SPINEPS—automatic whole spine segmentation of T2-weighted MR images using a two-phase approach to multi-class semantic and instance segmentation
European Radiology · 29.10.2024 · 35 (3) · 1178-1189
DOI: 10.1007/s00330-024-11155-y ↗Kurz gefasst
Fachartikel in der Zeitschrift European Radiology, online erschienen am 29.10.2024. Verfasst von Hendrik Möller und 18 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Technical University of Munich, Munich, Germany. hendrik.m…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Spine, Deep Learning, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: HORIZON EUROPE European Research Council.
Abstract (Originalsprache)
Objectives
Introducing SPINEPS, a deep learning method for semantic and instance segmentation of 14 spinal structures (ten vertebra substructures, intervertebral discs, spinal cord, spinal canal, and sacrum) in whole-body sagittal T2-weighted turbo spin echo images. Material and methods This local ethics committee-approved study utilized a public dataset (train/test 179/39 subjects, 137 female), a German National Cohort (NAKO) subset (train/test 1412/65 subjects, mean age 53, 694 female), and an in-house dataset (test 10 subjects, mean age 70, 5 female). SPINEPS is a semantic segmentation model, followed by a sliding window approach utilizing a second model to create instance masks from the semantic ones. Segmentation evaluation metrics included the Dice score and average symmetrical surface distance (ASSD). Statistical significance was assessed using the Wilcoxon signed-rank test.
Results
On the public dataset, SPINEPS outperformed a nnUNet baseline on every structure and metric (e.g., an average over vertebra instances: dice 0.933 vs 0.911, p < 0.001, ASSD 0.21 vs 0.435, p < 0.001). SPINEPS trained on automated annotations of the NAKO achieves an average global Dice score of 0.918 on the combined NAKO and in-house test split. Adding the training data from the public dataset outperforms this (average instance-wise Dice score over the vertebra substructures 0.803 vs 0.778, average global Dice score 0.931 vs 0.918).
Conclusion
SPINEPS offers segmentation of 14 spinal structures in T2w sagittal images. It provides a semantic mask and an instance mask separating the vertebrae and intervertebral discs. This is the first publicly available algorithm to enable this segmentation. Key Points Question No publicly available automatic approach can yield semantic and instance segmentation masks for the whole spine (including posterior elements) in T2-weighted sagittal TSE images .
Findings
Segmenting semantically first and then instance-wise outperforms a baseline trained directly on instance segmentation. The developed model produces high-resolution MRI segmentations for the whole spine . Clinical relevance This study introduces an automatic approach to whole spine segmentation, including posterior elements, in arbitrary fields of view T2w sagittal MR images, enabling easy biomarker extraction, automatic localization of pathologies and degenerative diseases, and quantifying analyses as downstream research .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Technical University of Munich, Munich, Germany. hendrik.moeller@tum.de.
- Institut Für KI Und Informatik in Der Medizin, Klinikum Rechts Der Isar, Technical University of Munich, Munich, Germany. hendrik.moeller@tum.de.
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Technical University of Munich, Munich, Germany.
- Institut Für KI Und Informatik in Der Medizin, Klinikum Rechts Der Isar, Technical University of Munich, Munich, Germany.
- Department of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology, University Medical Center Rostock, Rostock, Germany.
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland.
Förderung
- HORIZON EUROPE European Research Council
Zitieren
APA
Möller, H., Graf, R., Schmitt, J., Keinert, B., Schön, H., Atad, M., Sekuboyina, A., Streckenbach, F., Kofler, F., Kroencke, T., Bette, S., Willich, S. N., Keil, T., Niendorf, T., Pischon, T., Endemann, B., Menze, B., Rueckert, D., & Kirschke, J. S. (2024). SPINEPS—automatic whole spine segmentation of T2-weighted MR images using a two-phase approach to multi-class semantic and instance segmentation. European Radiology, 35(3), 1178-1189. https://doi.org/10.1007/s00330-024-11155-y
Vancouver
Möller H, Graf R, Schmitt J, Keinert B, Schön H, Atad M, et al. SPINEPS—automatic whole spine segmentation of T2-weighted MR images using a two-phase approach to multi-class semantic and instance segmentation. European Radiology. 2024;35(3):1178-1189. doi:10.1007/s00330-024-11155-y
BibTeX
@article{Mller2024,
author = {Möller, Hendrik and Graf, Robert and Schmitt, Joachim and Keinert, Benjamin and Schön, Hanna and Atad, Matan and Sekuboyina, Anjany and Streckenbach, Felix and Kofler, Florian and Kroencke, Thomas and Bette, Stefanie and Willich, Stefan N and Keil, Thomas and Niendorf, Thoralf and Pischon, Tobias and Endemann, Beate and Menze, Bjoern and Rueckert, Daniel and Kirschke, Jan S},
title = {SPINEPS—automatic whole spine segmentation of T2-weighted MR images using a two-phase approach to multi-class semantic and instance segmentation},
journal = {European Radiology},
year = {2024},
volume = {35},
number = {3},
pages = {1178--1189},
doi = {10.1007/s00330-024-11155-y}
}
EUVIMED