Atrophy-Robust Multiclass CNN Segmentation of Brainstem-Related Structures in Neurodegenerative Parkinson Syndromes.
Authors
Affiliations (9)
Affiliations (9)
- Department of Neuroradiology, Medical Center - University of Freiburg, Faculty of Medicine, Breisacher Straße 64, 79106 Freiburg, Baden-Württemberg, Germany (M.M., H.U., A.R.).
- Department of Neurology, Saarland University, Homburg, Saarland, Germany (N.S.); Department of Neurology, Saarland University Medical Center, Homburg, Saarland, Germany (N.S.); Department of Neurology and Clinical Neuroscience, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Baden-Württemberg, Germany (N.S., M.R., H.W.).
- Parkinson-Klinik Ortenau, Wolfach, Baden-Württemberg, Germany (W.H.J.).
- Department of Stereotactic and Functional Neurosurgery, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Baden-Württemberg, Germany (V.A.C., M.R.).
- Medical Physics, Department of Radiology, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Baden-Württemberg, Germany (E.K., M.R.).
- Department of Neurology and Clinical Neuroscience, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Baden-Württemberg, Germany (N.S., M.R., H.W.).
- Department of Stereotactic and Functional Neurosurgery, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Baden-Württemberg, Germany (V.A.C., M.R.); Medical Physics, Department of Radiology, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Baden-Württemberg, Germany (E.K., M.R.).
- Department of Diagnostic and Interventional Radiology, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Baden-Württemberg, Germany (M.F.R.).
- Department of Neuroradiology, Medical Center - University of Freiburg, Faculty of Medicine, Breisacher Straße 64, 79106 Freiburg, Baden-Württemberg, Germany (M.M., H.U., A.R.). Electronic address: [email protected].
Abstract
Neurodegenerative Parkinson syndromes show regionally distinct tissue loss involving several brainstem and midbrain structures. Reliable volumetry is constrained by atlas-based segmentation in atrophy-affected brains. We developed a multiclass convolutional neural network (CNN) for the segmentation of 16 brainstem-related regions on routine magnetic resonance imaging (MRI). In this retrospective single-center study, 200 manually annotated MRI datasets of patients with Parkinson's disease, atypical Parkinson syndromes, and healthy controls were used for model development and validation. A Deep Neural Patchwork model was trained on 150 datasets and evaluated in an independent test cohort of 50 participants against atlas-based segmentation using the Dice coefficient, 95% Hausdorff distance, and average symmetric surface distances (ASSD). In an extended validation cohort of 264 participants, CNN-derived regional volumes were analyzed across Parkinson's disease, progressive supranuclear palsy (PSP), and multiple system atrophy (MSA). CNN segmentation outperformed atlas-based segmentation across accuracy metrics. Overall medians were 0.75 vs 0.33 for Dice, 2.0 vs 5.0 mm for 95% Hausdorff distance, and 0.30 vs 1.02 mm for ASSD. CNN-derived volumetry recapitulated established disease-associated patterns, including predominant mesencephalic, superior cerebellar peduncle, and red nucleus atrophy in PSP and more marked pontine and middle cerebellar peduncle volume loss in MSA. The principal contribution of this study is an atrophy-robust multiclass brainstem segmentation framework. This framework may enable anatomically more faithful extraction of quantitative MRI metrics than atlas-based approaches and may reduce contamination from adjacent CSF spaces, particularly in small atrophy-affected structures.