Dataset Information

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.

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?ConclusionsAutomatic 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.

SUBMITTER: Zeng G

PROVIDER: S-EPMC7753932 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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.

Zeng Guodong G Schmaranzer Florian F Degonda Celia C Gerber Nicolas N Gerber Kate K Tannast Moritz M Burger Jürgen J Siebenrock Klaus A KA Zheng Guoyan G Lerch Till D TD

European journal of radiology open 20201218

<h4>Introduction</h4>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 manua ...[more]

PMID: 33364259

Similar Datasets

Project description:BACKGROUND:Hip dysplasia is one of the most common causes of hip arthritis. Its incidence is estimated to be between 3.6 and 12.8% (Canadian Institute for Health Information, Hip and knee replacements in Canada, 2017-2018: Canadian joint replacement registry annual report, 2019; Jacobsen and Sonne-Holm, Rheumatology 44:211-8, 2004). The Periacetabular Osteotomy (PAO) has been used successfully for over 30?years (Gosvig et al., J Bone Joint Surg Am 92:1162-9, 2010), but some patients continue to exhibit symptoms post-surgery (Wyles et al., Clin Orthop Relat Res 475:336-50, 2017). A hip arthroscopy, performed using a small camera, allows surgeons to address torn cartilage inside the hip joint. Although both procedures are considered standard of care treatment options, it is unknown whether the addition of hip arthroscopy improves patient outcomes compared to a PAO alone. To delay or prevent future joint replacement surgeries, joint preservation surgery is recommended for eligible patients. While previous studies found an added cost to perform hip arthroscopies, the cost-effectiveness to Canadian Health care system is not known. METHODS:Patients randomized to the experimental group will undergo central compartment hip arthroscopy prior to completion of the PAO. Patients randomized to the control group will undergo isolated PAO. Patient-reported quality of life will be the primary outcome used for comparison between the two treatment groups as measured by The International Hip Outcome Tool (iHOT-33) (Saberi Hosnijeh et al., Arthritis Rheum 69:86-93, 2017). Secondary outcomes will include the four-square step test and sit-to-stand (validated in patients with pre-arthritic hip pain) and hip-specific symptoms and impairment using the HOOS; global health assessment will be compared using the PROMIS Global 10 Score; health status will be assessed using the EQ-5D-5L and EQ VAS questionnaires (Ganz et al., Clin Orthop Relat Res 466:264-72, 2008) pre- and post-operatively. In addition, operative time, hospital length of stay, adverse events, and health services utilization will be collected. A sub-group of patients (26 in each group) will receive a T1rho MRI before and after surgery to study changes in cartilage quality over time. A cost-utility analysis will be performed to compare costs and quality-adjusted life years (QALYs) associated with the intervention. DISCUSSION:We hypothesize that (1) concomitant hip arthroscopy at the time of PAO to address central compartment pathology will result in clinically important improvements in patient-reported outcome measures (PROMs) versus PAO alone, that (2) additional costs associated with hip arthroscopy will be offset by greater clinical improvements in this group, and that (3) combined hip arthroscopy and PAO will prove to be a cost-effective procedure. TRIAL REGISTRATION:ClinicalTrials.gov NCT03481010 . Registered on 6 March 2020. Protocol version: version 3.

Dataset Information

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

Methods

Results

Publications

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.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure