Dominic Cushnan1, Oscar Bennett2, Rosalind Berka2, Ottavia Bertolli2, Ashwin Chopra2, Samie Dorgham2, Alberto Favaro2, Tara Ganepola2, Mark Halling-Brown3, Gergely Imreh2, Joseph Jacob4, Emily Jefferson5,6, François Lemarchand1, Daniel Schofield1, Jeremy C Wyatt7,8. 1. AI Lab, NHSX, Skipton House, 80 London Road, London SE1 6LH, UK. 2. Faculty, 54 Welbeck Street, London W1G 9XS, UK. 3. Scientific Computing, Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, UK. 4. UCL Respiratory, 1st Floor, Rayne Institute, University College London, London WC1E 6JF, UK. 5. Health Data Research UK, Gibbs Building, 215 Euston Road, London NW1 2BE, UK. 6. Health Informatics Centre (HIC), School of Medicine, University of Dundee, DD1 4HN, Dundee, UK. 7. Emeritus Professor of Digital Healthcare, University of Southampton, Southampton SO17 1BJ, UK. 8. NHSX, Skipton House, 80 London Road, London SE1 6LH, UK.
Abstract
BACKGROUND: The National COVID-19 Chest Imaging Database (NCCID) is a centralized database containing mainly chest X-rays and computed tomography scans from patients across the UK. The objective of the initiative is to support a better understanding of the coronavirus SARS-CoV-2 disease (COVID-19) and the development of machine learning technologies that will improve care for patients hospitalized with a severe COVID-19 infection. This article introduces the training dataset, including a snapshot analysis covering the completeness of clinical data, and availability of image data for the various use-cases (diagnosis, prognosis, longitudinal risk). An additional cohort analysis measures how well the NCCID represents the wider COVID-19-affected UK population in terms of geographic, demographic, and temporal coverage. FINDINGS: The NCCID offers high-quality DICOM images acquired across a variety of imaging machinery; multiple time points including historical images are available for a subset of patients. This volume and variety make the database well suited to development of diagnostic/prognostic models for COVID-associated respiratory conditions. Historical images and clinical data may aid long-term risk stratification, particularly as availability of comorbidity data increases through linkage to other resources. The cohort analysis revealed good alignment to general UK COVID-19 statistics for some categories, e.g., sex, whilst identifying areas for improvements to data collection methods, particularly geographic coverage. CONCLUSION: The NCCID is a growing resource that provides researchers with a large, high-quality database that can be leveraged both to support the response to the COVID-19 pandemic and as a test bed for building clinically viable medical imaging models.
BACKGROUND: The National COVID-19 Chest Imaging Database (NCCID) is a centralized database containing mainly chest X-rays and computed tomography scans from patients across the UK. The objective of the initiative is to support a better understanding of the coronavirus SARS-CoV-2 disease (COVID-19) and the development of machine learning technologies that will improve care for patients hospitalized with a severe COVID-19 infection. This article introduces the training dataset, including a snapshot analysis covering the completeness of clinical data, and availability of image data for the various use-cases (diagnosis, prognosis, longitudinal risk). An additional cohort analysis measures how well the NCCID represents the wider COVID-19-affected UK population in terms of geographic, demographic, and temporal coverage. FINDINGS: The NCCID offers high-quality DICOM images acquired across a variety of imaging machinery; multiple time points including historical images are available for a subset of patients. This volume and variety make the database well suited to development of diagnostic/prognostic models for COVID-associated respiratory conditions. Historical images and clinical data may aid long-term risk stratification, particularly as availability of comorbidity data increases through linkage to other resources. The cohort analysis revealed good alignment to general UK COVID-19 statistics for some categories, e.g., sex, whilst identifying areas for improvements to data collection methods, particularly geographic coverage. CONCLUSION: The NCCID is a growing resource that provides researchers with a large, high-quality database that can be leveraged both to support the response to the COVID-19 pandemic and as a test bed for building clinically viable medical imaging models.
Authors: Emily B Tsai; Scott Simpson; Matthew P Lungren; Michelle Hershman; Leonid Roshkovan; Errol Colak; Bradley J Erickson; George Shih; Anouk Stein; Jayashree Kalpathy-Cramer; Jody Shen; Mona Hafez; Susan John; Prabhakar Rajiah; Brian P Pogatchnik; John Mongan; Emre Altinmakas; Erik R Ranschaert; Felipe C Kitamura; Laurens Topff; Linda Moy; Jeffrey P Kanne; Carol C Wu Journal: Radiology Date: 2021-01-05 Impact factor: 11.105
Authors: Jeffrey P Kanne; Harrison Bai; Adam Bernheim; Michael Chung; Linda B Haramati; David F Kallmes; Brent P Little; Geoffrey D Rubin; Nicola Sverzellati Journal: Radiology Date: 2021-02-09 Impact factor: 11.105
Authors: Shirley Sze; Daniel Pan; Clareece R Nevill; Laura J Gray; Christopher A Martin; Joshua Nazareth; Jatinder S Minhas; Pip Divall; Kamlesh Khunti; Keith R Abrams; Laura B Nellums; Manish Pareek Journal: EClinicalMedicine Date: 2020-11-12
Authors: Elizabeth Sapey; Suzy Gallier; Chris Mainey; Peter Nightingale; David McNulty; Hannah Crothers; Felicity Evison; Katharine Reeves; Domenico Pagano; Alastair K Denniston; Krishnarajah Nirantharakumar; Peter Diggle; Simon Ball Journal: BMJ Open Respir Res Date: 2020-09