CoChat

Glioblastoma surgery imaging-reporting and data system: validation and performance of the automated segmentation task

Open access

The DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index.

Abstract

For patients with presumed glioblastoma, essential tumor characteristics are determined from preoperative MR images to optimize the treatment strategy. This procedure is time-consuming and subjective, if performed by crude eyeballing or manually. The standardized GSI-RADS aims to provide neurosurgeons with automatic tumor segmentations to extract tumor features rapidly and objectively. In this study, we improved automatic tumor segmentation and compared the agreement with manual raters, describe the technical details of the different components of GSI-RADS, and determined their speed. Two recent neural network architectures were considered for the segmentation task: nnU-Net and AGU-Net. Two preprocessing schemes were introduced to investigate the tradeoff between performance and processing speed. A summarized description of the tumor feature extraction and standardized reporting process is included. The trained architectures for automatic segmentation and the code for computing the standardized report are distributed as open-source and as open-access software. Validation studies were performed on a dataset of 1594 gadolinium-enhanced T1-weighted MRI volumes from 13 hospitals and 293 T1-weighted MRI volumes from the BraTS challenge. The glioblastoma tumor core segmentation reached a Dice score slightly below 90%, a patientwise F1-score close to 99%, and a 95th percentile Hausdorff distance slightly below 4.0 mm on average with either architecture and the heavy preprocessing scheme. A patient MRI volume can be segmented in less than one minute, and a standardized report can be generated in up to five minutes. The proposed GSI-RADS software showed robust performance on a large collection of MRI volumes from various hospitals and generated results within a reasonable runtime.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/cancers13184674

Cites

52 of 52 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Example axial views of T1-weighted MRI volumes used in the study, with manual segmentations outlined in red. One case from each hospital is shown, and the rightmost two cases featured in the last row are from the BraTS challenge dataset.
Figure 1 Example axial views of T1-weighted MRI volumes used in the study, with manual segmentations outlined in red. One case from each hospital is shown, and the rightmost two cases featured in the last row are from the BraTS challenge dataset.CC BY · PubMed Central
Figure 2 Illustration of the different atlases used for feature computation, all expressed in the MNI (Montreal Neurological Institute) space. Cortical structures atlases: MNI, Harvard-Oxford, Schaefer7, and Schaefer17. Subcortical structures atlases: BCB (Brain Connectivity Behaviour).
Figure 2 Illustration of the different atlases used for feature computation, all expressed in the MNI (Montreal Neurological Institute) space. Cortical structures atlases: MNI, Harvard-Oxford, Schaefer7, and Schaefer17. Subcortical structures atlases: BCB (Brain Connectivity Behaviour).CC BY · PubMed Central
Figure 3 Illustration of the proposed GSI-RADS. The GUI (Graphical User Interface) is presented to the left with a standardized report. To the right, the different outputs both in the patient and MNI space are illustrated. In the bottom row, the Schaefer7, Schaefer17, and Harvard-Oxford cortical structures are respectively shown.
Figure 3 Illustration of the proposed GSI-RADS. The GUI (Graphical User Interface) is presented to the left with a standardized report. To the right, the different outputs both in the patient and MNI space are illustrated. In the bottom row, the Schaefer7, Schaefer17, and Harvard-Oxford cortical structures are respectively shown.CC BY · PubMed Central
Figure 4 Segmentation comparison between the manual ground truth (overlaid in red) and the predictions (outlined in green) from the two architectures and with the two different preprocessing schemes. One patient is featured per row, and the overall raw Dice score is reported in white (best viewed digitally and in color).
Figure 4 Segmentation comparison between the manual ground truth (overlaid in red) and the predictions (outlined in green) from the two architectures and with the two different preprocessing schemes. One patient is featured per row, and the overall raw Dice score is reported in white (best viewed digitally and in color).CC BY · PubMed Central
Figure 5 Illustration of the manual segmentation differences between the different raters, one patient per row. Color code: red is the ground truth; blue is the majority voting across all raters; yellow is the majority voting across novice raters; green is the majority voting across expert raters (best viewed digitally and in color).
Figure 5 Illustration of the manual segmentation differences between the different raters, one patient per row. Color code: red is the ground truth; blue is the majority voting across all raters; yellow is the majority voting across novice raters; green is the majority voting across expert raters (best viewed digitally and in color).CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 52 references

Research works printed but not linked: 1

  1. Vezhnevets, 2005, GrowCut: Interactive multi-label ND image segmentation by cellular automata, Proc. Graphicon, Volume 1, 150

Cited by

See all 19

Metadata

Authors
Bouget, D., Eijgelaar, R. S., Pedersen, A., Kommers, I., Ardon, H., Barkhof, F., Bello, L., Berger, M. S., Nibali, M. C., Furtner, J., Fyllingen, E. H., Hervey-Jumper, S., Idema, A. J. S., Kiesel, B., Kloet, A., Mandonnet, E., Müller, D. M. J., Robe, P. A., Rossi, M., Sagberg, L. M., Sciortino, T., Van den Brink, W. A., Wagemakers, M., Widhalm, G., Witte, M. G., Zwinderman, A. H., Reinertsen, I., De Witt Hamer, P. C., & Solheim, O.
Affiliations
  • SINTEF (NO)
  • Amsterdam University Medical Centers (NL)
  • Elisabeth-TweeSteden Ziekenhuis (NL)
  • University of Milan (IT)
  • University of California, San Francisco (US)
  • Medical University of Vienna (AT)
  • Norwegian University of Science and Technology (NO)
  • Department of Neurological Surgery, University of California, San Francisco, CA 94143, USA
  • Noordwest Ziekenhuisgroep (NL)
  • Medisch Centrum Haaglanden (NL)
  • Hôpital Lariboisière (FR)
  • University Medical Center Utrecht (NL)
  • St Olav's University Hospital (NO)
  • Department of Neurosurgery, Isala Hospital Zwolle, 8025 AB Zwolle, The Netherlands
  • University Medical Center Groningen (NL)
  • The Netherlands Cancer Institute (NL)
  • Department of Neurosurgery, Amsterdam University Medical Centers, Vrije Universiteit, 1081 HV Amsterdam, The Netherlands
Corresponding author
Bouget, David
Venue
Cancers
Publisher
MDPI AG
Published
2021-09-17
Volume
13
Issue
18
Pages
4674
ISSN
2072-6694 (ISSN-L)
OpenAlex
W3201398975
Cited by
19
References
52
Citations by year
2026: 4 · 2025: 2 · 2024: 6 · 2023: 5 · 2022: 2
FWCI
1.30
Type
journal article
Language
en
Open access
Locations
  • Cancers (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, other-oa)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Amsterdam UMC (VU Amsterdam) - Institutional Repository (publishedVersion, other-oa)
  • Pure Amsterdam UMC (acceptedVersion, other-oa)
  • Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano) (submittedVersion, cc-by)
  • Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Utrecht University Repository (Utrecht University) (submittedVersion, other-oa)
  • UCL Discovery (University College London) (submittedVersion)
  • NORA - Norwegian Open Research Archives (submittedVersion, cc-by)
  • University of Groningen research database (University of Groningen / Centre for Information Technology) (submittedVersion, cc-by)
Funders
  • Norges Teknisk-Naturvitenskapelige Universitet
  • Rijksdienst voor Ondernemend Nederland
  • Amsterdam University Medical Centers
  • National Institute for Health and Care Research
  • Nederlandse Organisatie voor Wetenschappelijk Onderzoek (2020.027, 10-10400-96-14003)
  • Center for Translational Molecular Medicine
  • University College London Hospitals NHS Foundation Trust
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Brain Tumor Detection and Classification
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
  • Health Sciences › Medicine › Oncology › Glioma Diagnosis and Treatment
Keywords
glioblastoma, automated tumor segmentation, preoperative MRI, nnU-Net, tumor core segmentation, standardized reporting, BraTS, open source software, interobserver agreement

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Glioblastoma surgery imaging-reporting and data system: validation and performance of the automated segmentation task. https://app.cochat.ai/papers/10.3390/cancers13184674
The paper
Bouget, D., Eijgelaar, R. S., Pedersen, A., Kommers, I., Ardon, H., Barkhof, F., Bello, L., Berger, M. S., Nibali, M. C., Furtner, J., Fyllingen, E. H., Hervey-Jumper, S., Idema, A. J. S., Kiesel, B., Kloet, A., Mandonnet, E., Müller, D. M. J., Robe, P. A., Rossi, M., . . . Solheim, O. (2021). Glioblastoma surgery imaging-reporting and data system: validation and performance of the automated segmentation task. Cancers. https://doi.org/10.3390/cancers13184674

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.