EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

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

Alysha Chelliah iD, David A Wood, Liane S Canas iD, Haris Shuaib iD, Stuart Currie iD, Kavi Fatania, Russell Frood iD, Chris Rowland-Hill, Stefanie Thust iD, Stephen J Wastling iD, Sean Tenant, Catherine McBain und 28 weitere

Neuro-Oncology · 2024

DOI: 10.1093/neuonc/noae017 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Neuro-Oncology, 2024. Verfasst von Alysha Chelliah und 39 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK. Hauptthemen laut MEDLINE: Glioblastoma, Magnetic Resonance Imaging, Brain Neoplasms. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovation and Technology Commission, Leeds Hospitals Charity, Novocure.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GlioblastomaMagnetic Resonance ImagingBrain NeoplasmsHumansFemaleMaleMiddle AgedRetrospective StudiesProspective StudiesAgedPrognosisDeep LearningAdultSurvival RateFollow-Up StudiesTemozolomide

Stichwörter der Autor:innen

artificial intelligencedeep learningglioblastomamagnetic resonance imagingsurvival

Substanzen

Temozolomide

Autor:innen und Institutionen

  • School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK.
  • Guy's and St. Thomas' NHS Foundation Trust, London, UK.
  • Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK.
  • Leeds Teaching Hospitals NHS Trust, Leeds, UK.
  • Hull University Teaching Hospitals NHS Trust, England, UK.
  • University College London Hospitals NHS Foundation Trust, London, UK.

ORCID-Profile: Alysha Chelliah, Liane S Canas, Haris Shuaib, Stuart Currie, Russell Frood, Stefanie Thust, Stephen J Wastling, Yue Hui Lau, Christian A Linares, Ahmed Bassiouny, Edward Chandy, Joanne Lewis, Ryan Mathew, Eric Kerfoot, Richard Brown, Sébastien Ourselin, Marc Modat

Förderung

  • Innovation and Technology Commission
  • Leeds Hospitals Charity
  • Novocure
  • Yorkshire's Brain Tumour Charity
  • Medical Research Council
  • Wellcome Trust
  • Cancer Research UK
  • Candlelighters

Zitieren

APA

Chelliah, A., Wood, D. A., Canas, L. S., Shuaib, H., Currie, S., Fatania, K., Frood, R., Rowland-Hill, C., Thust, S., Wastling, S. J., Tenant, S., McBain, C., Foweraker, K., Williams, M., Wang, Q., Roman, A., Dragos, C., MacDonald, M., Lau, Y. H., …, & Booth, T. C. (2024). Glioblastoma and radiotherapy: A multicenter AI study for Survival Predictions from MRI (GRASP study). Neuro-Oncology. https://doi.org/10.1093/neuonc/noae017

Vancouver

Chelliah A, Wood DA, Canas LS, Shuaib H, Currie S, Fatania K, et al. Glioblastoma and radiotherapy: A multicenter AI study for Survival Predictions from MRI (GRASP study). Neuro-Oncology. 2024. doi:10.1093/neuonc/noae017

BibTeX
@article{Chelliah2024,
  author = {Chelliah, Alysha and Wood, David A and Canas, Liane S and Shuaib, Haris and Currie, Stuart and Fatania, Kavi and Frood, Russell and Rowland-Hill, Chris and Thust, Stefanie and Wastling, Stephen J and Tenant, Sean and McBain, Catherine and Foweraker, Karen and Williams, Matthew and Wang, Qiquan and Roman, Andrei and Dragos, Carmen and MacDonald, Mark and Lau, Yue Hui and Linares, Christian A and Bassiouny, Ahmed and Luis, Aysha and Young, Thomas and Brock, Juliet and Chandy, Edward and Beaumont, Erica and Lam, Tai-Chung and Welsh, Liam and Lewis, Joanne and Mathew, Ryan and Kerfoot, Eric and Brown, Richard and Beasley, Daniel and Glendenning, Jennifer and Brazil, Lucy and Swampillai, Angela and Ashkan, Keyoumars and Ourselin, Sébastien and Modat, Marc and Booth, Thomas C},
  title = {Glioblastoma and radiotherapy: A multicenter AI study for Survival Predictions from MRI (GRASP study)},
  journal = {Neuro-Oncology},
  year = {2024},
  doi = {10.1093/neuonc/noae017}
}
Kostenlos starten →