Dataset Information

Three-Dimensional Magnetic Resonance Imaging Bone Models of the Hip Joint Using Deep Learning: Dynamic Simulation of Hip Impingement for Diagnosis of Intra- and Extra-articular Hip Impingement.

ABSTRACT:

Background

Dynamic 3-dimensional (3D) simulation of hip impingement enables better understanding of complex hip deformities in young adult patients with femoroacetabular impingement (FAI). Deep learning algorithms may improve magnetic resonance imaging (MRI) segmentation.

Purpose

(1) To evaluate the accuracy of 3D models created using convolutional neural networks (CNNs) for fully automatic MRI bone segmentation of the hip joint, (2) to correlate hip range of motion (ROM) between manual and automatic segmentation, and (3) to compare location of hip impingement in 3D models created using automatic bone segmentation in patients with FAI.

Study design

Cohort study (diagnosis); Level of evidence, 3.

Methods

The authors retrospectively reviewed 31 hip MRI scans from 26 symptomatic patients (mean age, 27 years) with hip pain due to FAI. All patients had matched computed tomography (CT) and MRI scans of the pelvis and the knee. CT- and MRI-based osseous 3D models of the hip joint of the same patients were compared (MRI: T1 volumetric interpolated breath-hold examination high-resolution sequence; 0.8 mm³ isovoxel). CNNs were used to develop fully automatic bone segmentation of the hip joint, and the 3D models created using this method were compared with manual segmentation of CT- and MRI-based 3D models. Impingement-free ROM and location of hip impingement were calculated using previously validated collision detection software.

Results

The difference between the CT- and MRI-based 3D models was <1 mm, and the difference between fully automatic and manual segmentation of MRI-based 3D models was <1 mm. The correlation of automatic and manual MRI-based 3D models was excellent and significant for impingement-free ROM (r = 0.995; P < .001), flexion (r = 0.953; P < .001), and internal rotation at 90° of flexion (r = 0.982; P < .001). The correlation for impingement-free flexion between automatic MRI-based 3D models and CT-based 3D models was 0.953 (P < .001). The location of impingement was not significantly different between manual and automatic segmentation of MRI-based 3D models, and the location of extra-articular hip impingement was not different between CT- and MRI-based 3D models.

Conclusion

CNN can potentially be used in clinical practice to provide rapid and accurate 3D MRI hip joint models for young patients. The created models can be used for simulation of impingement during diagnosis of intra- and extra-articular hip impingement to enable radiation-free and patient-specific surgical planning for hip arthroscopy and open hip preservation surgery.

SUBMITTER: Zeng G

PROVIDER: S-EPMC8685729 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeWe aimed to determine the relationship between recreational sports and intra-articular hip injuries in an active population that had undergone hip arthroscopy for femoroacetabular impingement syndrome.MethodsA retrospective review was performed of prospectively collected data from patients undergoing hip arthroscopy between January 2015 and December 2016. Inclusion criteria included patients between 18 and 50 years of age who had participated in recreational sports prior to surgery and had a minimum of a 2-year follow-up. Labral injury was evaluated using the Multicenter Arthroscopic Hip Outcome Research Network classification, and rim chondral injuries were evaluated using the Acetabular Labral Articular Disruptions system. Ligamentum teres tear and psoas impingement were also recorded. Sports were classified as rotational running (soccer, basketball, handball), flexibility (martial arts, dance), asymmetric-overhead (racquet), or endurance (running, swimming, cycling). Primary univariate analysis of sports' independent associations, demographic characteristics, intra-articular hip injuries, and outcomes was performed.ResultsPatients included 185 people with a mean age of 36.7 years. Patients participating in rotational running sports and flexibility sports had a significantly greater proportion of rim chondral injuries than those participating in endurance sports or asymmetric overhead sports (P = 0.02). Ligamentum teres tears were significantly associated with flexibility sports (P < 0.001). A total of 84.7%, 67.7%, 67.2%, and 71.2% of patients met minimal clinically important difference levels for the modified Harris Hip Score (mHHS), the Hip Outcome Score (HOS)10 questionnaire with activities of daily living (HOS-ADL), the sports subscale (HOS-SSS), and the International Hip Outcome Tool (iHOT-12), respectively; 94.9%, 66.2% and 62.7% met the patient acceptable symptom state for mHHS, HOS-ADL, and HOS-SSS, respectively; 86.7%, 48.5%, 47.8%, and 32.4% found substantial clinical benefit for mHHS, HOS-ADL, HOS-SSS, and iHOT-12, respectively.ConclusionsRotational running sports were significantly associated with rim chondral injuries. Flexibility sports were significantly associated with rim chondral injuries and ligamentum teres tears. Athletes participating in these sports are more likely to have intra-articular hip injuries than those in the other sports categories.Level of evidenceLevel IV, prognostic case series.

Project description:BackgroundPosterior extra-articular hip impingement has been described for valgus hips with increased femoral version (FV). These patients can present clinically with lack of external rotation (ER) and extension and with a positive posterior impingement test. But we do not know the effect of the combination of deformities, and the impingement location in early flexion is unknown.PurposeTo evaluate patient-specific 3-dimensional computed tomography (3D CT) scans of hips with increased FV and control hips for differences in range of motion, location and prevalence of osseous posterior intra- and extra-articular hip impingement.Study designCase series; Level of evidence, 4.MethodsOsseous 3D models based on segmentation of 3D CT scans were analyzed for 52 hips (38 symptomatic patients) with positive posterior impingement test and increased FV (>35°). There were 26 hips with an increased McKibbin instability index >70 (unstable hips). Patients were mainly female (96%), with an age range of 18 to 45 years. Of them, 21 hips had isolated increased FV (>35°); 22 hips had increased FV and increased acetabular version (AV; >25°); and 9 valgus hips (caput-collum-diaphyseal angle >139°) had increased FV and increased AV. The control group consisted of 20 hips with normal FV, normal AV, and no valgus (caput-collum-diaphyseal angle <139°). Validated 3D CT-based collision detection software for impingement simulation was used to calculate impingement-free range of motion and location of hip impingement. Surgical treatment was performed after the 3D CT-based impingement simulation in 27 hips (52%).ResultsHips with increased FV had significantly (P < .001) decreased extension and ER at 90° of flexion as compared with the control group. Posterior impingement was extra-articular (92%) in hips with increased FV. Valgus hips with increased FV and AV had combined intra- and extra-articular impingement. Posterior hip impingement occurred between the ischium and the lesser trochanter at 20° of extension and 20° of ER. Impingement was located between the ischium and the greater trochanter or intertrochanteric area at 20° of flexion and 40° of ER, with a modification of the flexion-abduction-ER (FABER) test.ConclusionPosterior extra-articular ischiofemoral hip impingement can be caused by the lesser and greater trochanter or the intertrochanteric region. We recommend performing the modified FABER test during clinical examination in addition to the posterior impingement test for female patients with high FV. In addition, 3D CT can help for surgical planning, such as femoral derotation osteotomy and/or hip arthroscopy or resection of the lesser trochanter.