Guodong Zeng1, Florian Schmaranzer2,3, Celia Degonda2, Nicolas Gerber1, Kate Gerber1, Moritz Tannast2,4, Jürgen Burger1, Klaus A Siebenrock2, Guoyan Zheng5, Till D Lerch2,3. 1. Sitem Center for Translational Medicine and Biomedical Entrepreneurship, University of Bern, Switzerland. 2. Department of Orthopedic Surgery, Inselspital, University of Bern, Bern, Switzerland. 3. Department of Diagnostic, Interventional and Paediatric Radiology, University of Bern, Inselspital, Bern, Switzerland. 4. Department of Orthopaedic Surgery and Traumatology, Cantonal Hospital, University of Fribourg, Switzerland. 5. Institute for Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, China.
Abstract
INTRODUCTION: Both Hip Dysplasia(DDH) and Femoro-acetabular-Impingement(FAI) are complex three-dimensional hip pathologies causing hip pain and osteoarthritis in young patients. 3D-MRI-based models were used for radiation-free computer-assisted surgical planning. Automatic segmentation of MRI-based 3D-models are preferred because manual segmentation is time-consuming.To investigate(1) the difference and(2) the correlation for femoral head coverage(FHC) between automatic MR-based and manual CT-based 3D-models and (3) feasibility of preoperative planning in symptomatic patients with hip diseases. METHODS: We performed an IRB-approved comparative, retrospective study of 31 hips(26 symptomatic patients with hip dysplasia or FAI). 3D MRI sequences and CT scans of the hip were acquired. Preoperative MRI included axial-oblique T1 VIBE sequence(0.8 mm3 isovoxel) of the hip joint. Manual segmentation of MRI and CT scans were performed. Automatic segmentation of MRI-based 3D-models was performed using deep learning. RESULTS: (1)The difference between automatic and manual segmentation of MRI-based 3D hip joint models was below 1 mm(proximal femur 0.2 ± 0.1 mm and acetabulum 0.3 ± 0.5 mm). Dice coefficients of the proximal femur and the acetabulum were 98 % and 97 %, respectively. (2)The correlation for total FHC was excellent and significant(r = 0.975, p < 0.001) between automatic MRI-based and manual CT-based 3D-models. Correlation for total FHC (r = 0.979, p < 0.001) between automatic and manual MR-based 3D models was excellent.(3)Preoperative planning and simulation of periacetabular osteotomy was feasible in all patients(100 %) with hip dysplasia or acetabular retroversion. CONCLUSIONS: Automatic segmentation of MRI-based 3D-models using deep learning is as accurate as CT-based 3D-models for patients with hip diseases of childbearing age. This allows radiation-free and patient-specific preoperative simulation and surgical planning of periacetabular osteotomy for patients with DDH.
INTRODUCTION: Both Hip Dysplasia(DDH) and Femoro-acetabular-Impingement(FAI) are complex three-dimensional hip pathologies causing hip pain and osteoarthritis in young patients. 3D-MRI-based models were used for radiation-free computer-assisted surgical planning. Automatic segmentation of MRI-based 3D-models are preferred because manual segmentation is time-consuming.To investigate(1) the difference and(2) the correlation for femoral head coverage(FHC) between automatic MR-based and manual CT-based 3D-models and (3) feasibility of preoperative planning in symptomatic patients with hip diseases. METHODS: We performed an IRB-approved comparative, retrospective study of 31 hips(26 symptomatic patients with hip dysplasia or FAI). 3D MRI sequences and CT scans of the hip were acquired. Preoperative MRI included axial-oblique T1 VIBE sequence(0.8 mm3 isovoxel) of the hip joint. Manual segmentation of MRI and CT scans were performed. Automatic segmentation of MRI-based 3D-models was performed using deep learning. RESULTS: (1)The difference between automatic and manual segmentation of MRI-based 3D hip joint models was below 1 mm(proximal femur 0.2 ± 0.1 mm and acetabulum 0.3 ± 0.5 mm). Dice coefficients of the proximal femur and the acetabulum were 98 % and 97 %, respectively. (2)The correlation for total FHC was excellent and significant(r = 0.975, p < 0.001) between automatic MRI-based and manual CT-based 3D-models. Correlation for total FHC (r = 0.979, p < 0.001) between automatic and manual MR-based 3D models was excellent.(3)Preoperative planning and simulation of periacetabular osteotomy was feasible in all patients(100 %) with hip dysplasia or acetabular retroversion. CONCLUSIONS: Automatic segmentation of MRI-based 3D-models using deep learning is as accurate as CT-based 3D-models for patients with hip diseases of childbearing age. This allows radiation-free and patient-specific preoperative simulation and surgical planning of periacetabular osteotomy for patients with DDH.
Keywords:
ASD, Average Surface Distance; Automatic segmentation; DDH; DDH, developmental dysplasia of the hip; DOC, Dice Overlap Coefficients; Deep learning; FAI, Femoroacetabular Impingement; FHC, femoral head center; GPU, Graphics processing unit; Hip dysplasia; Hip joint; MRI; Machine learning; Magnetic resonance imaging; ROM, range of motion
Authors: Markus S Hanke; Simon D Steppacher; Helen Anwander; Stefan Werlen; Klaus A Siebenrock; Moritz Tannast Journal: Clin Orthop Relat Res Date: 2017-04 Impact factor: 4.176
Authors: Jan Neumann; Alan L Zhang; Benedikt J Schwaiger; Michael A Samaan; Richard Souza; Sarah C Foreman; Gabby B Joseph; Trevor Grace; Sharmila Majumdar; Thomas M Link Journal: Eur Radiol Date: 2018-07-09 Impact factor: 5.315
Authors: Till D Lerch; Inga A S Todorski; Simon D Steppacher; Florian Schmaranzer; Stefan F Werlen; Klaus A Siebenrock; Moritz Tannast Journal: Am J Sports Med Date: 2017-09-22 Impact factor: 6.202
Authors: Lieve Morbée; Min Chen; Thomas Van Den Berghe; Eva Schiettecatte; Robert Gosselin; Nele Herregods; Lennart B O Jans Journal: Eur Radiol Date: 2022-01-23 Impact factor: 5.315
Authors: Till D Lerch; Malin K Meier; Adam Boschung; Simon D Steppacher; Klaus A Siebenrock; Moritz Tannast; Florian Schmaranzer Journal: Eur J Radiol Open Date: 2022-02-25
Authors: Nastassja Pamela Ewertowski; Christoph Schleich; Daniel Benjamin Abrar; Harish S Hosalkar; Bernd Bittersohl Journal: J Orthop Surg Res Date: 2022-07-30 Impact factor: 2.677
Authors: Till D Lerch; Tiziano Antioco; Malin K Meier; Adam Boschung; Markus S Hanke; Moritz Tannast; Klaus A Siebenrock; Florian Schmaranzer; Simon D Steppacher Journal: J Hip Preserv Surg Date: 2022-04-21
Authors: Stanislav Y Shilov; Yulia A Rozhkova; Lubov N Markova; Mikhail A Tashkinov; Ilya V Vindokurov; Vadim V Silberschmidt Journal: Polymers (Basel) Date: 2022-09-22 Impact factor: 4.967
Authors: Mateusz C Florkow; Koen Willemsen; Vasco V Mascarenhas; Edwin H G Oei; Marijn van Stralen; Peter R Seevinck Journal: J Magn Reson Imaging Date: 2022-01-19 Impact factor: 5.119