To main content

Segmentation of glioblastomas in early post-operative multi-modal MRI with deep neural networks

Abstract

Extent of resection after surgery is one of the main prognostic factors for patients diagnosed with glioblastoma. To achieve this, accurate segmentation and classification of residual tumor from post-operative MR images is essential. The current standard method for estimating it is subject to high inter- and intra-rater variability, and an automated method for segmentation of residual tumor in early post-operative MRI could lead to a more accurate estimation of extent of resection. In this study, two state-of-the-art neural network architectures for pre-operative segmentation were trained for the task. The models were extensively validated on a multicenter dataset with nearly 1000 patients, from 12 hospitals in Europe and the United States. The best performance achieved was a 61% Dice score, and the best classification performance was about 80% balanced accuracy, with a demonstrated ability to generalize across hospitals. In addition, the segmentation performance of the best models was on par with human expert raters. The predicted segmentations can be used to accurately classify the patients into those with residual tumor, and those with gross total resection.
Read the publication

Category

Academic article

Language

English

Author(s)

  • Ragnhild Holden Helland
  • Alexandros Ferles
  • Andre Pedersen
  • Ivar Kommers
  • Hilko Ardon
  • Frederik Barkhof
  • Lorenzo Bello
  • Mitchel S. Berger
  • Tora Dunås
  • Marco Conti Nibali
  • Julia Furtner
  • Shawn Hervey-Jumper
  • Albert J. S. Idema
  • Barbara Kiesel
  • Rishi Nandoe Tewari
  • Emmanuel Mandonnet
  • Domenique M. J. Müller
  • Pierre A. Robe
  • Marco Rossi
  • Lisa Millgård Sagberg
  • Tommaso Sciortino
  • Tom Aalders
  • Michiel Wagemakers
  • Georg Widhalm
  • Marnix G. Witte
  • Aeilko H. Zwinderman
  • Paulina Luiza Majewska
  • Asgeir Store Jakola
  • Ole Skeidsvoll Solheim
  • Philip C. De Witt Hamer
  • Ingerid Reinertsen
  • Roelant S. Eijgelaar
  • David Bouget

Affiliation

  • SINTEF Digital / Health Research
  • Sahlgrenska Academy, University of Gothenburg
  • Sahlgrenska University Hospital
  • Lariboisiere–Saint-Louis Hospitals, DMU Parabol, AP–HP Nord
  • Italy
  • University of Milan
  • IRCCS: Scientific Institute for Research, Hospitalization and Healthcare
  • Netherlands
  • University of Amsterdam
  • Free University Amsterdam
  • Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital
  • University Medical Center Utrecht
  • Vrije Universiteit Amsterdam Medical Center
  • University Medical Center Groningen
  • Haaglanden Medical Center
  • Isala
  • Amsterdam Medical Centre, Amsterdam, the Netherlands
  • University College London
  • Danube University Krems
  • Medical University of Vienna
  • St. Olavs Hospital, Trondheim University Hospital
  • Norwegian University of Science and Technology
  • University of California

Year

2023

Published in

Scientific Reports

Volume

13

Issue

1

View this publication at Norwegian Research Information Repository