Machine learning in radiology: the new frontier in interstitial lung diseases.

Autor:	Barnes H; Department of Respiratory Medicine, Alfred Health, Melbourne, VIC, Australia; Central Clinical School, Monash University, Melbourne, VIC, Australia; Centre for Occupational and Environmental Health, Monash University, Melbourne, VIC, Australia. Electronic address: hayley.barnes@monash.edu., Humphries SM; Department of Radiology, National Jewish Health, Denver, CO, USA., George PM; Interstitial Lung Disease Unit, Royal Brompton and Harefield Hospitals, London, UK; National Heart and Lung Institute, Imperial College London, London, UK., Assayag D; Department of Medicine, McGill University, Montreal, QC, Canada., Glaspole I; Department of Respiratory Medicine, Alfred Health, Melbourne, VIC, Australia; Central Clinical School, Monash University, Melbourne, VIC, Australia., Mackintosh JA; Department of Thoracic Medicine, The Prince Charles Hospital, Brisbane, QLD, Australia., Corte TJ; Department of Respiratory Medicine, Royal Prince Alfred Hospital, Sydney, NSW, Australia; Central Clinical School, University of Sydney, Sydney, NSW, Australia., Glassberg M; Division of Pulmonary, Critical Care and Sleep Medicine, University of Arizona College of Medicine Phoenix, Phoenix, AR, USA., Johannson KA; Department of Medicine, University of Calgary, Calgary, AB, Canada., Calandriello L; Department of Diagnostic Imaging, Oncological Radiotherapy and Haematology, Fondazione Policlinico Universitario A Gemelli, IRCCS, Rome, Italy., Felder F; National Heart and Lung Institute, Imperial College London, London, UK., Wells A; Interstitial Lung Disease Unit, Royal Brompton and Harefield Hospitals, London, UK; National Heart and Lung Institute, Imperial College London, London, UK., Walsh S; National Heart and Lung Institute, Imperial College London, London, UK.
Jazyk:	angličtina
Zdroj:	The Lancet. Digital health [Lancet Digit Health] 2023 Jan; Vol. 5 (1), pp. e41-e50. Date of Electronic Publication: 2022 Dec 12.
DOI:	10.1016/S2589-7500(22)00230-8
Abstrakt:	Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes. Competing Interests: Declaration of interests SMH reports grants from Boehringer Ingelheim and NHLBI; service contracts from Calyx outside the present work; the US patent 10,706,533 Systems and Methods for Automatic Detection and Quantification of Pathology Using Dynamic Feature Classification (assigned to National Jewish Health and not licensed); grants and consulting fees from Veracyte; consulting fees from Lyra Therapeutics and IMIDEX; and payment or honorarium for attending the 2021 World Association of Sarcoidosis and Other Granulomatous Disease Conference. PMG reports consulting fees from Boehringer Ingelheim; payment or honoraria from Boehringer Ingelheim, Roche Pharmaceuticals, Teva, Cipla, and AstraZeneca; support for attending meetings or travel from Brainomix; and stock options in Brainomix. DA reports consulting fees and speaker fees from Boehringer Ingelheim and Roche; and grants or contracts from Boehringer Ingelheim and Fonds de Recherche Québec–Santé. TJC reports grants or contracts from Boehringer Ingelheim, Roche, Biogen, and Three Lakes Foundation; consulting fees from, and participation on a Data Safety Monitoring Board or Advisory Board for, Boehringer Ingelheim, Roche and Bristol Myers Squibb; payment or honoraria from Boehringer Ingelheim; and is the cochair of Australian ILD Registry. KAJ reports grants or contracts from the University of Calgary Cumming School of Medicine, Three Lakes Foundation, and the Chest Foundation; consulting fees from Boehringer Ingelheim, Roche, Pliant Therapeutics, Three Lakes Foundation, and Thyron; payment or honoraria from Boehringer Ingelheim and Roche; and participation on a Data Safety Monitoring Board or Advisory Board for the PFOX trial. LC reports payments or honoraria from Boehringer Ingelheim, and participation on a data safety monitoring board or advisory board for Boehringer Ingelheim. AW reports personal fees from Boehringer Ingelheim, Roche, and Veracyte outside the submitted work; payment or honoraria from Roche and Boehringer Ingelheim; and support for attending meetings or travel from Boehringer Ingelheim (or both). SW reports grants from National Institute for Health Research Clinician Scientist Award CS-2018-18-ST2-004; consulting fees and payment or honoraria from Boehringer Ingelheim and Roche; a leadership or fiduciary role on NHS England AI Award Advisory Panel; and is the Radiology Lead for the Open Source Imaging Consortium. IG reports consulting fees from Ad Alta, Amplia, Accendatech, and Lassen; participation on a data safety monitoring board or advisory board for Boehringer Ingelheim; and is the cochair of Australian ILD Registry. HB, JAM, MG, FF report no competing interests. (Copyright © 2023 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu