of the crucial aspects of the Internet of things. Connected machine learning-based systems provide faster healthcare services. Doctors and radiologists can also use these systems for collaboration to provide better help to patients. The recently emerged Coronavirus (COVID-19) is known to have strong infectious ability. Reverse transcription-polymerase chain reaction (RT-PCR) is recognised as being one of the primary diagnostic tools. However, RT-PCR tests might not be accurate. In contrast, doctors can employ artificial intelligence techniques on X-ray and CT scans for analysis. Artificial intelligent methods need a large number of images; however, this might not be possible during a pandemic. In this paper, a novel data-efficient deep network is proposed for the identification of COVID-19 on CT images. This method increases the small number of available CT scans by generating synthetic versions of CT scans using the generative adversarial network (GAN). Then, we estimate the parameters of convolutional and fully connected layers of the deep networks using synthetic and augmented data. The method shows that the GAN-based deep learning model provides higher performance than classic deep learning models for COVID-19 detection. The performance evaluation is performed on COVID19-CT and Mosmed datasets. The best performing models are ResNet-18 and MobileNetV2 on COVID19-CT and Mosmed, respectively. The area under curve values of ResNet-18 and MobileNetV2 are 0.89% and 0.84%, respectively.
Collapse
|