Glioblastoma and radiotherapy: A multicenter AI study for Survival Predictions from MRI (GRASP study).

Autor:	Chelliah A; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK., Wood DA; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK., Canas LS; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK., Shuaib H; Guy's and St. Thomas' NHS Foundation Trust, London, UK.; Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK., Currie S; Leeds Teaching Hospitals NHS Trust, Leeds, UK., Fatania K; Leeds Teaching Hospitals NHS Trust, Leeds, UK., Frood R; Leeds Teaching Hospitals NHS Trust, Leeds, UK., Rowland-Hill C; Hull University Teaching Hospitals NHS Trust, England, UK., Thust S; University College London Hospitals NHS Foundation Trust, London, UK.; Institute of Neurology, University College London, London, UK.; Nottingham University Hospitals NHS Trust, Nottingham, UK.; Precision Imaging Beacon, School of Medicine, University of Nottingham, Nottingham, UK., Wastling SJ; University College London Hospitals NHS Foundation Trust, London, UK.; Institute of Neurology, University College London, London, UK., Tenant S; The Christie NHS Foundation Trust, Withington, Manchester, UK., McBain C; The Christie NHS Foundation Trust, Withington, Manchester, UK., Foweraker K; Nottingham University Hospitals NHS Trust, Nottingham, UK., Williams M; Radiotherapy Department, Imperial College Healthcare NHS Trust, London, UK.; Institute for Global Health Improvement, Imperial College London, London, UK., Wang Q; Radiotherapy Department, Imperial College Healthcare NHS Trust, London, UK.; Institute for Global Health Improvement, Imperial College London, London, UK., Roman A; Guy's and St. Thomas' NHS Foundation Trust, London, UK.; Oncology Institute Prof. Dr. Ion Chiricuta, Cluj-Napoca, Romania., Dragos C; Buckinghamshire Healthcare NHS Trust, Amersham, UK., MacDonald M; Guy's and St. Thomas' NHS Foundation Trust, London, UK., Lau YH; King's College Hospital NHS Foundation Trust, London, UK., Linares CA; Guy's and St. Thomas' NHS Foundation Trust, London, UK., Bassiouny A; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK.; Department of Radiology, Mansoura University, Mansoura, Egypt., Luis A; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK.; King's College Hospital NHS Foundation Trust, London, UK., Young T; Guy's and St. Thomas' NHS Foundation Trust, London, UK., Brock J; Brighton and Sussex University Hospitals NHS Trust, England, UK., Chandy E; Brighton and Sussex University Hospitals NHS Trust, England, UK., Beaumont E; Lancashire Teaching Hospitals NHS Foundation Trust, England, UK., Lam TC; Lancashire Teaching Hospitals NHS Foundation Trust, England, UK., Welsh L; The Royal Marsden NHS Foundation Trust, London, UK., Lewis J; Newcastle upon Tyne Hospitals NHS Foundation Trust, England, UK., Mathew R; Leeds Teaching Hospitals NHS Trust, Leeds, UK.; School of Medicine, University of Leeds, Leeds, UK., Kerfoot E; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK., Brown R; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK., Beasley D; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK.; Guy's and St. Thomas' NHS Foundation Trust, London, UK., Glendenning J; Maidstone and Tunbridge Wells NHS Trust, Kent, UK., Brazil L; Guy's and St. Thomas' NHS Foundation Trust, London, UK., Swampillai A; Guy's and St. Thomas' NHS Foundation Trust, London, UK., Ashkan K; Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK.; King's College Hospital NHS Foundation Trust, London, UK., Ourselin S; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK., Modat M; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK., Booth TC; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK.; King's College Hospital NHS Foundation Trust, London, UK.
Jazyk:	angličtina
Zdroj:	Neuro-oncology [Neuro Oncol] 2024 Jun 03; Vol. 26 (6), pp. 1138-1151.
DOI:	10.1093/neuonc/noae017
Abstrakt:	Background: The aim was to predict survival of glioblastoma at 8 months after radiotherapy (a period allowing for completing a typical course of adjuvant temozolomide), by applying deep learning to the first brain MRI after radiotherapy completion. Methods: Retrospective and prospective data were collected from 206 consecutive glioblastoma, isocitrate dehydrogenase -wildtype patients diagnosed between March 2014 and February 2022 across 11 UK centers. Models were trained on 158 retrospective patients from 3 centers. Holdout test sets were retrospective (n = 19; internal validation), and prospective (n = 29; external validation from 8 distinct centers). Neural network branches for T2-weighted and contrast-enhanced T1-weighted inputs were concatenated to predict survival. A nonimaging branch (demographics/MGMT/treatment data) was also combined with the imaging model. We investigated the influence of individual MR sequences; nonimaging features; and weighted dense blocks pretrained for abnormality detection. Results: The imaging model outperformed the nonimaging model in all test sets (area under the receiver-operating characteristic curve, AUC P = .038) and performed similarly to a combined imaging/nonimaging model (P > .05). Imaging, nonimaging, and combined models applied to amalgamated test sets gave AUCs of 0.93, 0.79, and 0.91. Initializing the imaging model with pretrained weights from 10 000s of brain MRIs improved performance considerably (amalgamated test sets without pretraining 0.64; P = .003). Conclusions: A deep learning model using MRI images after radiotherapy reliably and accurately determined survival of glioblastoma. The model serves as a prognostic biomarker identifying patients who will not survive beyond a typical course of adjuvant temozolomide, thereby stratifying patients into those who might require early second-line or clinical trial treatment. (© The Author(s) 2024. Published by Oxford University Press on behalf of the Society for Neuro-Oncology.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu