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.
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.
复制标题
DOI：
10.1016/j.ejro.2020.100303
复制
发表时间：
2021
影响因子：
2
通讯作者：
Lerch TD
中科院分区：
文献类型：
--
作者：
Zeng G;Schmaranzer F;Degonda C;Gerber N;Gerber K;Tannast M;Burger J;Siebenrock KA;Zheng G;Lerch TD
髋关节发育不良(DDH)和髋臼撞击(FAI)都是导致年轻患者髋关节疼痛和骨关节炎的复杂三维髋关节病理。基于3D-MRI的模型用于无放射计算机辅助手术计划。基于MRI的3D模型的自动分割是首选的，因为手动分割很耗时。探讨(1)基于自动MR和基于人工CT的三维模型对股骨头覆盖率(FHC)的差异和相关性；(3)对有症状的髋关节疾病患者进行术前计划的可行性。我们对31个髋关节(26个有症状的髋关节发育不良或FAI患者)进行了IRB批准的对比、回顾研究。获得髋关节的3D MRI序列和CT扫描。术前MRI包括髋关节轴向-斜位T1Vibe序列(0.8 mm~3等体素)。对MRI和CT扫描进行手动分割。利用深度学习实现了基于MRI的3D模型的自动分割。(1)基于磁共振成像的三维髋关节模型自动分割与手动分割的差值小于1 mm(股骨近端0.2 ± 0.1 mm，髋臼0.3 ± 0.5 mm)。股骨近端和髋臼的骰子系数分别为98%和97%。(2)基于自动磁共振成像的三维模型与基于手动CT的三维模型之间的相关性良好且显著(r = 0.975，p <； 0.001)。自动和手动基于MR的3D模型之间的总FHC(r = 0.979，p <； 0.001)相关性很好。(3)对于髋关节发育不良或髋臼后倾的患者，术前计划和模拟髋臼周围截骨术是可行的(100%)。对于育龄髋关节疾病患者，基于深度学习的基于MRI的3D模型的自动分割与基于CT的3D模型的自动分割一样准确。这使得DDH患者的髋臼周围截骨术可以在无放射和患者特定的术前模拟和手术计划中进行。
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. 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. (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. 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.
登录
查看更多内容
DOI：
10.1097/01.blo.0000096804.78689.c2
发表时间：
2003-12-01
影响因子：
4.2
作者：
Ganz, R;Parvizi, J;Siebenrock, KA
通讯作者：
Siebenrock, KA
DOI：
10.1016/j.arthro.2012.12.009
发表时间：
2013-04-01
影响因子：
4.7
作者：
Buechler, Lorenz;Neumann, Mirjam;Beck, Martin
通讯作者：
Beck, Martin
影响因子：
2.6
作者：
Childs, Sean;McVicker, Zachary;Giordano, Brian
通讯作者：
Giordano, Brian
DOI：
10.1016/j.arthro.2019.03.046
发表时间：
2019-11-01
影响因子：
4.7
作者：
Lall, Ajay C.;Battaglia, Muriel R.;Domb, Benjamin G.
通讯作者：
Domb, Benjamin G.
影响因子：
5.9
作者：
Cheng, Chi-Tung;Ho, Tsung-Ying;Liao, Chien-Hung
通讯作者：
Liao, Chien-Hung