Automatic Cartilage Segmentation for Delayed Gadolinium-Enhanced Magnetic Resonance Imaging of Hip Joint Cartilage: A Feasibility Study

3.0T magnetic resonance imaging-based hip bone models for femoroacetabular impingement syndrome are equivalent to computed tomography-based models

This study aimed to compare three-dimensional (3D) proximal femoral and acetabular surface models generated from 3.0T magnetic resonance imaging (MRI) to the clinical gold standard of computed tomography (CT). Ten intact fresh-frozen cadaveric hips underwent CT and 3.0T MRI scans. The CT- and MRI-based segmented models were superimposed using a validated 3D-3D registration volume-merge method to compare them. The least surface-to-surface distance between the models was calculated by a point-to-surface calculation algorithm using a custom-written program. The variables of interest were the signed and absolute surface-to-surface distance between the paired bone models. One-sample t-tests were performed using a signed and absolute test value of 0.16 mm and 0.37 mm, respectively, based on a previous study that validated 1.5T MRI bone models by comparison with CT bone models. For the femur, the average signed and absolute surface-to-surface distance was 0.18 ± 0.09 mm and 0.30 ± 0.06 mm, respectively. There was no difference in the signed surface-to-surface distance and the 0.16 mm test value (t = 0.650, p = 0.532). However, the absolute surface-to-surface difference was less than the 0.37 mm test value (t = -4.025, p = 0.003). For the acetabulum, the average signed and absolute surface-to-surface distance was -0.06 ± 0.06 mm and 0.26 ± 0.04 mm, respectively. The signed (t = -12.569, p < 0.001) and absolute (t = -8.688, p < 0.001) surface-to-surface difference were less than the 0.16 mm and 0.37 mm test values, respectively. Our data shows that 3.0T MRI bone models are more similar to CT bone models than previously validated 1.5T MRI bone models. This is likely due to the higher resolution of the 3T data.

[Innovative image-based planning in musculoskeletal surgery]

BACKGROUND

For the preparation of surgical procedures in orthopedics and trauma surgery, precise knowledge of imaging and the three-dimensional imagination of the surgeon are of outstanding importance. Image-based, preoperative two-dimensional planning is the gold standard in arthroplasty today. In complex cases, further imaging such as computed tomography (CT) or magnetic resonance imaging is also performed, generating a three-dimensional model of the body region and helping the surgeon in the planning of the surgical treatment. Four-dimensional, dynamic CT studies have also been reported and are available as a complementary tool.

DIGITAL AIDS

Furthermore, digital aids should generate an improved representation of the pathology to be treated and optimize the surgeon's imagination. The finite element method allows patient-specific and implant-specific parameters to be taken into account in preoperative surgical planning. Intraoperatively, relevant information can be provided by augmented reality without significantly influencing the surgical workflow.

Automated quantification of cartilage quality for hip treatment decision support

Purpose

Preservation surgery can halt the progress of joint degradation, preserving the life of the hip; however, outcome depends on the existing cartilage quality. Biochemical analysis of the hip cartilage utilizing MRI sequences such as delayed gadolinium-enhanced MRI of cartilage (dGEMRIC), in addition to morphological analysis, can be used to detect early signs of cartilage degradation. However, a complete, accurate 3D analysis of the cartilage regions and layers is currently not possible due to a lack of diagnostic tools.

Methods

A system for the efficient automatic parametrization of the 3D hip cartilage was developed. 2D U-nets were trained on manually annotated dual-flip angle (DFA) dGEMRIC for femoral head localization and cartilage segmentation. A fully automated cartilage sectioning pipeline for analysis of central and peripheral regions, femoral-acetabular layers, and a variable number of section slices, was developed along with functionality for the automatic calculation of dGEMRIC index, thickness, surface area, and volume.

Results

The trained networks locate the femoral head and segment the cartilage with a Dice similarity coefficient of 88 ± 3 and 83 ± 4% on DFA and magnetization-prepared 2 rapid gradient-echo (MP2RAGE) dGEMRIC, respectively. A completely automatic cartilage analysis was performed in 18s, and no significant difference for average dGEMRIC index, volume, surface area, and thickness calculated on manual and automatic segmentation was observed.

Conclusion

An application for the 3D analysis of hip cartilage was developed for the automated detection of subtle morphological and biochemical signs of cartilage degradation in prognostic studies and clinical diagnosis. The segmentation network achieved a 4-time increase in processing speed without loss of segmentation accuracy on both normal and deformed anatomy, enabling accurate parametrization. Retraining of the networks with the promising MP2RAGE protocol would enable analysis without the need for B1 inhomogeneity correction in the future.

Automated measurement of alpha angle on 3D-magnetic resonance imaging in femoroacetabular impingement hips: a pilot study

BACKGROUND

Femoroacetabular impingement (FAI) syndrome is an established pre-osteoarthritic condition. Diagnosis is based on both clinical and radiographic parameters. An abnormal manually calculated alpha angle in magnetic resonance imaging (MRI) is traditionally utilized to diagnose abnormal femoral head-neck offset. This pilot study aimed to assess the feasibility of automated alpha angle measurements in patients with FAI syndrome, and to compare automated with manual measurements data with regard to the time and effort needed in each method.

METHODS

Alpha angles were measured with manual and automated techniques, using postprocessing software in nineteen hip MRIs of FAI syndrome patients. Two observers conducted manual measurements. Intra- and inter-observer reproducibility and correlation of manual and automated alpha angle measurements were calculated using intra-class correlation (ICC) analysis. Both techniques were compared regarding the time taken (in minutes) and effort required, measured as the amount of mouse button presses performed.

RESULTS

The first observer's intra-observer reproducibility was good (ICC 0.77; p < 0.001) while the second observer's was good-to-excellent (ICC 0.93; p < 0.001). Inter-observer reproducibility between both observers in the first (ICC 0.45; p < 0.001) and second (ICC 0.56; p < 0.001) manual alpha angle assessment was moderate. The intra-class correlation coefficients between manual and automated alpha angle measurements were ICC = 0.24 (p = 0.052; observer 1, 1st measurement), ICC = 0.32 (p = 0.015; observer 1, 2nd measurement), ICC = 0.50 (p < 0.001; observer 2, 1st measurement), and ICC = 0.45 (p < 0.001; observer 2, 2nd measurement). Average runtime for automatic processing of the image data for the automated assessment was 16.6 ± 1.9 min. Automatic alpha angle measurements took longer (time difference: 14.6 ± 3.9 min; p < 0.001) but required less effort (difference in button presses: 231 ± 23; p < 0.001). While the automatic processing is running, the user can perform other tasks.

CONCLUSIONS

This pilot study demonstrates that objective and reliable automated alpha angle measurement of MRIs in FAI syndrome hips is feasible. Trial registration The Ethics Committee of the University of Düsseldorf approved our study (Registry-ID: 2017084398).

[Recent research progress of hip-preserving treatment for adolescents and adults with developmental dysplasia of the hip]

Objective

To review the imaging evaluation, treatment progress, and controversy related to developmental dysplasia of the hip (DDH) in adolescents and adults.

Methods

The domestic and abroad hot issues related to adolescents and adults with DDH in recent years, including new imaging techniques for assessing cartilage, controversies over the diagnosis and treatment of borderline DDH (BDDH), and the improvement and prospect of peracetabular osteotomy (PAO) were summarized and analyzed.

Results

DDH is one of the main factors leading to hip osteoarthritis. As the understanding of the pathological changes of DDH continues to deepen, the use of delayed gadolinium-enhanced MRI of cartilage can further evaluate the progress of osteoarthritis and predict the prognosis after hip preservation. There are still controversies about the diagnosis and treatment of BDDH. At the same time, PAO technology and concepts are still being improved.

Conclusion

Cartilage injury and bony structure determine the choice of surgical methods and postoperative prognosis of hip preservation surgery. The hip preservation of adolescent and adult DDH patients will move towards the goal of individualization and accuracy.

Reproducibility of an Automated Quantitative MRI Assessment of Low-Grade Knee Articular Cartilage Lesions

OBJECTIVE

The goal of this study was to assess the reproducibility of an automated knee cartilage segmentation of 21 cartilage regions with a model-based algorithm and to compare the results with manual segmentation.

DESIGN

Thirteen patients with low-grade femoral cartilage defects were included in the study and were scanned twice on a 7-T magnetic resonance imaging (MRI) scanner 8 days apart. A 3-dimensional double-echo steady-state (3D-DESS) sequence was used to acquire MR images for automated cartilage segmentation, and T2-mapping was performed using a 3D triple-echo steady-state (3D-TESS) sequence. Cartilage volume, thickness, and T2 and texture features were automatically extracted from each knee for each of the 21 subregions. DESS was used for manual cartilage segmentation and compared with automated segmentation using the Dice coefficient. The reproducibility of each variable was expressed using standard error of measurement (SEM) and smallest detectable change (SDC).

RESULTS

The Dice coefficient for the similarity between manual and automated segmentation ranged from 0.83 to 0.88 in different cartilage regions. Test-retest analysis of automated cartilage segmentation and automated quantitative parameter extraction revealed excellent reproducibility for volume measurement (mean SDC for all subregions of 85.6 mm³), for thickness detection (SDC = 0.16 mm) and also for T2 values (SDC = 2.38 ms) and most gray-level co-occurrence matrix features (SDC = 0.1 a.u.).

CONCLUSIONS

The proposed technique of automated knee cartilage evaluation based on the segmentation of 3D MR images and correlation with T2 mapping provides highly reproducible results and significantly reduces the segmentation effort required for the analysis of knee articular cartilage in longitudinal studies.

Magnetization-prepared 2 Rapid Gradient-Echo MRI for B1 Insensitive 3D T1 Mapping of Hip Cartilage: An Experimental and Clinical Validation

Background Often used for T1 mapping of hip cartilage, three-dimensional (3D) dual-flip-angle (DFA) techniques are highly sensitive to flip angle variations related to B₁ inhomogeneities. The authors hypothesized that 3D magnetization-prepared 2 rapid gradient-echo (MP2RAGE) MRI would help provide more accurate T1 mapping of hip cartilage at 3.0 T than would 3D DFA techniques. Purpose To compare 3D MP2RAGE MRI with 3D DFA techniques using two-dimensional (2D) inversion recovery T1 mapping as a standard of reference for hip cartilage T1 mapping in phantoms, healthy volunteers, and participants with hip pain. Materials and Methods T1 mapping at 3.0 T was performed in phantoms and in healthy volunteers using 3D MP2RAGE MRI and 3D DFA techniques with B₁ field mapping for flip angle correction. Participants with hip pain prospectively (July 2019-January 2020) underwent indirect MR arthrography (with intravenous administration of 0.2 mmol/kg of gadoterate meglumine), including 3D MP2RAGE MRI. A 2D inversion recovery-based sequence served as a T1 reference in phantoms and in participants with hip pain. In healthy volunteers, cartilage T1 was compared between 3D MP2RAGE MRI and 3D DFA techniques. Paired t tests and Bland-Altman analysis were performed. Results Eleven phantoms, 10 healthy volunteers (median age, 27 years; range, 26-30 years; five men), and 20 participants with hip pain (mean age, 34 years ± 10 [standard deviation]; 17 women) were evaluated. In phantoms, T1 bias from 2D inversion recovery was lower for 3D MP2RAGE MRI than for 3D DFA techniques (mean, 3 msec ± 11 vs 253 msec ± 85; P < .001), and, unlike 3D DFA techniques, the deviation found with MP2RAGE MRI did not correlate with increasing B₁ deviation. In healthy volunteers, regional cartilage T1 difference (109 msec ± 163; P = .008) was observed only for the 3D DFA technique. In participants with hip pain, the mean T1 bias of 3D MP2RAGE MRI from 2D inversion recovery was -23 msec ± 31 (P < .001). Conclusion Compared with three-dimensional (3D) dual-flip-angle techniques, 3D magnetization-prepared 2 rapid gradient-echo MRI enabled more accurate T1 mapping of hip cartilage, was less affected by B₁ inhomogeneities, and showed high accuracy against a T1 reference in participants with hip pain. © RSNA, 2021.

Automatic MRI-based Three-dimensional Models of Hip Cartilage Provide Improved Morphologic and Biochemical Analysis

BACKGROUND

The time-consuming and user-dependent postprocessing of biochemical cartilage MRI has limited the use of delayed gadolinium-enhanced MRI of cartilage (dGEMRIC). An automated analysis of biochemical three-dimensional (3-D) images could deliver a more time-efficient and objective evaluation of cartilage composition, and provide comprehensive information about cartilage thickness, surface area, and volume compared with manual two-dimensional (2-D) analysis.

QUESTIONS/PURPOSES

(1) How does the 3-D analysis of cartilage thickness and dGEMRIC index using both a manual and a new automated method compare with the manual 2-D analysis (gold standard)? (2) How does the manual 3-D analysis of regional patterns of dGEMRIC index, cartilage thickness, surface area and volume compare with a new automatic method? (3) What is the interobserver reliability and intraobserver reproducibility of software-assisted manual 3-D and automated 3-D analysis of dGEMRIC indices, thickness, surface, and volume for two readers on two time points?

METHODS

In this IRB-approved, retrospective, diagnostic study, we identified the first 25 symptomatic hips (23 patients) who underwent a contrast-enhanced MRI at 3T including a 3-D dGEMRIC sequence for intraarticular pathology assessment due to structural hip deformities. Of the 23 patients, 10 (43%) were male, 16 (64%) hips had a cam deformity and 16 (64%) hips had either a pincer deformity or acetabular dysplasia. The development of an automated deep-learning-based approach for 3-D segmentation of hip cartilage models was based on two steps: First, one reader (FS) provided a manual 3-D segmentation of hip cartilage, which served as training data for the neural network and was used as input data for the manual 3-D analysis. Next, we developed the deep convolutional neural network to obtain an automated 3-D cartilage segmentation that we used as input data for the automated 3-D analysis. For actual analysis of the manually and automatically generated 3-D cartilage models, a dedicated software was developed. Manual 2-D analysis of dGEMRIC indices and cartilage thickness was performed at each "full-hour" position on radial images and served as the gold standard for comparison with the corresponding measurements of the manual and the automated 3-D analysis. We measured dGEMRIC index, cartilage thickness, surface area, and volume for each of the four joint quadrants and compared the manual and the automated 3-D analyses using mean differences. Agreement between the techniques was assessed using intraclass correlation coefficients (ICC). The overlap between 3-D cartilage volumes was assessed using dice coefficients and means of all distances between surface points of the models were calculated as average surface distance. The interobserver reliability and intraobserver reproducibility of the software-assisted manual 3-D and the automated 3-D analysis of dGEMRIC indices, thickness, surface and volume was assessed for two readers on two different time points using ICCs.

RESULTS

Comparable mean overall difference and almost-perfect agreement in dGEMRIC indices was found between the manual 3-D analysis (8 ± 44 ms, p = 0.005; ICC = 0.980), the automated 3-D analysis (7 ± 43 ms, p = 0.015; ICC = 0.982), and the manual 2-D analysis.Agreement for measuring overall cartilage thickness was almost perfect for both 3-D methods (ICC = 0.855 and 0.881) versus the manual 2-D analysis. A mean difference of -0.2 ± 0.5 mm (p < 0.001) was observed for overall cartilage thickness between the automated 3-D analysis and the manual 2-D analysis; no such difference was observed between the manual 3-D and the manual 2-D analysis.Regional patterns were comparable for both 3-D methods. The highest dGEMRIC indices were found posterosuperiorly (manual: 602 ± 158 ms; p = 0.013, automated: 602 ± 158 ms; p = 0.012). The thickest cartilage was found anteroinferiorly (manual: 5.3 ± 0.8 mm, p < 0.001; automated: 4.3 ± 0.6 mm; p < 0.001). The smallest surface area was found anteroinferiorly (manual: 134 ± 60 mm; p < 0.001, automated: 155 ± 60 mm; p < 0.001). The largest volume was found anterosuperiorly (manual: 2343 ± 492 mm; p < 0.001, automated: 2294 ± 467 mm; p < 0.001). Mean average surface distance was 0.26 ± 0.13 mm and mean Dice coefficient was 86% ± 3%. Intraobserver reproducibility and interobserver reliability was near perfect for overall analysis of dGEMRIC indices, thickness, surface area, and volume (ICC range, 0.962-1).

CONCLUSIONS

The presented deep learning approach for a fully automatic segmentation of hip cartilage enables an accurate, reliable and reproducible analysis of dGEMRIC indices, thickness, surface area, and volume. This time-efficient and objective analysis of biochemical cartilage composition and morphology yields the potential to improve patient selection in femoroacetabular impingement (FAI) surgery and to aid surgeons with planning of acetabuloplasty and periacetabular osteotomies in pincer FAI and hip dysplasia. In addition, this validation paves way to the large-scale use of this method for prospective trials which longitudinally monitor the effect of reconstructive hip surgery and the natural course of osteoarthritis.

LEVEL OF EVIDENCE

Level III, diagnostic study.