Cartilage Topography Assessment With Local-Area Cartilage Segmentation for Knee Magnetic Resonance Imaging

OBJECTIVE

Local-area cartilage segmentation (LACS) software was developed to segment medial femur (MF) cartilage on magnetic resonance imaging (MRI). Our objectives were 1) to extend LACS to the lateral femur (LF), medial tibia (MT), and lateral tibia (LT), 2) to compare LACS to an established manual segmentation method, and 3) to visualize cartilage responsiveness over each cartilage plate.

METHODS

Osteoarthritis Initiative participants with symptomatic knee osteoarthritis (OA) were selected, including knees selected at random (n = 40) and knees identified with loss of cartilage based on manual segmentation (Chondrometrics GmbH), an enriched sample of 126 knees. LACS was used to segment cartilage in the MF, LF, MT, and LT on sagittal 3D double-echo steady-state MRI scans at baseline and at 2-year follow-up. We compared LACS and Chondrometrics average thickness measures by estimating the correlation in each cartilage plate and estimating the standardized response mean (SRM) for 2-year cartilage change. We illustrated cartilage loss topographically with SRM heatmaps.

RESULTS

The estimated correlation between LACS and Chondrometrics measures was r = 0.91 (95% confidence interval [95% CI] 0.86, 0.94) for LF, r = 0.93 (95% CI 0.89, 0.95) for MF, r = 0.97 (95% CI 0.96, 0.98) for LT, and r = 0.87 (95% CI 0.81, 0.91) for MT. Estimated SRMs for LACS and Chondrometrics measures were similar in the random sample, and SRM heatmaps identified subregions of LACS-measured cartilage loss.

CONCLUSION

LACS cartilage thickness measurement in the MF and LF and tibia correlated well with established manual segmentation-based measurement, with similar responsiveness to change, among knees with symptomatic knee OA. LACS measurement of cartilage plate topography enables spatiotemporal analysis of cartilage loss in future knee OA studies.

Knee Bone and Cartilage Segmentation Based on a 3D Deep Neural Network Using Adversarial Loss for Prior Shape Constraint

Fast and accurate segmentation of knee bone and cartilage on MRI images is becoming increasingly important in the orthopaedic area, as the segmentation is an essential prerequisite step to a patient-specific diagnosis, optimising implant design and preoperative and intraoperative planning. However, manual segmentation is time-intensive and subjected to inter- and intra-observer variations. Hence, in this study, a three-dimensional (3D) deep neural network using adversarial loss was proposed to automatically segment the knee bone in a resampled image volume in order to enlarge the contextual information and incorporate prior shape constraints. A restoration network was proposed to further improve the bone segmentation accuracy by restoring the bone segmentation back to the original resolution. A conventional U-Net-like network was used to segment the cartilage. The ultimate results were the combination of the bone and cartilage outcomes through post-processing. The quality of the proposed method was thoroughly assessed using various measures for the dataset from the Grand Challenge Segmentation of Knee Images 2010 (SKI10), together with a comparison with a baseline network U-Net. A fine-tuned U-Net-like network can achieve state-of-the-art results without any post-processing operations. This method achieved a total score higher than 76 in terms of the SKI10 validation dataset. This method showed to be robust to extract bone and cartilage masks from the MRI dataset, even for the pathological case.

Open Source Software for Automatic Subregional Assessment of Knee Cartilage Degradation Using Quantitative T2 Relaxometry and Deep Learning

OBJECTIVE

We evaluated a fully automated femoral cartilage segmentation model for measuring T2 relaxation values and longitudinal changes using multi-echo spin-echo (MESE) magnetic resonance imaging (MRI). We open sourced this model and developed a web app available at https://kl.stanford.edu into which users can drag and drop images to segment them automatically.

DESIGN

We trained a neural network to segment femoral cartilage from MESE MRIs. Cartilage was divided into 12 subregions along medial-lateral, superficial-deep, and anterior-central-posterior boundaries. Subregional T2 values and four-year changes were calculated using a radiologist's segmentations (Reader 1) and the model's segmentations. These were compared using 28 held-out images. A subset of 14 images were also evaluated by a second expert (Reader 2) for comparison.

RESULTS

Model segmentations agreed with Reader 1 segmentations with a Dice score of 0.85 ± 0.03. The model's estimated T2 values for individual subregions agreed with those of Reader 1 with an average Spearman correlation of 0.89 and average mean absolute error (MAE) of 1.34 ms. The model's estimated four-year change in T2 for individual subregions agreed with Reader 1 with an average correlation of 0.80 and average MAE of 1.72 ms. The model agreed with Reader 1 at least as closely as Reader 2 agreed with Reader 1 in terms of Dice score (0.85 vs. 0.75) and subregional T2 values.

CONCLUSIONS

Assessments of cartilage health using our fully automated segmentation model agreed with those of an expert as closely as experts agreed with one another. This has the potential to accelerate osteoarthritis research.

Utility of deep learning super-resolution in the context of osteoarthritis MRI biomarkers

BACKGROUND

Super-resolution is an emerging method for enhancing MRI resolution; however, its impact on image quality is still unknown.

PURPOSE

To evaluate MRI super-resolution using quantitative and qualitative metrics of cartilage morphometry, osteophyte detection, and global image blurring.

STUDY TYPE

Retrospective.

POPULATION

In all, 176 MRI studies of subjects at varying stages of osteoarthritis.

FIELD STRENGTH/SEQUENCE

Original-resolution 3D double-echo steady-state (DESS) and DESS with 3× thicker slices retrospectively enhanced using super-resolution and tricubic interpolation (TCI) at 3T.

ASSESSMENT

A quantitative comparison of femoral cartilage morphometry was performed for the original-resolution DESS, the super-resolution, and the TCI scans in 17 subjects. A reader study by three musculoskeletal radiologists assessed cartilage image quality, overall image sharpness, and osteophytes incidence in all three sets of scans. A referenceless blurring metric evaluated blurring in all three image dimensions for the three sets of scans.

STATISTICAL TESTS

Mann-Whitney U-tests compared Dice coefficients (DC) of segmentation accuracy for the DESS, super-resolution, and TCI images, along with the image quality readings and blurring metrics. Sensitivity, specificity, and diagnostic odds ratio (DOR) with 95% confidence intervals compared osteophyte detection for the super-resolution and TCI images, with the original-resolution as a reference.

RESULTS

DC for the original-resolution (90.2 ± 1.7%) and super-resolution (89.6 ± 2.0%) were significantly higher (P < 0.001) than TCI (86.3 ± 5.6%). Segmentation overlap of super-resolution with the original-resolution (DC = 97.6 ± 0.7%) was significantly higher (P < 0.0001) than TCI overlap (DC = 95.0 ± 1.1%). Cartilage image quality for sharpness and contrast levels, and the through-plane quantitative blur factor for super-resolution images, was significantly (P < 0.001) better than TCI. Super-resolution osteophyte detection sensitivity of 80% (76-82%), specificity of 93% (92-94%), and DOR of 32 (22-46) was significantly higher (P < 0.001) than TCI sensitivity of 73% (69-76%), specificity of 90% (89-91%), and DOR of 17 (13-22).

DATA CONCLUSION

Super-resolution appears to consistently outperform naïve interpolation and may improve image quality without biasing quantitative biomarkers.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:768-779.

The Use of a Novel Machine Learning Algorithm for Cartilage Segmentation of Magnetic Resonance Images

BACKGROUND

The variation in articular cartilage thickness (ACT) in healthy knees is difficult to quantify and therefore poorly documented. Our aims are to (1) define how machine learning (ML) algorithms can automate the segmentation and measurement of ACT on magnetic resonance imaging (MRI) (2) use ML to provide reference data on ACT in healthy knees, and (3) identify whether demographic variables impact these results.

METHODS

Patients recruited into the Osteoarthritis Initiative with a radiographic Kellgren-Lawrence grade of 0 or 1 with 3D double-echo steady-state MRIs were included and their gender, age, and body mass index were collected. Using a validated ML algorithm, 2 orthogonal points on each femoral condyle were identified (distal and posterior) and ACT was measured on each MRI. Site-specific ACT was compared using paired t-tests, and multivariate regression was used to investigate the risk-adjusted effect of each demographic variable on ACT.

RESULTS

A total of 3910 MRI were included. The average femoral ACT was 2.34 mm (standard deviation, 0.71; 95% confidence interval, 0.95-3.73). In multivariate analysis, distal-medial (-0.17 mm) and distal-lateral cartilage (-0.32 mm) were found to be thinner than posterior-lateral cartilage, while posterior-medial cartilage was found to be thicker (0.21 mm). In addition, female sex was found to negatively impact cartilage thickness (OR, -0.36; all values: P < .001).

CONCLUSION

ML was effectively used to automate the segmentation and measurement of cartilage thickness on a large number of MRIs of healthy knees to provide normative data on the variation in ACT in this population. We further report patient variables that can influence ACT. Further validation will determine whether this technique represents a powerful new tool for tracking the impact of medical intervention on the progression of articular cartilage degeneration.

Intra- and inter-observer reproducibility of volume measurement of knee cartilage segmented from the OAI MR image set using a novel semi-automated segmentation method

OBJECTIVE

We developed a semi-automated method based on a graph-cuts algorithm for segmentation and volumetric measurements of the cartilage from high-resolution knee magnetic resonance (MR) images from the Osteoarthritis Initiative (OAI) database and assessed the intra- and inter-observer reproducibility of measurements obtained via this method.

DESIGN

MR image sets from 20 subjects of varying Kellgren-Lawrence (KL) grades (from 0 to IV) on fixed flexion knee radiographs were selected from the baseline double-echo and steady-state (DESS) knee MR images in the OAI database (0.B.1 Imaging Data set). Two trained radiologists independently performed the segmentation of knee cartilage twice using the semi-automated method. The volumes of segmented cartilage were computed and compared. The intra- and inter-observer reproducibility were determined by means of the coefficient of variation (CV%) of repeated cartilage segmented volume measurements. The subjects were also divided into the low- (0, I or II) and high-KL (III or IV) groups. The differences in cartilage volume measurements and CV% within and between the observers were tested with t tests.

RESULTS

The mean (+/-SD) intra-observer CV% for the 20 cases was 1.29 (+/-1.05)% for observer 1 and 1.67 (+/-1.14)% for observer 2, while the mean (+/-SD) inter-observer CV% was 1.31 (+/-1.26)% for session 1 and 1.79 (+/-1.72)% for session 2. There was no significant difference between the two intra-observer CV%'s (P=0.272) and between the two inter-observer CV%'s (P=0.353). The mean intra-observer CV% of the low-KL group was significantly smaller than that for the high-KL group for observer 1 (0.83 vs 1.86%: P=0.025). The segmentation processing times used by the two observers were significantly different (observer 1 vs 2): (mean 49+/-12 vs 33+/-6min) for session 1 and (49+/-8 vs 32+/-8min) for session 2.

CONCLUSION

The semi-automated graph-cuts method allowed us to segment and measure cartilage from high-resolution 3T MR images of the knee with high intra- and inter-observer reproducibility in subjects with varying severity of OA.

Evaluation of a computerized measurement technique for joint alignment before and during periacetabular osteotomy

Periacetabular osteotomy (PAO) is intended to treat a painful dysplastic hip. Manual radiological angle measurements are used to diagnose dysplasia and to define regions of insufficient femoral head coverage for planning PAO. No method has yet been described that recalculates radiological angles as the acetabular bone fragment is reoriented. In this study, we propose a technique for computationally measuring the radiological angles from a joint contact surface model segmented from CT-scan data. Using oblique image slices, we selected the lateral and medial edge of the acetabulum lunate to form a closed, continuous, 3D curve. The joint surface is generated by interpolating the curve, and the radiological angles are measured directly using the 3D surface. This technique was evaluated using CT data for both normal and dysplastic hips. Manual measurements made by three independent observers showed minor discrepancies between the manual observations and the computerized technique. Inter-observer error (mean difference +/- standard deviation) was 0.04 +/- 3.53 degrees for Observer 1; -0.46 +/- 3.13 degrees for Observer 2; and 0.42 +/- 2.73 degrees for Observer 3. The measurement error for the proposed computer method was -1.30 +/- 3.30 degrees . The computerized technique demonstrates sufficient accuracy compared to manual techniques, making it suitable for planning and intraoperative evaluation of radiological metrics for periacetabular osteotomy.

Evaluation of a computerized measurement technique for joint alignment before and during periacetabular osteotomy

Periacetabular osteotomy (PAO) is intended to treat a painful dysplastic hip. Manual radiological angle measurements are used to diagnose dysplasia and to define regions of insufficient femoral head coverage for planning PAO. No method has yet been described that recalculates radiological angles as the acetabular bone fragment is reoriented. In this study, we propose a technique for computationally measuring the radiological angles from a joint contact surface model segmented from CT-scan data. Using oblique image slices, we selected the lateral and medial edge of the acetabulum lunate to form a closed, continuous, 3D curve. The joint surface is generated by interpolating the curve, and the radiological angles are measured directly using the 3D surface. This technique was evaluated using CT data for both normal and dysplastic hips. Manual measurements made by three independent observers showed minor discrepancies between the manual observations and the computerized technique. Inter-observer error (mean difference +/- standard deviation) was 0.04 +/- 3.53 degrees for Observer 1; -0.46 +/- 3.13 degrees for Observer 2; and 0.42 +/- 2.73 degrees for Observer 3. The measurement error for the proposed computer method was -1.30 +/- 3.30 degrees . The computerized technique demonstrates sufficient accuracy compared to manual techniques, making it suitable for planning and intraoperative evaluation of radiological metrics for periacetabular osteotomy.