Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessments
Abstract Scapular morphological attributes show promise as prognostic indicators of retear following rotator cuff repair. Current evaluation techniques using single-slice magnetic-resonance imaging (MRI) are, however, prone to error, while more accurate computed tomography (CT)-based three-dimension...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84107-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850118683451457536 |
|---|---|
| author | Hanspeter Hess Alexandra Oswald J. Tomás Rojas Alexandre Lädermann Matthias A. Zumstein Kate Gerber |
| author_facet | Hanspeter Hess Alexandra Oswald J. Tomás Rojas Alexandre Lädermann Matthias A. Zumstein Kate Gerber |
| author_sort | Hanspeter Hess |
| collection | DOAJ |
| description | Abstract Scapular morphological attributes show promise as prognostic indicators of retear following rotator cuff repair. Current evaluation techniques using single-slice magnetic-resonance imaging (MRI) are, however, prone to error, while more accurate computed tomography (CT)-based three-dimensional techniques, are limited by cost and radiation exposure. In this study we propose deep learning-based methods that enable automatic scapular morphological analysis from diagnostic MRI despite the anisotropic resolution and reduced field of view, compared to CT. A deep learning-based segmentation network was trained with paired CT derived scapula segmentations. An algorithm to fuse multi-plane segmentations was developed to generated high-resolution 3D models of the scapula on which morphological landmark- and axes were predicted using a second deep learning network for morphological analysis. Using the proposed methods, the critical shoulder angle, glenoid inclination and version were measured from MRI with accuracies of -1.3 ± 1.7 degrees, 1.3 ± 2.1 degree, and − 1.4 ± 3.4 degrees respectively, compared to CT. Inter-class correlation between MRI and CT derived metrics were substantial for the glenoid version and almost perfect for the other metrics. This study demonstrates how deep learning can overcome reduced resolution, bone border contrast and field of view, to enable 3D scapular morphology analysis on MRI. |
| format | Article |
| id | doaj-art-984d990dccdf498daa59d71047cae6bd |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-984d990dccdf498daa59d71047cae6bd2025-08-20T02:35:49ZengNature PortfolioScientific Reports2045-23222025-01-0115111110.1038/s41598-024-84107-7Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessmentsHanspeter Hess0Alexandra Oswald1J. Tomás Rojas2Alexandre Lädermann3Matthias A. Zumstein4Kate Gerber5Department of Orthopaedic Surgery and Traumatology, Bern University Hospital, Inselspital, University of BernDepartment of Orthopaedic Surgery and Traumatology, Bern University Hospital, Inselspital, University of BernShoulder, Elbow and Orthopaedic Sports Medicine, Orthopaedics SonnenhofDivision of Orthopaedics and Trauma Surgery, Hôpital de La TourShoulder, Elbow and Orthopaedic Sports Medicine, Orthopaedics SonnenhofDepartment of Orthopaedic Surgery and Traumatology, Bern University Hospital, Inselspital, University of BernAbstract Scapular morphological attributes show promise as prognostic indicators of retear following rotator cuff repair. Current evaluation techniques using single-slice magnetic-resonance imaging (MRI) are, however, prone to error, while more accurate computed tomography (CT)-based three-dimensional techniques, are limited by cost and radiation exposure. In this study we propose deep learning-based methods that enable automatic scapular morphological analysis from diagnostic MRI despite the anisotropic resolution and reduced field of view, compared to CT. A deep learning-based segmentation network was trained with paired CT derived scapula segmentations. An algorithm to fuse multi-plane segmentations was developed to generated high-resolution 3D models of the scapula on which morphological landmark- and axes were predicted using a second deep learning network for morphological analysis. Using the proposed methods, the critical shoulder angle, glenoid inclination and version were measured from MRI with accuracies of -1.3 ± 1.7 degrees, 1.3 ± 2.1 degree, and − 1.4 ± 3.4 degrees respectively, compared to CT. Inter-class correlation between MRI and CT derived metrics were substantial for the glenoid version and almost perfect for the other metrics. This study demonstrates how deep learning can overcome reduced resolution, bone border contrast and field of view, to enable 3D scapular morphology analysis on MRI.https://doi.org/10.1038/s41598-024-84107-7Shoulder surgeryRotator cuffMRI ReconstructionArtificial intelligence (AI)PlanificationPredictive model |
| spellingShingle | Hanspeter Hess Alexandra Oswald J. Tomás Rojas Alexandre Lädermann Matthias A. Zumstein Kate Gerber Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessments Scientific Reports Shoulder surgery Rotator cuff MRI Reconstruction Artificial intelligence (AI) Planification Predictive model |
| title | Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessments |
| title_full | Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessments |
| title_fullStr | Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessments |
| title_full_unstemmed | Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessments |
| title_short | Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessments |
| title_sort | deep learning algorithms enable mri based scapular morphology analysis with values comparable to ct based assessments |
| topic | Shoulder surgery Rotator cuff MRI Reconstruction Artificial intelligence (AI) Planification Predictive model |
| url | https://doi.org/10.1038/s41598-024-84107-7 |
| work_keys_str_mv | AT hanspeterhess deeplearningalgorithmsenablemribasedscapularmorphologyanalysiswithvaluescomparabletoctbasedassessments AT alexandraoswald deeplearningalgorithmsenablemribasedscapularmorphologyanalysiswithvaluescomparabletoctbasedassessments AT jtomasrojas deeplearningalgorithmsenablemribasedscapularmorphologyanalysiswithvaluescomparabletoctbasedassessments AT alexandreladermann deeplearningalgorithmsenablemribasedscapularmorphologyanalysiswithvaluescomparabletoctbasedassessments AT matthiasazumstein deeplearningalgorithmsenablemribasedscapularmorphologyanalysiswithvaluescomparabletoctbasedassessments AT kategerber deeplearningalgorithmsenablemribasedscapularmorphologyanalysiswithvaluescomparabletoctbasedassessments |