VIBESegmentator: Full Body MRI Segmentation for the NAKO and UK Biobank
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909775181119488 |
|---|---|
| author | Graf, Robert Platzek, Paul-Sören Riedel, Evamaria Olga Ramschütz, Constanze Starck, Sophie Möller, Hendrik Kristian Atad, Matan Völzke, Henry Bülow, Robin Schmidt, Carsten Oliver Rüdebusch, Julia Jung, Matthias Reisert, Marco Weiss, Jakob Löffler, Maximilian Bamberg, Fabian Wiestler, Bene Paetzold, Johannes C. Rueckert, Daniel Kirschke, Jan Stefan |
| author_facet | Graf, Robert Platzek, Paul-Sören Riedel, Evamaria Olga Ramschütz, Constanze Starck, Sophie Möller, Hendrik Kristian Atad, Matan Völzke, Henry Bülow, Robin Schmidt, Carsten Oliver Rüdebusch, Julia Jung, Matthias Reisert, Marco Weiss, Jakob Löffler, Maximilian Bamberg, Fabian Wiestler, Bene Paetzold, Johannes C. Rueckert, Daniel Kirschke, Jan Stefan |
| contents | Objectives: To present a publicly available deep learning-based torso segmentation model that provides comprehensive voxel-wise coverage, including delineations that extend to the boundaries of anatomical compartments. Materials and Methods: We extracted preliminary segmentations from TotalSegmentator, spine, and body composition models for Magnetic Resonance Tomography (MR) images, then improved them iteratively and retrained an nnUNet model. Using a random retrospective subset of German National Cohort (NAKO), UK Biobank, internal MR and Computed Tomography (CT) data (Training: 2897 series from 626 subjects, 290 female; mean age 53+-16; 3-fold-cross validation (20% hold-out). Internal testing 36 series from 12 subjects, 6 male; mean age 60+-11), we segmented 71 structures in torso MR and 72 in CT images: 20 organs, 10 muscles, 19 vessels, 16 bones, ribs in CT, intervertebral discs, spinal cord, spinal canal and body composition (subcutaneous fat, unclassified muscles and visceral fat). For external validation, we used existing automatic organ segmentations, independent ground truth segmentations on gradient echo images, and the Amos data. We used non-parametric bootstrapping for confidence intervals and Wilcoxon rank-sum test for computing statistical significance. Results: We achieved an average Dice score of 0.90+-0.06 on our internal gradient echo test set, which included 71 semantic segmentation labels. Our model ties with the best model on Amos with a Dice of 0,81+-0.14, while having a larger field of view and a considerably higher number structures included. Conclusion: Our work presents a publicly available full-torso segmentation model for MRI and CT images that classifies almost all subject voxels to date. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00125 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VIBESegmentator: Full Body MRI Segmentation for the NAKO and UK Biobank Graf, Robert Platzek, Paul-Sören Riedel, Evamaria Olga Ramschütz, Constanze Starck, Sophie Möller, Hendrik Kristian Atad, Matan Völzke, Henry Bülow, Robin Schmidt, Carsten Oliver Rüdebusch, Julia Jung, Matthias Reisert, Marco Weiss, Jakob Löffler, Maximilian Bamberg, Fabian Wiestler, Bene Paetzold, Johannes C. Rueckert, Daniel Kirschke, Jan Stefan Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Objectives: To present a publicly available deep learning-based torso segmentation model that provides comprehensive voxel-wise coverage, including delineations that extend to the boundaries of anatomical compartments. Materials and Methods: We extracted preliminary segmentations from TotalSegmentator, spine, and body composition models for Magnetic Resonance Tomography (MR) images, then improved them iteratively and retrained an nnUNet model. Using a random retrospective subset of German National Cohort (NAKO), UK Biobank, internal MR and Computed Tomography (CT) data (Training: 2897 series from 626 subjects, 290 female; mean age 53+-16; 3-fold-cross validation (20% hold-out). Internal testing 36 series from 12 subjects, 6 male; mean age 60+-11), we segmented 71 structures in torso MR and 72 in CT images: 20 organs, 10 muscles, 19 vessels, 16 bones, ribs in CT, intervertebral discs, spinal cord, spinal canal and body composition (subcutaneous fat, unclassified muscles and visceral fat). For external validation, we used existing automatic organ segmentations, independent ground truth segmentations on gradient echo images, and the Amos data. We used non-parametric bootstrapping for confidence intervals and Wilcoxon rank-sum test for computing statistical significance. Results: We achieved an average Dice score of 0.90+-0.06 on our internal gradient echo test set, which included 71 semantic segmentation labels. Our model ties with the best model on Amos with a Dice of 0,81+-0.14, while having a larger field of view and a considerably higher number structures included. Conclusion: Our work presents a publicly available full-torso segmentation model for MRI and CT images that classifies almost all subject voxels to date. |
| title | VIBESegmentator: Full Body MRI Segmentation for the NAKO and UK Biobank |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2406.00125 |