A deep learning approach for automatic 3D segmentation of hip cartilage and labrum from direct hip MR arthrography
Abstract The objective was to use convolutional neural networks (CNNs) for automatic segmentation of hip cartilage and labrum based on 3D MRI. In this retrospective single-center study, CNNs with a U-Net architecture were used to develop a fully automated segmentation model for hip cartilage and lab...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-86727-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862487467950080 |
|---|---|
| author | Malin Kristin Meier Ramon Andreas Helfenstein Adam Boschung Andreas Nanavati Adrian Ruckli Till D. Lerch Nicolas Gerber Bernd Jung Onur Afacan Moritz Tannast Klaus A. Siebenrock Simon D Steppacher Florian Schmaranzer |
| author_facet | Malin Kristin Meier Ramon Andreas Helfenstein Adam Boschung Andreas Nanavati Adrian Ruckli Till D. Lerch Nicolas Gerber Bernd Jung Onur Afacan Moritz Tannast Klaus A. Siebenrock Simon D Steppacher Florian Schmaranzer |
| author_sort | Malin Kristin Meier |
| collection | DOAJ |
| description | Abstract The objective was to use convolutional neural networks (CNNs) for automatic segmentation of hip cartilage and labrum based on 3D MRI. In this retrospective single-center study, CNNs with a U-Net architecture were used to develop a fully automated segmentation model for hip cartilage and labrum from MRI. Direct hip MR arthrographies (01/2020-10/2021) were selected from 100 symptomatic patients. Institutional routine protocol included a 3D T1 mapping sequence, which was used for manual segmentation of hip cartilage and labrum. 80 hips were used for training and the remaining 20 for testing. Model performance was assessed with six evaluation metrics including Dice similarity coefficient (DSC). In addition, model performance was tested on an external dataset (40 patients) with a 3D T2-weighted sequence from a different institution. Inter-rater agreement of manual segmentation served as benchmark for automatic segmentation performance. 100 patients were included (mean age 30 ± 10 years, 64% female patients). Mean DSC for cartilage was 0.92 ± 0.02 (95% confidence interval [CI] 0.92–0.93) and 0.83 ± 0.04 (0.81–0.85) for labrum and comparable (p = 0.232 and 0.297, respectively) to inter-rater agreement of manual segmentation: DSC cartilage 0.93 ± 0.04 (0.92–0.95); DSC labrum 0.82 ± 0.05 (0.80–0.85). When tested on the external dataset, the DSC was 0.89 ± 0.02 (0.88–0.90) and 0.71 ± 0.04 (0.69–0.73) for cartilage and labrum, respectively.The presented deep learning approach accurately segments hip cartilage and labrum from 3D MRI sequences and can potentially be used in clinical practice to provide rapid and accurate 3D MRI models. |
| format | Article |
| id | doaj-art-7b43ca0881e849428f235bf0e819718d |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-7b43ca0881e849428f235bf0e819718d2025-02-09T12:30:09ZengNature PortfolioScientific Reports2045-23222025-02-0115111110.1038/s41598-025-86727-zA deep learning approach for automatic 3D segmentation of hip cartilage and labrum from direct hip MR arthrographyMalin Kristin Meier0Ramon Andreas Helfenstein1Adam Boschung2Andreas Nanavati3Adrian Ruckli4Till D. Lerch5Nicolas Gerber6Bernd Jung7Onur Afacan8Moritz Tannast9Klaus A. Siebenrock10Simon D Steppacher11Florian Schmaranzer12Department of Orthopedic Surgery, University Hospital, Inselspital Bern, University of BernDepartment of Orthopedic Surgery, University Hospital, Inselspital Bern, University of BernDepartment of Orthopaedic Surgery and Traumatology, Fribourg Cantonal Hospital, University of FribourgDepartment of Orthopedic Surgery, University Hospital, Inselspital Bern, University of BernDepartment of Orthopedic Surgery, University Hospital, Inselspital Bern, University of BernDepartment of Diagnostic, Interventional and Pediatric Radiology, Inselspital, Bern University Hospital, University of BernDepartment of Orthopedic Surgery, University Hospital, Inselspital Bern, University of BernDepartment of Diagnostic, Interventional and Pediatric Radiology, Inselspital, Bern University Hospital, University of BernDepartment of Radiology, Boston Children’s HospitalDepartment of Orthopedic Surgery, University Hospital, Inselspital Bern, University of BernDepartment of Orthopedic Surgery, University Hospital, Inselspital Bern, University of BernDepartment of Orthopedic Surgery, University Hospital, Inselspital Bern, University of BernDepartment of Diagnostic, Interventional and Pediatric Radiology, Inselspital, Bern University Hospital, University of BernAbstract The objective was to use convolutional neural networks (CNNs) for automatic segmentation of hip cartilage and labrum based on 3D MRI. In this retrospective single-center study, CNNs with a U-Net architecture were used to develop a fully automated segmentation model for hip cartilage and labrum from MRI. Direct hip MR arthrographies (01/2020-10/2021) were selected from 100 symptomatic patients. Institutional routine protocol included a 3D T1 mapping sequence, which was used for manual segmentation of hip cartilage and labrum. 80 hips were used for training and the remaining 20 for testing. Model performance was assessed with six evaluation metrics including Dice similarity coefficient (DSC). In addition, model performance was tested on an external dataset (40 patients) with a 3D T2-weighted sequence from a different institution. Inter-rater agreement of manual segmentation served as benchmark for automatic segmentation performance. 100 patients were included (mean age 30 ± 10 years, 64% female patients). Mean DSC for cartilage was 0.92 ± 0.02 (95% confidence interval [CI] 0.92–0.93) and 0.83 ± 0.04 (0.81–0.85) for labrum and comparable (p = 0.232 and 0.297, respectively) to inter-rater agreement of manual segmentation: DSC cartilage 0.93 ± 0.04 (0.92–0.95); DSC labrum 0.82 ± 0.05 (0.80–0.85). When tested on the external dataset, the DSC was 0.89 ± 0.02 (0.88–0.90) and 0.71 ± 0.04 (0.69–0.73) for cartilage and labrum, respectively.The presented deep learning approach accurately segments hip cartilage and labrum from 3D MRI sequences and can potentially be used in clinical practice to provide rapid and accurate 3D MRI models.https://doi.org/10.1038/s41598-025-86727-z |
| spellingShingle | Malin Kristin Meier Ramon Andreas Helfenstein Adam Boschung Andreas Nanavati Adrian Ruckli Till D. Lerch Nicolas Gerber Bernd Jung Onur Afacan Moritz Tannast Klaus A. Siebenrock Simon D Steppacher Florian Schmaranzer A deep learning approach for automatic 3D segmentation of hip cartilage and labrum from direct hip MR arthrography Scientific Reports |
| title | A deep learning approach for automatic 3D segmentation of hip cartilage and labrum from direct hip MR arthrography |
| title_full | A deep learning approach for automatic 3D segmentation of hip cartilage and labrum from direct hip MR arthrography |
| title_fullStr | A deep learning approach for automatic 3D segmentation of hip cartilage and labrum from direct hip MR arthrography |
| title_full_unstemmed | A deep learning approach for automatic 3D segmentation of hip cartilage and labrum from direct hip MR arthrography |
| title_short | A deep learning approach for automatic 3D segmentation of hip cartilage and labrum from direct hip MR arthrography |
| title_sort | deep learning approach for automatic 3d segmentation of hip cartilage and labrum from direct hip mr arthrography |
| url | https://doi.org/10.1038/s41598-025-86727-z |
| work_keys_str_mv | AT malinkristinmeier adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT ramonandreashelfenstein adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT adamboschung adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT andreasnanavati adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT adrianruckli adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT tilldlerch adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT nicolasgerber adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT berndjung adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT onurafacan adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT moritztannast adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT klausasiebenrock adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT simondsteppacher adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT florianschmaranzer adeeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT malinkristinmeier deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT ramonandreashelfenstein deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT adamboschung deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT andreasnanavati deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT adrianruckli deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT tilldlerch deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT nicolasgerber deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT berndjung deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT onurafacan deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT moritztannast deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT klausasiebenrock deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT simondsteppacher deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography AT florianschmaranzer deeplearningapproachforautomatic3dsegmentationofhipcartilageandlabrumfromdirecthipmrarthrography |