COVID-19 is a highly communicable respiratory illness caused by the novel coronavirus SARS-CoV-2, which has had a significant impact on global public health and the economy. Detecting COVID-19 patients during a pandemic with limited medical facilities can be challenging, resulting in errors and further complications. Therefore, this study aims to develop deep learning models to facilitate automated diagnosis of COVID-19 from CT scan records of patients. The study also introduced COVID-MAH-CT, a new dataset that contains 4442 CT scan images from 133 COVID-19 patients, as well as 133 CT scan 3D volumes. We proposed and evaluated six different transfer learning models for slide-level analysis that are responsible for detecting COVID-19 in multi-slice spiral CT. Additionally, multi-head attention squeeze and excitation residual (MASERes) neural network, a novel 3D deep model was developed for patient-level analysis, which analyzes all the CT slides of a given patient as a whole and can accurately diagnose COVID-19. The codes and dataset developed in this study are available at https://github.com/alrzsdgh/COVID . The proposed transfer learning models for slide-level analysis were able to detect COVID-19 CT slides with an accuracy of more than 99%, while MASERes was able to detect COVID-19 patients from 3D CT volumes with an accuracy of 100%. These achievements demonstrate that the proposed models in this study can be useful for automatically detecting COVID-19 in both slide-level and patient-level from patients' CT scan records, and can be applied for real-world utilization, particularly in diagnosing COVID-19 cases in areas with limited medical facilities.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10762017 | PMC |
http://dx.doi.org/10.1038/s41598-023-50742-9 | DOI Listing |
Pancreatology
December 2024
Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, MN, USA. Electronic address:
Background: Multiple management guidelines for intraductal papillary mucinous neoplasms (IPMNs) have been published to improve risk stratification and resource utilization. This study aims to evaluate trends in endoscopic ultrasound (EUS) use and agreement between cross-sectional imaging and EUS for specific pancreas cystic lesion (PCL) features.
Methods: This retrospective cohort study included consecutive adults undergoing EUS for suspected IPMN detected with cross-sectional imaging (CT/MRCP) between 2013 and 2015 (Cohort 1) and 2018-2020 (Cohort 2).
J Infect Public Health
December 2024
Ecosystem Change and Population Health Research Group, School of Public Health and Social Work, Queensland University of Technology, Brisbane, Australia. Electronic address:
Background: During the COVID-19 pandemic, seasonal influenza virus circulation was heavily suppressed worldwide. In Australia, since the virus re-emerged in 2022, shifts in seasonal influenza patterns have been observed. Both the 2022 and 2023 seasons started earlier than pre-pandemic norms and were categorised as moderate to severe, highlighting the renewed importance of prevention strategies for seasonal influenza.
View Article and Find Full Text PDFInt J Clin Pharm
December 2024
School of Pharmacy, Applied Sciences and Public Health, Robert Gordon University, Garthdee Road, Aberdeen, AB10 7QB, Scotland, UK.
Background: Paxlovid® (nirmatrelvir and ritonavir) is the only licensed oral antiviral for COVID-19. Ritonavir is a potent inhibitor of cytochrome P450 enzymes causing numerous drug-drug interactions (DDIs).
Aim: To describe the frequency, type, and severity of detected drug related problems (DRPs) associated with Paxlovid®.
Acta Dermatovenerol Alp Pannonica Adriat
December 2024
Center for the Evaluation of Vaccination, Vaccine and Infectious Disease Institute, University of Antwerp, Antwerp, Belgium.
This review assesses Poland's activities in preventing and managing human papillomavirus (HPV)-related diseases, summarizing information from the 2023 HPV Prevention and Control Board meeting. Progress in primary, secondary, and tertiary prevention identifies opportunities to strengthen control of cervical cancer. Poland's national HPV vaccination program, launched in June 2023, initially achieved suboptimal coverage.
View Article and Find Full Text PDFHealth Technol Assess
December 2024
Usher Institute, University of Edinburgh, Edinburgh, UK.
Background: Around one in three pregnant women undergoes induction of labour in the United Kingdom, usually preceded by in-hospital cervical ripening to soften and open the cervix.
Objectives: This study set out to determine whether cervical ripening at home is within an acceptable safety margin of cervical ripening in hospital, is effective, acceptable and cost-effective from both National Health Service and service user perspectives.
Design: The CHOICE study comprised a prospective multicentre observational cohort study using routinely collected data (CHOICE cohort), a process evaluation comprising a survey and nested case studies (qCHOICE) and a cost-effectiveness analysis.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!