Evaluation of the HD-GLIO Deep Learning Algorithm for Brain Tumour Segmentation on Postoperative MRI
Diagnostics · 18.01.2023 · 13 (3) · 363
DOI: 10.3390/diagnostics13030363 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 18.01.2023. Verfasst von Peter Jagd Sørensen und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Centre of Diagnostic Investigation, Copenhagen University Hospital-Rigshospitalet, 2100 Copenhagen, Denmark. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Danish Cancer Society.
Abstract (Originalsprache)
In the context of brain tumour response assessment, deep learning-based three-dimensional (3D) tumour segmentation has shown potential to enter the routine radiological workflow. The purpose of the present study was to perform an external evaluation of a state-of-the-art deep learning 3D brain tumour segmentation algorithm (HD-GLIO) on an independent cohort of consecutive, post-operative patients. For 66 consecutive magnetic resonance imaging examinations, we compared delineations of contrast-enhancing (CE) tumour lesions and non-enhancing T2/FLAIR hyperintense abnormality (NE) lesions by the HD-GLIO algorithm and radiologists using Dice similarity coefficients (Dice). Volume agreement was assessed using concordance correlation coefficients (CCCs) and Bland–Altman plots. The algorithm performed very well regarding the segmentation of NE volumes (median Dice = 0.79) and CE tumour volumes larger than 1.0 cm3 (median Dice = 0.86). If considering all cases with CE tumour lesions, the performance dropped significantly (median Dice = 0.40). Volume agreement was excellent with CCCs of 0.997 (CE tumour volumes) and 0.922 (NE volumes). The findings have implications for the application of the HD-GLIO algorithm in the routine radiological workflow where small contrast-enhancing tumours will constitute a considerable share of the follow-up cases. Our study underlines that independent validations on clinical datasets are key to asserting the robustness of deep learning algorithms.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Centre of Diagnostic Investigation, Copenhagen University Hospital-Rigshospitalet, 2100 Copenhagen, Denmark.
- Department of Clinical Medicine, University of Copenhagen, 2100 Copenhagen, Denmark.
- The DCCC Brain Tumor Center, 2100 Copenhagen, Denmark.
- Department of Clinical Physiology and Nuclear Medicine, Centre of Diagnostic Investigation, Copenhagen University Hospital-Rigshospitalet, 2100 Copenhagen, Denmark.
- Department of Oncology, Centre for Cancer and Organ Diseases, Copenhagen University Hospital-Rigshospitalet, 2100 Copenhagen, Denmark.
ORCID-Profile: Peter Jagd Sørensen, Jonathan Frederik Carlsen, Michael Bachmann Nielsen, Adam Espe Hansen
Förderung
- Danish Cancer Society
Zitieren
APA
Sørensen, P. J., Carlsen, J. F., Larsen, V. A., Andersen, F. L., Ladefoged, C. N., Nielsen, M. B., Poulsen, H. S., & Hansen, A. E. (2023). Evaluation of the HD-GLIO Deep Learning Algorithm for Brain Tumour Segmentation on Postoperative MRI. Diagnostics, 13(3), 363. https://doi.org/10.3390/diagnostics13030363
Vancouver
Sørensen PJ, Carlsen JF, Larsen VA, Andersen FL, Ladefoged CN, Nielsen MB, et al. Evaluation of the HD-GLIO Deep Learning Algorithm for Brain Tumour Segmentation on Postoperative MRI. Diagnostics. 2023;13(3):363. doi:10.3390/diagnostics13030363
BibTeX
@article{Srensen2023,
author = {Sørensen, Peter Jagd and Carlsen, Jonathan Frederik and Larsen, Vibeke Andrée and Andersen, Flemming Littrup and Ladefoged, Claes Nøhr and Nielsen, Michael Bachmann and Poulsen, Hans Skovgaard and Hansen, Adam Espe},
title = {Evaluation of the HD-GLIO Deep Learning Algorithm for Brain Tumour Segmentation on Postoperative MRI},
journal = {Diagnostics},
year = {2023},
volume = {13},
number = {3},
pages = {363},
doi = {10.3390/diagnostics13030363}
}
EUVIMED