Extended Technical and Clinical Validation of Deep Learning-Based Brainstem Segmentation for Application in Neurodegenerative Diseases.

Journal: Human brain mapping
PMID: 39936343

Abstract

Disorders of the central nervous system, including neurodegenerative diseases, frequently affect the brainstem and can present with focal atrophy. This study aimed to (1) optimize deep learning-based brainstem segmentation for a wide range of pathologies and T1-weighted image acquisition parameters, (2) conduct a systematic technical and clinical validation, (3) improve segmentation quality in the presence of brainstem lesions, and (4) make an optimized brainstem segmentation tool available for public use. An intentionally heterogeneous ground truth dataset (n = 257) was employed in the training of deep learning models based on multi-dimensional gated recurrent units (MD-GRU) or the nnU-Net method. Segmentation performance was evaluated against ground truth labels. FreeSurfer was used for benchmarking in subsequent validation. Technical validation, including scan-rescan repeatability (n = 46) and inter-scanner reproducibility (n = 20, 3 different scanners) in unseen data, was conducted in patients with cerebral small vessel disease. Clinical validation in unseen data was performed in 1-year follow-up data of 16 patients with multiple system atrophy, evaluating the annual percentage volume change. Two lesion filling algorithms were investigated to improve segmentation performance in 23 patients with multiple sclerosis. The MD-GRU and nnU-Net models demonstrated very good segmentation performance (median Dice coefficients ≥ 0.95 each) and outperformed a previously published model trained on a narrower dataset. Scan-rescan repeatability and inter-scanner reproducibility yielded similar Bland-Altman derived limits of agreement for longitudinal FreeSurfer (total brainstem volume repeatability/reproducibility 0.68/1.85), MD-GRU (0.72/1.46), and nnU-Net (0.48/1.52). All methods showed comparable performance in the detection of atrophy in the total brainstem (atrophy detected in 100% of patients) and its substructures. In patients with multiple sclerosis, lesion filling further improved the accuracy of brainstem segmentation. We enhanced and systematically validated two fully automated deep learning brainstem segmentation methods and released them publicly. This enables a broader evaluation of brainstem volume as a candidate biomarker for neurodegeneration.

Authors

  • Benno Gesierich
    Institute for Stroke and Dementia Research (ISD), University Hospital, Ludwig Maximilian University of Munich (LMU), 81377 Munich, Germany.
  • Laura Sander
    Neurologic Clinic and Policlinic, Departments of Neurology and Clinical Research, University Hospital Basel and University of Basel, Basel, Switzerland.
  • Lukas Pirpamer
    Department of Neurology, Medical University of Graz, Graz, Austria.
  • Dominik S Meier
    Medical Image Analysis Center (MIAC), Basel, Switzerland.
  • Esther Ruberte
    Medical Image Analysis Center (MIAC), Basel, Switzerland.
  • Michael Amann
    Medical Image Analysis Center (MIAC AG), Mittlere Str. 83, CH-4031, Basel, Switzerland.
  • Tim Sinnecker
    Medical Image Analysis Center (MIAC), Basel, Switzerland.
  • Antal Huck
    Center for Medical Image Analysis & Navigation (CIAN), Department of Biomedical Engineering, University of Basel, Allschwil, Switzerland.
  • Frank-Erik de Leeuw
    Department of Neurology, Research Institute for Medical Innovation, Radboud University Medical Center, Donders Institute for Brain, Cognition & Behavior, Center for Medical Neuroscience, Nijmegen, The Netherlands.
  • Pauline Maillard
    Department of Neurology, University of California Davis, Davis, CA 95816, USA.
  • Sue Moy
    Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts, USA.
  • Karl G Helmer
    Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA.
  • Johannes Levin
    Munich Cluster for Systems Neurology, Munich, Germany.
  • Günter U Höglinger
    Department of Neurology, University Hospital Gießen and Marburg, Marburg, Germany.
  • Michael Kühne
    University Hospital Basel, Basel, Switzerland.
  • Leo H Bonati
    Neurologic Clinic and Policlinic, Departments of Neurology and Clinical Research, University Hospital Basel and University of Basel, Basel, Switzerland.
  • Jens Kuhle
    Neurologic Clinic and Policlinic, Multiple Sclerosis (MS) Center and Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), Departments of Clinical Research and Biomedicine, University Hospital Basel, University of Basel, Basel, Switzerland.
  • Philippe Cattin
    Center for Medical Image Analysis and Navigation, University of Basel, Gewerbestrasse 14, 4123, Allschwil, Switzerland.
  • Cristina Granziera
    Translational Imaging in Neurology Basel, Department of Medicine and Biomedical Engineering, University Hospital Basel and University of Basel, Basel, Switzerland; Neurologic Clinic and Policlinic, Departments of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland.
  • Regina Schlaeger
    Neurologic Clinic and Policlinic, Departments of Neurology and Clinical Research, University Hospital Basel and University of Basel, Basel, Switzerland.
  • Marco Duering
    Institute for Stroke and Dementia Research, Klinikum der Universität München, Ludwig-Maximilians-Universität LMU, Munich, Germany.

Keywords

External Resources

Popular Topics
Recent Journals