Lisa Duff1,2, Andrew F Scarsbrook3,4, Sarah L Mackie5,6, Russell Frood3,4, Marc Bailey7,8, Ann W Morgan7,6, Charalampos Tsoumpas7,9,10. 1. Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, 8.49b Worsley Building, Clarendon Way, Leeds, LS2 9JT, UK. mnlmd@leeds.ac.uk. 2. Institute of Medical and Biological Engineering, University of Leeds, Leeds, UK. mnlmd@leeds.ac.uk. 3. Leeds Institute of Medical Research - St James's, University of Leeds, Leeds, UK. 4. Department of Radiology, St. James University Hospital, Leeds, UK. 5. Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds, UK. 6. Leeds Teaching Hospitals NHS Trust, Biomedical Research Centre, NIHR Leeds, Leeds, UK. 7. Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, 8.49b Worsley Building, Clarendon Way, Leeds, LS2 9JT, UK. 8. The Leeds Vascular Institute, Leeds General Infirmary, Leeds, UK. 9. Icahn School of Medicine at Mount Sinai, Biomedical Engineering and Imaging Institute, New York, USA. 10. Department of Nuclear Medicine and Molecular Imaging, University Medical Center of Groningen, University of Groningen, 9700 RB, Groningen, Netherlands.
Abstract
BACKGROUND: The aim of this study was to explore the feasibility of assisted diagnosis of active (peri-)aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images. METHODS: The aorta was manually segmented on FDG PET-CT in 50 patients with aortitis and 25 controls. Radiomic features (RF) (n = 107), including SUV (Standardized Uptake Value) metrics, were extracted from the segmented data and harmonized using the ComBat technique. Individual RFs and groups of RFs (i.e., signatures) were used as input in Machine Learning classifiers. The diagnostic utility of these classifiers was evaluated with area under the receiver operating characteristic curve (AUC) and accuracy using the clinical diagnosis as the ground truth. RESULTS: Several RFs had high accuracy, 84% to 86%, and AUC scores 0.83 to 0.97 when used individually. Radiomic signatures performed similarly, AUC 0.80 to 1.00. CONCLUSION: A methodological framework for a radiomic-based approach to support diagnosis of aortitis was outlined. Selected RFs, individually or in combination, showed similar performance to the current standard of qualitative assessment in terms of AUC for identifying active aortitis. This framework could support development of a clinical decision-making tool for a more objective and standardized assessment of aortitis.
BACKGROUND: The aim of this study was to explore the feasibility of assisted diagnosis of active (peri-)aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images. METHODS: The aorta was manually segmented on FDG PET-CT in 50 patients with aortitis and 25 controls. Radiomic features (RF) (n = 107), including SUV (Standardized Uptake Value) metrics, were extracted from the segmented data and harmonized using the ComBat technique. Individual RFs and groups of RFs (i.e., signatures) were used as input in Machine Learning classifiers. The diagnostic utility of these classifiers was evaluated with area under the receiver operating characteristic curve (AUC) and accuracy using the clinical diagnosis as the ground truth. RESULTS: Several RFs had high accuracy, 84% to 86%, and AUC scores 0.83 to 0.97 when used individually. Radiomic signatures performed similarly, AUC 0.80 to 1.00. CONCLUSION: A methodological framework for a radiomic-based approach to support diagnosis of aortitis was outlined. Selected RFs, individually or in combination, showed similar performance to the current standard of qualitative assessment in terms of AUC for identifying active aortitis. This framework could support development of a clinical decision-making tool for a more objective and standardized assessment of aortitis.
Authors: Vikas Veeranna; Alexander Fisher; Prashant Nagpal; Nina Ghosh; Edward Fisher; Michael Steigner; Mark A Creager; Sharmila Dorbala; Marcelo F Di Carli Journal: J Nucl Cardiol Date: 2015-07-18 Impact factor: 5.952
Authors: Jessica C Wilson; Khaled Sarsour; Neil Collinson; Katie Tuckwell; David Musselman; Micki Klearman; Pavel Napalkov; Susan S Jick; John H Stone; Christoph R Meier Journal: Semin Arthritis Rheum Date: 2016-11-28 Impact factor: 5.532
Authors: Sarah L Mackie; Christian Dejaco; Simone Appenzeller; Dario Camellino; Christina Duftner; Solange Gonzalez-Chiappe; Alfred Mahr; Chetan Mukhtyar; Gary Reynolds; Alexandre Wagner S de Souza; Elisabeth Brouwer; Marwan Bukhari; Frank Buttgereit; Dorothy Byrne; Maria C Cid; Marco Cimmino; Haner Direskeneli; Kate Gilbert; Tanaz A Kermani; Asad Khan; Peter Lanyon; Raashid Luqmani; Christian Mallen; Justin C Mason; Eric L Matteson; Peter A Merkel; Susan Mollan; Lorna Neill; Eoin O' Sullivan; Maria Sandovici; Wolfgang A Schmidt; Richard Watts; Madeline Whitlock; Elaine Yacyshyn; Steven Ytterberg; Bhaskar Dasgupta Journal: Rheumatology (Oxford) Date: 2020-03-01 Impact factor: 7.580
Authors: Sara Monti; Ana F Águeda; Raashid Ahmed Luqmani; Frank Buttgereit; Maria Cid; Christian Dejaco; Alfred Mahr; Cristina Ponte; Carlo Salvarani; Wolfgang Schmidt; Bernhard Hellmich Journal: RMD Open Date: 2019-09-16