MRI-based 3D models of the hip joint enables radiation-free computer-assisted planning of periacetabular osteotomy for treatment of hip dysplasia using deep learning for automatic segmentation

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.

[1]  Fang Chen,et al.  Three-Dimensional Feature-Enhanced Network for Automatic Femur Segmentation , 2019, IEEE Journal of Biomedical and Health Informatics.

[2]  Comparison Between 3-Dimensional Multiple-Echo Recombined Gradient Echo Magnetic Resonance Imaging and Arthroscopic Findings for the Evaluation of Acetabular Labrum Tear. , 2019, Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association.

[3]  S. Glyn-Jones,et al.  Osseous impingement occurs early in flexion in cam‐type femoroacetabular impingement: A 4D CT MODEL , 2017, The bone & joint journal.

[4]  L. Maini,et al.  Application of three dimensional printing in surgery for cam type of femoro-acetabular impingement. , 2018, Journal of clinical orthopaedics and trauma.

[5]  Guoyan Zheng,et al.  Hip2Norm: An object-oriented cross-platform program for 3D analysis of hip joint morphology using 2D pelvic radiographs , 2007, Comput. Methods Programs Biomed..

[6]  Marc Puls,et al.  The Equidistant Method – a novel hip joint simulation algorithm for detection of femoroacetabular impingement , 2010, Computer aided surgery : official journal of the International Society for Computer Aided Surgery.

[7]  M. Tannast,et al.  What MRI Findings Predict Failure 10 Years After Surgery for Femoroacetabular Impingement? , 2017, Clinical orthopaedics and related research.

[8]  Patient-Specific 3-Dimensional Modeling and Its Use for Preoperative Counseling of Patients Undergoing Hip Arthroscopy , 2018, Orthopaedic journal of sports medicine.

[9]  Michael P Reiman,et al.  The Warwick Agreement on femoroacetabular impingement syndrome (FAI syndrome): an international consensus statement , 2016, British Journal of Sports Medicine.

[10]  M. Tannast,et al.  Femoroacetabular impingement: radiographic diagnosis--what the radiologist should know. , 2007, AJR. American journal of roentgenology.

[11]  M. Beck,et al.  Do Normal Radiographs Exclude Asphericity of the Femoral Head-Neck Junction? , 2009, Clinical orthopaedics and related research.

[12]  R. Ganz,et al.  Femoroacetabular impingement: a cause for osteoarthritis of the hip. , 2003, Clinical orthopaedics and related research.

[13]  G Zheng,et al.  Biomechanical validation of computer assisted planning of periacetabular osteotomy: A preliminary study based on finite element analysis. , 2015, Medical engineering & physics.

[14]  R. Richards,et al.  The Influence of Pelvic Tilt on Acetabular Orientation and Cover: A Three-Dimensional Computerised Tomography Analysis , 2013, Hip international : the journal of clinical and experimental research on hip pathology and therapy.

[15]  A. Heinecke,et al.  Acetabular and femoral anteversion: relationship with osteoarthritis of the hip. , 1999, The Journal of bone and joint surgery. American volume.

[16]  Guoyan Zheng,et al.  Augmented marker tracking for peri-acetabular osteotomy surgery , 2018, International Journal of Computer Assisted Radiology and Surgery.

[17]  C. Pfirrmann,et al.  Pincer‐type MRI morphology seen in over a third of asymptomatic healthy volunteers without femoroacetabular impingement , 2018, Journal of magnetic resonance imaging : JMRI.

[18]  Beat Schmutz,et al.  Quantification of the accuracy of MRI generated 3D models of long bones compared to CT generated 3D models. , 2012, Medical engineering & physics.

[19]  T. Maak,et al.  Computed Tomography Scans in Patients With Young Adult Hip Pain Carry a Lifetime Risk of Malignancy. , 2018, Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association.

[20]  Joan M. Whitworth,et al.  Hip arthroscopy versus best conservative care for the treatment of femoroacetabular impingement syndrome (UK FASHIoN): a multicentre randomised controlled trial , 2018, The Lancet.

[21]  M. Tannast,et al.  Femoroacetabular Impingement Patients With Decreased Femoral Version Have Different Impingement Locations and Intra- and Extraarticular Anterior Subspine FAI on 3D-CT–Based Impingement Simulation: Implications for Hip Arthroscopy , 2019, The American journal of sports medicine.

[22]  S B Murphy,et al.  Planning acetabular redirection osteotomies based on joint contact pressures. , 1999, Clinical orthopaedics and related research.

[23]  M. Tannast,et al.  What Are the Radiographic Reference Values for Acetabular Under- and Overcoverage? , 2015, Clinical orthopaedics and related research.

[24]  M. Tannast,et al.  Differences in Femoral Torsion Among Various Measurement Methods Increase in Hips With Excessive Femoral Torsion , 2019, Clinical orthopaedics and related research.

[25]  C. Pfirrmann,et al.  Cam and pincer femoroacetabular impingement: characteristic MR arthrographic findings in 50 patients. , 2006, Radiology.

[26]  R. Poss,et al.  Osteotomies of the hip in the prevention and treatment of osteoarthritis. , 1992, Instructional course lectures.

[27]  Chengwen Chu,et al.  FACTS: Fully Automatic CT Segmentation of a Hip Joint , 2014, Annals of Biomedical Engineering.

[28]  Guoyan Zheng,et al.  Holistic decomposition convolution for effective semantic segmentation of medical volume images , 2019, Medical Image Anal..

[29]  Guoyan Zheng,et al.  3D U-net with Multi-level Deep Supervision: Fully Automatic Segmentation of Proximal Femur in 3D MR Images , 2017, MLMI@MICCAI.

[30]  David R. Maldonado,et al.  Does Femoral Retroversion Adversely Affect Outcomes After Hip Arthroscopy for Femoroacetabular Impingement Syndrome? A Midterm Analysis. , 2019, Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association.

[31]  M. Tannast,et al.  Patient-Specific 3-D Magnetic Resonance Imaging–Based Dynamic Simulation of Hip Impingement and Range of Motion Can Replace 3-D Computed Tomography–Based Simulation for Patients With Femoroacetabular Impingement: Implications for Planning Open Hip Preservation Surgery and Hip Arthroscopy , 2019, The American journal of sports medicine.

[32]  Michael P Reiman,et al.  Diagnostic accuracy of clinical tests for the diagnosis of hip femoroacetabular impingement/labral tear: a systematic review with meta-analysis , 2014, British Journal of Sports Medicine.

[33]  Nadia Magnenat-Thalmann,et al.  Bone motion analysis from dynamic MRI: acquisition and tracking. , 2005 .

[34]  Guoyan Zheng,et al.  Latent3DU-net: Multi-level Latent Shape Space Constrained 3D U-net for Automatic Segmentation of the Proximal Femur from Radial MRI of the Hip , 2018, MLMI@MICCAI.

[35]  M. Tannast,et al.  Arthroscopic versus open cam resection in the treatment of femoroacetabular impingement. , 2013, Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association.

[36]  Alan L. Zhang,et al.  Validation of scoring hip osteoarthritis with MRI (SHOMRI) scores using hip arthroscopy as a standard of reference , 2018, European Radiology.

[37]  Nicholas P. Fey,et al.  Cam-type femoroacetabular impingement—correlations between alpha angle versus volumetric measurements and surgical findings , 2019, European Radiology.

[38]  Jos Vander Sloten,et al.  Segmentation accuracy of long bones. , 2014, Medical engineering & physics.

[39]  Michael P Reiman,et al.  Diagnostic Accuracy of Imaging Modalities and Injection Techniques for the Diagnosis of Femoroacetabular Impingement/Labral Tear: A Systematic Review With Meta-analysis , 2017, The American journal of sports medicine.

[40]  Chengwen Chu,et al.  MASCG: Multi-Atlas Segmentation Constrained Graph method for accurate segmentation of hip CT images , 2015, Medical Image Anal..

[41]  M. Tannast,et al.  What Is the Prevalence of Cam Deformity After Prophylactic Pinning of the Contralateral Asymptomatic Hip in Unilateral Slipped Capital Femoral Epiphysis? A 10-year Minimum Followup Study , 2018, Clinical orthopaedics and related research.

[42]  Moritz Tannast,et al.  Prevalence of Femoral and Acetabular Version Abnormalities in Patients With Symptomatic Hip Disease: A Controlled Study of 538 Hips , 2018, The American journal of sports medicine.

[43]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[44]  Guoyan Zheng,et al.  Segmentation of the proximal femur in radial MR scans using a random forest classifier and deformable model registration , 2018, International Journal of Computer Assisted Radiology and Surgery.

[45]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[46]  C. Pfirrmann,et al.  Cam and pincer impingements rarely occur in isolation. , 2007, Radiology.

[47]  M. Tannast,et al.  Twelve Percent of Hips With a Primary Cam Deformity Exhibit a Slip-like Morphology Resembling Sequelae of Slipped Capital Femoral Epiphysis , 2015, Clinical orthopaedics and related research.

[48]  Arakua Welbeck,et al.  Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks , 2017, Scientific Reports.

[49]  M Tannast,et al.  Size and shape of the lunate surface in different types of pincer impingement: theoretical implications for surgical therapy. , 2014, Osteoarthritis and cartilage.

[50]  K. Siebenrock,et al.  High Survivorship and Little Osteoarthritis at 10-year Followup in SCFE Patients Treated With a Modified Dunn Procedure , 2017, Clinical orthopaedics and related research.

[51]  C. Pfirrmann,et al.  Hip Imaging. , 2017, Seminars in musculoskeletal radiology.

[52]  Li Liu,et al.  Computer Assisted Planning and Navigation of Periacetabular Osteotomy with Range of Motion Optimization , 2014, MICCAI.

[53]  Reto Sutter,et al.  How useful is the alpha angle for discriminating between symptomatic patients with cam-type femoroacetabular impingement and asymptomatic volunteers? , 2012, Radiology.

[54]  Chien-Hung Liao,et al.  Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs , 2019, European Radiology.

[55]  E. Genda,et al.  Three-dimensional evaluation of acetabular coverage of the femoral head in normal hip joints and hip joints with acetabular dysplasia. , 1992, Nihon Seikeigeka Gakkai zasshi.

[56]  Jonathan K. Kazam,et al.  Preoperative Use of a 3D Printed Model for Femoroacetabular Impingement Surgery and Its Effect on Planned Osteoplasty. , 2018, AJR. American journal of roentgenology.

[57]  M. Tannast,et al.  One-third of Hips After Periacetabular Osteotomy Survive 30 Years With Good Clinical Results, No Progression of Arthritis, or Conversion to THA , 2017, Clinical orthopaedics and related research.

[58]  R. Richards,et al.  Analysis of cover of the femoral head in normal and dysplastic hips: new CT-based technique. , 2008, The Journal of bone and joint surgery. British volume.

[59]  J. Hodler,et al.  The contour of the femoral head-neck junction as a predictor for the risk of anterior impingement. , 2002, The Journal of bone and joint surgery. British volume.