Evaluation of a nnU-Net type automated clinical volumetric tumor segmentation tool for diffuse low-grade glioma follow-up.

Deep-learning Follow-up Glioma Segmentation

Journal

Journal of neuroradiology = Journal de neuroradiologie
ISSN: 0150-9861
Titre abrégé: J Neuroradiol
Pays: France
ID NLM: 7705086

Informations de publication

Date de publication:
10 Jun 2023
Historique:
received: 12 12 2022
revised: 30 05 2023
accepted: 30 05 2023
medline: 13 6 2023
pubmed: 13 6 2023
entrez: 12 6 2023
Statut: aheadofprint

Résumé

Diffuse low-grade gliomas (DLGG) are characterized by a slow and continuous growth and always evolve towards an aggressive grade. Accurate prediction of the malignant transformation is essential as it requires immediate therapeutic intervention. One of its most precise predictors is the velocity of diameter expansion (VDE). Currently, the VDE is estimated either by linear measurements or by manual delineation of the DLGG on T2 FLAIR acquisitions. However, because of the DLGG's infiltrative nature and its blurred contours, manual measures are challenging and variable, even for experts. Therefore we propose an automated segmentation algorithm using a 2D nnU-Net, to 1) gain time and 2) standardize VDE assessment. The 2D nnU-Net was trained on 318 acquisitions (T2 FLAIR & 3DT1 longitudinal follow-up of 30 patients, including pre- & post-surgery acquisitions, different scanners, vendors, imaging parameters…). Automated vs. manual segmentation performance was evaluated on 167 acquisitions, and its clinical interest was validated by quantifying the amount of manual correction required after automated segmentation of 98 novel acquisitions. Automated segmentation showed a good performance with a mean Dice Similarity Coefficient (DSC) of 0.82±0.13 with manual segmentation and a substantial concordance between VDE calculations. Major manual corrections (i.e., DSC<0.7) were necessary only in 3/98 cases and 81% of the cases had a DSC>0.9. The proposed automated segmentation algorithm can successfully segment DLGG on highly variable MRI data. Although manual corrections are sometimes necessary, it provides a reliable, standardized and time-winning support for VDE extraction to asses DLGG growth.

Sections du résumé

BACKGROUND AND PURPOSE OBJECTIVE
Diffuse low-grade gliomas (DLGG) are characterized by a slow and continuous growth and always evolve towards an aggressive grade. Accurate prediction of the malignant transformation is essential as it requires immediate therapeutic intervention. One of its most precise predictors is the velocity of diameter expansion (VDE). Currently, the VDE is estimated either by linear measurements or by manual delineation of the DLGG on T2 FLAIR acquisitions. However, because of the DLGG's infiltrative nature and its blurred contours, manual measures are challenging and variable, even for experts. Therefore we propose an automated segmentation algorithm using a 2D nnU-Net, to 1) gain time and 2) standardize VDE assessment.
MATERIALS AND METHODS METHODS
The 2D nnU-Net was trained on 318 acquisitions (T2 FLAIR & 3DT1 longitudinal follow-up of 30 patients, including pre- & post-surgery acquisitions, different scanners, vendors, imaging parameters…). Automated vs. manual segmentation performance was evaluated on 167 acquisitions, and its clinical interest was validated by quantifying the amount of manual correction required after automated segmentation of 98 novel acquisitions.
RESULTS RESULTS
Automated segmentation showed a good performance with a mean Dice Similarity Coefficient (DSC) of 0.82±0.13 with manual segmentation and a substantial concordance between VDE calculations. Major manual corrections (i.e., DSC<0.7) were necessary only in 3/98 cases and 81% of the cases had a DSC>0.9.
CONCLUSION CONCLUSIONS
The proposed automated segmentation algorithm can successfully segment DLGG on highly variable MRI data. Although manual corrections are sometimes necessary, it provides a reliable, standardized and time-winning support for VDE extraction to asses DLGG growth.

Identifiants

pubmed: 37308338
pii: S0150-9861(23)00213-4
doi: 10.1016/j.neurad.2023.05.008
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

Copyright © 2023 Elsevier Masson SAS. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of Competing Interest Thomas Troalen is part of Siemens healthcare (France). Bénédicte Maréchal and Till Huelnhagen are part of the Advanced Clinical Imaging Technology group of Siemens Healthcare in Lausanne (Switzerland).

Auteurs

Margaux Verdier (M)

I2FH, Institut d'Imagerie Fonctionnelle Humaine, Department of Neuroradiology, Montpellier University Medical Center, Montpellier, France. Electronic address: verdiermarg@gmail.com.

Jeremy Deverdun (J)

I2FH, Institut d'Imagerie Fonctionnelle Humaine, Department of Neuroradiology, Montpellier University Medical Center, Montpellier, France.

Nicolas Menjot de Champfleur (NM)

I2FH, Institut d'Imagerie Fonctionnelle Humaine, Department of Neuroradiology, Montpellier University Medical Center, Montpellier, France; Department of Neuroradiology, Montpellier University Medical Center, Montpellier, France; Laboratoire Charles Coulomb, University of Montpellier, France.

Hugues Duffau (H)

Department of Neurosurgery, Montpellier University Medical Center, Montpellier, France; Institute for Neuroscience of Montpellier, INSERM U1051, Montpellier University Medical Center, Montpellier, France.

Philippe Lam (P)

Department of Neuroradiology, Montpellier University Medical Center, Montpellier, France.

Thomas Dos Santos (TD)

Department of Neuroradiology, Montpellier University Medical Center, Montpellier, France.

Thomas Troalen (T)

Siemens Healthcare SAS, Saint-Denis, France.

Bénédicte Maréchal (B)

Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland; LTS5, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.

Till Huelnhagen (T)

Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland; LTS5, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.

Emmanuelle Le Bars (EL)

I2FH, Institut d'Imagerie Fonctionnelle Humaine, Department of Neuroradiology, Montpellier University Medical Center, Montpellier, France; Department of Neuroradiology, Montpellier University Medical Center, Montpellier, France.

Classifications MeSH