Segmentation of joint and musculoskeletal tissue in the study of arthritis

Arthritis Foundation/HSS Workshop on Hip Osteoarthritis, Part 2: Detecting Hips at Risk: Early Biomechanical and Structural Mechanisms

Far more publications are available for osteoarthritis of the knee than of the hip. Recognizing this research gap, the Arthritis Foundation (AF), in partnership with the Hospital for Special Surgery (HSS), convened an in-person meeting of thought leaders to review the state of the science of and clinical approaches to hip osteoarthritis. This article summarizes the recommendations gleaned from 5 presentations given in the "early hip osteoarthritis" session of the 2023 Hip Osteoarthritis Clinical Studies Conference, which took place on February 17 and 18, 2023, in New York City. It also summarizes the workgroup recommendations from a small-group discussion on clinical research gaps.

Patch-wise 3D segmentation quality assessment combining reconstruction and regression networks

Purpose

General deep-learning (DL)-based semantic segmentation methods with expert level accuracy may fail in 3D medical image segmentation due to complex tissue structures, lack of large datasets with ground truth, etc. For expeditious diagnosis, there is a compelling need to predict segmentation quality without ground truth. In some medical imaging applications, maintaining the quality of segmentation is crucial to the localized regions where disease is prevalent rather than just globally maintaining high-average segmentation quality. We propose a DL framework to identify regions of segmentation inaccuracies by combining a 3D generative adversarial network (GAN) and a convolutional regression network.

Approach

Our approach is methodologically based on the learned ability to reconstruct the original images identifying the regions of location-specific segmentation failures, in which the reconstruction does not match the underlying original image. We use conditional GAN to reconstruct input images masked by the segmentation results. The regression network is trained to predict the patch-wise Dice similarity coefficient (DSC), conditioned on the segmentation results. The method relies directly on the extracted segmentation related features and does not need to use ground truth during the inference phase to identify erroneous regions in the computed segmentation.

Results

We evaluated the proposed method on two public datasets: osteoarthritis initiative 4D (3D + time) knee MRI (knee-MR) and 3D non-small cell lung cancer CT (lung-CT). For the patch-wise DSC prediction, we observed the mean absolute errors of 0.01 and 0.04 with the independent standard for the knee-MR and lung-CT data, respectively.

Conclusions

This method shows promising results in localizing the erroneous segmentation regions that may aid the downstream analysis of disease diagnosis and prognosis prediction.

Generalizability of Deep Learning Segmentation Algorithms for Automated Assessment of Cartilage Morphology and MRI Relaxometry

BACKGROUND

Deep learning (DL)-based automatic segmentation models can expedite manual segmentation yet require resource-intensive fine-tuning before deployment on new datasets. The generalizability of DL methods to new datasets without fine-tuning is not well characterized.

PURPOSE

Evaluate the generalizability of DL-based models by deploying pretrained models on independent datasets varying by MR scanner, acquisition parameters, and subject population.

STUDY TYPE

Retrospective based on prospectively acquired data.

POPULATION

Overall test dataset: 59 subjects (26 females); Study 1: 5 healthy subjects (zero females), Study 2: 8 healthy subjects (eight females), Study 3: 10 subjects with osteoarthritis (eight females), Study 4: 36 subjects with various knee pathology (10 females).

FIELD STRENGTH/SEQUENCE

A 3-T, quantitative double-echo steady state (qDESS).

ASSESSMENT

Four annotators manually segmented knee cartilage. Each reader segmented one of four qDESS datasets in the test dataset. Two DL models, one trained on qDESS data and another on Osteoarthritis Initiative (OAI)-DESS data, were assessed. Manual and automatic segmentations were compared by quantifying variations in segmentation accuracy, volume, and T2 relaxation times for superficial and deep cartilage.

STATISTICAL TESTS

Dice similarity coefficient (DSC) for segmentation accuracy. Lin's concordance correlation coefficient (CCC), Wilcoxon rank-sum tests, root-mean-squared error-coefficient-of-variation to quantify manual vs. automatic T2 and volume variations. Bland-Altman plots for manual vs. automatic T2 agreement. A P value < 0.05 was considered statistically significant.

RESULTS

DSCs for the qDESS-trained model, 0.79-0.93, were higher than those for the OAI-DESS-trained model, 0.59-0.79. T2 and volume CCCs for the qDESS-trained model, 0.75-0.98 and 0.47-0.95, were higher than respective CCCs for the OAI-DESS-trained model, 0.35-0.90 and 0.13-0.84. Bland-Altman 95% limits of agreement for superficial and deep cartilage T2 were lower for the qDESS-trained model, ±2.4 msec and ±4.0 msec, than the OAI-DESS-trained model, ±4.4 msec and ±5.2 msec.

DATA CONCLUSION

The qDESS-trained model may generalize well to independent qDESS datasets regardless of MR scanner, acquisition parameters, and subject population.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 1.

Diffusion-weighted MRI of total hip arthroplasty for classification of synovial reactions: A pilot study

BACKGROUND

Conventional quantitative diffusion-weighted imaging (DWI) is sensitive to changes in tissue microstructure, but its application to evaluating patients with orthopaedic hardware has generally been limited due to metallic susceptibility artifacts. The apparent diffusion coefficient (ADC) and T2-values from a multi-spectral imaging (MSI) DWI combined with 2D multi-spectral imaging with a 2D periodically rotated overlapping parallel lines with enhanced reconstruction (2D-MSI PROPELLER DWI) based sequence and a MAVRIC based T2 mapping sequence, respectively, may mitigate the artifact and provide additional quantitative information on synovial reactions in individuals with total hip arthroplasty (THA). The aim of this pilot study is to utilize a 2D-MSI PROPELLER DWI and a MAVRIC-based T2 mapping to evaluate ADC and T2-values of synovial reactions in patients with THA.

METHODS

Coronal morphologic MRIs from THA patients underwent evaluation of the synovium and were assigned a synovial classification of 'normal', or 'grouped abnormal' (consisting of sub-groups 'infection', 'polymeric', 'metallosis', 'adverse local tissue reaction' [ALTR], or 'non-specific') and type of synovial reaction present (fluid-like, solid-like, or mixed). Regions of interest (ROIs) were placed in synovial reactions for measurement of ADC and T2-values, obtained from the 2D-MSI PROPELLER DWI and T2-MAVRIC sequences, respectively. A one-way analysis of variance (ANOVA) and Kruskal-Wallis rank sum tests were used to compare the differences in ADC and T2-values across the different synovial reaction classifications. A Kruskal-Wallis test was used to compare the ROI areas for the ADC and T2-values. A principal component analysis (PCA) was performed to evaluate the possible effects of ADC values, size of the ADC ROI, T2-values, and size of the T2 ROI with respect to synovial reaction classification.

RESULTS

Differences of ADC and T2 among the individual synovial reactions were not found. A difference of ADC between 'normal' and 'grouped abnormal' synovial reactions was also not detected even as the ADC area of 'grouped abnormal' synovial reactions were significantly larger (p = 0.02). The 'grouped abnormal' synovial reactions had significantly shorter T2-values than 'normal' synovial reactions (p = 0.02), and that the T2 area of 'grouped abnormal' synovial reactions were significantly larger (p = 0.01). A larger ROI area on the T2-maps was observed in the mixed synovial reaction type as compared to the fluid-like reaction type area (p = 0.01). Heterogeneity was noted in calculated ADC and T2 maps. PCA analysis revealed obvious clustering by the 'normal' and 'grouped abnormal' classifications.

CONCLUSIONS

2D-MSI PROPELLER DWI and MAVRIC-T2 generate quantitative images of periprosthetic tissues within clinically feasible scan times. The combination of derived ADC and T2-values with area of synovial reaction may aid in differentiating normal from abnormal synovial reactions between types of synovial reactions in patients with THA.

Narrative Review of Machine Learning in Rheumatic and Musculoskeletal Diseases for Clinicians and Researchers: Biases, Goals, and Future Directions

There has been rapid growth in the use of artificial intelligence (AI) analytics in medicine in recent years, including in rheumatic and musculoskeletal diseases (RMDs). Such methods represent a challenge to clinicians, patients, and researchers, given the "black box" nature of most algorithms, the unfamiliarity of the terms, and the lack of awareness of potential issues around these analyses. Therefore, this review aims to introduce this subject area in a way that is relevant and meaningful to clinicians and researchers. We hope to provide some insights into relevant strengths and limitations, reporting guidelines, as well as recent examples of such analyses in key areas, with a focus on lessons learned and future directions in diagnosis, phenotyping, prognosis, and precision medicine in RMDs.

Imaging in Osteoarthritis

Osteoarthritis (OA) is the most frequent form of arthritis with major implications on both individual and public health care levels. The field of joint imaging, and particularly magnetic resonance imaging (MRI), has evolved rapidly due to the application of technical advances to the field of clinical research. This narrative review will provide an introduction to the different aspects of OA imaging aimed at an audience of scientists, clinicians, students, industry employees, and others who are interested in OA but who do not necessarily focus on OA. The current role of radiography and recent advances in measuring joint space width will be discussed. The status of cartilage morphology assessment and evaluation of cartilage biochemical composition will be presented. Advances in quantitative three-dimensional morphologic cartilage assessment and semi-quantitative whole-organ assessment of OA will be reviewed. Although MRI has evolved as the most important imaging method used in OA research, other modalities such as ultrasound, computed tomography, and metabolic imaging play a complementary role and will also be discussed.

Entropy and distance maps-guided segmentation of articular cartilage: data from the Osteoarthritis Initiative

PURPOSE

Accurate segmentation of articular cartilage from MR images is crucial for quantitative investigation of pathoanatomical conditions such as osteoarthritis (OA). Recently, deep learning-based methods have made significant progress in hard tissue segmentation. However, it remains a challenge to develop accurate methods for automatic segmentation of articular cartilage.

METHODS

We propose a two-stage method for automatic segmentation of articular cartilage. At the first stage, nnU-Net is employed to get segmentation of both hard tissues and articular cartilage. Based on the initial segmentation, we compute distance maps as well as entropy maps, which encode the uncertainty information about the initial cartilage segmentation. At the second stage, both distance maps and entropy maps are concatenated to the original image. We then crop a sub-volume around the cartilage region based on the initial segmentation, which is used as the input to another nnU-Net for segmentation refinement.

RESULTS

We designed and conducted comprehensive experiments on segmenting three different types of articular cartilage from two datasets, i.e., an in-house dataset consisting of 25 hip MR images and a publicly available dataset from Osteoarthritis Initiative (OAI). Our method achieved an average Dice similarity coefficient (DSC) of [Formula: see text] for the combined hip cartilage, [Formula: see text] for the femoral cartilage and [Formula: see text] for the tibial cartilage, respectively.

CONCLUSION

In summary, we developed a new approach for automatic segmentation of articular cartilage from MR images. Comprehensive experiments conducted on segmenting articular cartilage of the knee and hip joints demonstrated the efficacy of the present approach. Our method achieved equivalent or better results than the state-of-the-art methods.

A Coarse-to-Fine Framework for Automated Knee Bone and Cartilage Segmentation Data from the Osteoarthritis Initiative

Knee osteoarthritis (OA) is a degenerative joint disease that is prevalent in advancing age. The pathology of OA disease is still unclear, and there are no effective interventions that can completely alter the OA disease process. Magnetic resonance (MR) image evaluation is sensitive for depicting early changes of knee OA, and therefore important for early clinical intervention for relieving the symptom. Automated cartilage segmentation based on MR images is a vital step in experimental longitudinal studies to follow-up the patients and prospectively define a new quantitative marker from OA progression. In this paper, we develop a deep learning-based coarse-to-fine approach for automated knee bone, cartilage, and meniscus segmentation with high computational efficiency. The proposed method is evaluated using two-fold cross-validation on 507 MR volumes (81,120 slices) with OA from the Osteoarthritis Initiative (OAI)1 dataset. The mean dice similarity coefficients (DSCs) of femoral bone (FB), tibial bone (TB), femoral cartilage (FC), and tibial cartilage (TC) separately are 99.1%, 98.2%, 90.9%, and 85.8%. The time of segmenting each patient is 12 s, which is fast enough to be used in clinical practice. Our proposed approach may provide an automated toolkit to help computer-aided quantitative analyses of OA images.

Automatic knee cartilage and bone segmentation using multi-stage convolutional neural networks: data from the osteoarthritis initiative

OBJECTIVES

Accurate and efficient knee cartilage and bone segmentation are necessary for basic science, clinical trial, and clinical applications. This work tested a multi-stage convolutional neural network framework for MRI image segmentation.

MATERIALS AND METHODS

Stage 1 of the framework coarsely segments images outputting probabilities of each voxel belonging to the classes of interest: 4 cartilage tissues, 3 bones, 1 background. Stage 2 segments overlapping sub-volumes that include Stage 1 probability maps concatenated to raw image data. Using six fold cross-validation, this framework was tested on two datasets comprising 176 images [88 individuals in the Osteoarthritis Initiative (OAI)] and 60 images (15 healthy young men), respectively.

RESULTS

On the OAI segmentation dataset, the framework produces cartilage segmentation accuracies (Dice similarity coefficient) of 0.907 (femoral), 0.876 (medial tibial), 0.913 (lateral tibial), and 0.840 (patellar). Healthy cartilage accuracies are excellent (femoral = 0.938, medial tibial = 0.911, lateral tibial = 0.930, patellar = 0.955). Average surface distances are less than in-plane resolution. Segmentations take 91 ± 11 s per knee.

DISCUSSION

The framework learns to automatically segment knee cartilage tissues and bones from MR images acquired with two sequences, producing efficient, accurate quantifications at varying disease severities.

Accuracy and longitudinal reproducibility of quantitative femorotibial cartilage measures derived from automated U-Net-based segmentation of two different MRI contrasts: data from the osteoarthritis initiative healthy reference cohort

OBJECTIVE

To evaluate the agreement, accuracy, and longitudinal reproducibility of quantitative cartilage morphometry from 2D U-Net-based automated segmentations for 3T coronal fast low angle shot (corFLASH) and sagittal double echo at steady-state (sagDESS) MRI.

METHODS

2D U-Nets were trained using manual, quality-controlled femorotibial cartilage segmentations available for 92 Osteoarthritis Initiative healthy reference cohort participants from both corFLASH and sagDESS (n = 50/21/21 training/validation/test-set). Cartilage morphometry was computed from automated and manual segmentations for knees from the test-set. Agreement and accuracy were evaluated from baseline visits (dice similarity coefficient: DSC, correlation analysis, systematic offset). The longitudinal reproducibility was assessed from year-1 and -2 follow-up visits (root-mean-squared coefficient of variation, RMSCV%).

RESULTS

Automated segmentations showed high agreement (DSC 0.89-0.92) and high correlations (r ≥ 0.92) with manual ground truth for both corFLASH and sagDESS and only small systematic offsets (≤ 10.1%). The automated measurements showed a similar test-retest reproducibility over 1 year (RMSCV% 1.0-4.5%) as manual measurements (RMSCV% 0.5-2.5%).

DISCUSSION

The 2D U-Net-based automated segmentation method yielded high agreement compared with manual segmentation and also demonstrated high accuracy and longitudinal test-retest reproducibility for morphometric analysis of articular cartilage derived from it, using both corFLASH and sagDESS.

Machine Learning Solutions for Osteoporosis-A Review

Osteoporosis and its clinical consequence, bone fracture, is a multifactorial disease that has been the object of extensive research. Recent advances in machine learning (ML) have enabled the field of artificial intelligence (AI) to make impressive breakthroughs in complex data environments where human capacity to identify high-dimensional relationships is limited. The field of osteoporosis is one such domain, notwithstanding technical and clinical concerns regarding the application of ML methods. This qualitative review is intended to outline some of these concerns and to inform stakeholders interested in applying AI for improved management of osteoporosis. A systemic search in PubMed and Web of Science resulted in 89 studies for inclusion in the review. These covered one or more of four main areas in osteoporosis management: bone properties assessment (n = 13), osteoporosis classification (n = 34), fracture detection (n = 32), and risk prediction (n = 14). Reporting and methodological quality was determined by means of a 12-point checklist. In general, the studies were of moderate quality with a wide range (mode score 6, range 2 to 11). Major limitations were identified in a significant number of studies. Incomplete reporting, especially over model selection, inadequate splitting of data, and the low proportion of studies with external validation were among the most frequent problems. However, the use of images for opportunistic osteoporosis diagnosis or fracture detection emerged as a promising approach and one of the main contributions that ML could bring to the osteoporosis field. Efforts to develop ML-based models for identifying novel fracture risk factors and improving fracture prediction are additional promising lines of research. Some studies also offered insights into the potential for model-based decision-making. Finally, to avoid some of the common pitfalls, the use of standardized checklists in developing and sharing the results of ML models should be encouraged. © 2021 American Society for Bone and Mineral Research (ASBMR).

Texture analysis to differentiate anterior cruciate ligament in patients after surgery with platelet-rich plasma

BACKGROUND

Platelet-rich plasma (PRP) has been used to favor anterior cruciate ligament (ACL) healing after reconstruction surgeries. However, clinical data are still inconclusive and subjective about PRP. Thus, we propose a quantitative method to demonstrate that PRP produced morphological structure changes.

METHODS

Thirty-four patients undergoing ACL reconstruction surgery were evaluated and divided into control group (sixteen patients) without PRP application and experiment group (eighteen patients) with intraoperative application of PRP. Magnetic resonance imaging (MRI) scans were performed 3 months after surgery. We used Matlab® and machine learning (ML) in Orange Canvas® to texture analysis (TA) features extraction. Experienced radiologists delimited the regions of interest (RoIs) in the T2-weighted images. Sixty-two texture parameters were extracted, including gray-level co-occurrence matrix and gray level run length. We used the algorithms logistic regression (LR), naive Bayes (NB), and stochastic gradient descent (SGD).

RESULTS

The accuracy of the classification with NB, LR, and SGD was 83.3%, 75%, 75%, respectively. For the area under the curve, NB, LR, and SGD presented values of 91.7%, 94.4%, 75%, respectively. In clinical evaluations, the groups show similar responses in terms of improvement in pain and increase in the IKDC index (International Knee Documentation Committee) and Lysholm score indices differing only in the assessment of flexion, which presents a significant difference for the group treated with PRP.

CONCLUSIONS

Here, we demonstrated quantitatively that patients who received PRP presented texture changes when compared to the control group. Thus, our findings suggest that PRP interferes with morphological parameters of the ACL.

TRIAL REGISTRATION

Protocol no. CAAE 56164316.6.0000.5411.

Barriers and Enablers for Artificial Intelligence in Dental Diagnostics: A Qualitative Study

The present study aimed to identify barriers and enablers for the implementation of artificial intelligence (AI) in dental, specifically radiographic, diagnostics. Semi-structured phone interviews with dentists and patients were conducted between the end of May and the end of June 2020 (convenience/snowball sampling). A questionnaire developed along the Theoretical Domains Framework (TDF) and the Capabilities, Opportunities and Motivations influencing Behaviors model (COM-B) was used to guide interviews. Mayring's content analysis was employed to point out barriers and enablers. We identified 36 barriers, conflicting themes or enablers, covering nine of the fourteen domains of the TDF and all three determinants of behavior (COM). Both stakeholders emphasized chances and hopes for AI. A range of enablers for implementing AI in dental diagnostics were identified (e.g., the chance for higher diagnostic accuracy, a reduced workload, more comprehensive reporting and better patient-provider communication). Barriers related to reliance on AI and responsibility for medical decisions, as well as the explainability of AI and the related option to de-bug AI applications, emerged. Decision-makers and industry may want to consider these aspects to foster implementation of AI in dentistry.

Automated MRI assessment confirms cartilage thickness modification in patients with knee osteoarthritis: post-hoc analysis from a phase II sprifermin study

BACKGROUND

Sprifermin is under investigation as a potential disease-modifying osteoarthritis drug. Previously, 2-year results from the FORWARD study showed significant dose-dependent modification of cartilage thickness in the total femorotibial joint (TFTJ), medial and lateral femorotibial compartments (MFTC, LFTC), and central medial and lateral TFTJ subregions, by quantitative magnetic resonance imaging (qMRI) using manual segmentation.

OBJECTIVE

To determine whether qMRI findings from FORWARD could be reproduced by an independent method of automated segmentation using an identical dataset and similar anatomical regions in a post-hoc analysis.

METHOD

Cartilage thickness was assessed at baseline and 6, 12, 18 and 24 months, using automated cartilage segmentation with active appearance models, a supervised machine learning method. Images were blinded for treatment and timepoint. Treatment effect was assessed by observed and adjusted changes using a linear mixed model for repeated measures.

RESULTS

Based on automated segmentation, statistically significant, dose-dependent structural modification of cartilage thickness was observed over 2 years with sprifermin vs placebo for TFTJ (overall treatment effect and dose response, both P < 0.001), MFTC (P = 0.004 and P = 0.044), and LFTC (both P < 0.001) regions. For highest dose, in the central medial tibial (P = 0.008), central lateral tibial (P < 0.001) and central lateral femoral (P < 0.001) regions.

CONCLUSIONS

Cartilage thickness assessed by automated segmentation provided a consistent dose response in structural modification compared with manual segmentation. This is the first time that two independent quantification methods of image analysis have reached the same conclusions in an interventional trial, strengthening the conclusions that sprifermin modifies structural progression in knee osteoarthritis.

The optimisation of deep neural networks for segmenting multiple knee joint tissues from MRIs

Automated semantic segmentation of multiple knee joint tissues is desirable to allow faster and more reliable analysis of large datasets and to enable further downstream processing e.g. automated diagnosis. In this work, we evaluate the use of conditional Generative Adversarial Networks (cGANs) as a robust and potentially improved method for semantic segmentation compared to other extensively used convolutional neural network, such as the U-Net. As cGANs have not yet been widely explored for semantic medical image segmentation, we analysed the effect of training with different objective functions and discriminator receptive field sizes on the segmentation performance of the cGAN. Additionally, we evaluated the possibility of using transfer learning to improve the segmentation accuracy. The networks were trained on i) the SKI10 dataset which comes from the MICCAI grand challenge "Segmentation of Knee Images 2010″, ii) the OAI ZIB dataset containing femoral and tibial bone and cartilage segmentations of the Osteoarthritis Initiative cohort and iii) a small locally acquired dataset (Advanced MRI of Osteoarthritis (AMROA) study) consisting of 3D fat-saturated spoiled gradient recalled-echo knee MRIs with manual segmentations of the femoral, tibial and patellar bone and cartilage, as well as the cruciate ligaments and selected peri-articular muscles. The Sørensen-Dice Similarity Coefficient (DSC), volumetric overlap error (VOE) and average surface distance (ASD) were calculated for segmentation performance evaluation. DSC ≥ 0.95 were achieved for all segmented bone structures, DSC ≥ 0.83 for cartilage and muscle tissues and DSC of ≈0.66 were achieved for cruciate ligament segmentations with both cGAN and U-Net on the in-house AMROA dataset. Reducing the receptive field size of the cGAN discriminator network improved the networks segmentation performance and resulted in segmentation accuracies equivalent to those of the U-Net. Pretraining not only increased segmentation accuracy of a few knee joint tissues of the fine-tuned dataset, but also increased the network's capacity to preserve segmentation capabilities for the pretrained dataset. cGAN machine learning can generate automated semantic maps of multiple tissues within the knee joint which could increase the accuracy and efficiency for evaluating joint health.

Image-based biomechanical models of the musculoskeletal system

Finite element modeling is a precious tool for the investigation of the biomechanics of the musculoskeletal system. A key element for the development of anatomically accurate, state-of-the art finite element models is medical imaging. Indeed, the workflow for the generation of a finite element model includes steps which require the availability of medical images of the subject of interest: segmentation, which is the assignment of each voxel of the images to a specific material such as bone and cartilage, allowing for a three-dimensional reconstruction of the anatomy; meshing, which is the creation of the computational mesh necessary for the approximation of the equations describing the physics of the problem; assignment of the material properties to the various parts of the model, which can be estimated for example from quantitative computed tomography for the bone tissue and with other techniques (elastography, T1rho, and T2 mapping from magnetic resonance imaging) for soft tissues. This paper presents a brief overview of the techniques used for image segmentation, meshing, and assessing the mechanical properties of biological tissues, with focus on finite element models of the musculoskeletal system. Both consolidated methods and recent advances such as those based on artificial intelligence are described.

An Open-Source, Vender Agnostic Hardware and Software Pipeline for Integration of Artificial Intelligence in Radiology Workflow

Although machine learning (ML) has made significant improvements in radiology, few algorithms have been integrated into clinical radiology workflow. Complex radiology IT environments and Picture Archiving and Communication System (PACS) pose unique challenges in creating a practical ML schema. However, clinical integration and testing are critical to ensuring the safety and accuracy of ML algorithms. This study aims to propose, develop, and demonstrate a simple, efficient, and understandable hardware and software system for integrating ML models into the standard radiology workflow and PACS that can serve as a framework for testing ML algorithms. A Digital Imaging and Communications in Medicine/Graphics Processing Unit (DICOM/GPU) server and software pipeline was established at a metropolitan county hospital intranet to demonstrate clinical integration of ML algorithms in radiology. A clinical ML integration schema, agnostic to the hospital IT system and specific ML models/frameworks, was implemented and tested with a breast density classification algorithm and prospectively evaluated for time delays using 100 digital 2D mammograms. An open-source clinical ML integration schema was successfully implemented and demonstrated. This schema allows for simple uploading of custom ML models. With the proposed setup, the ML pipeline took an average of 26.52 s per second to process a batch of 100 studies. The most significant processing time delays were noted in model load and study stability times. The code is made available at " http://bit.ly/2Z121hX ". We demonstrated the feasibility to deploy and utilize ML models in radiology without disrupting existing radiology workflow.

Improving Quantitative Magnetic Resonance Imaging Using Deep Learning

Deep learning methods have shown promising results for accelerating quantitative musculoskeletal (MSK) magnetic resonance imaging (MRI) for T2 and T1ρ relaxometry. These methods have been shown to improve musculoskeletal tissue segmentation on parametric maps, allowing efficient and accurate T2 and T1ρ relaxometry analysis for monitoring and predicting MSK diseases. Deep learning methods have shown promising results for disease detection on quantitative MRI with diagnostic performance superior to conventional machine-learning methods for identifying knee osteoarthritis.

Clinical Contrast-Enhanced Computed Tomography With Semi-Automatic Segmentation Provides Feasible Input for Computational Models of the Knee Joint

Computational models can provide information on joint function and risk of tissue failure related to progression of osteoarthritis (OA). Currently, the joint geometries utilized in modeling are primarily obtained via manual segmentation, which is time-consuming and hence impractical for direct clinical application. The aim of this study was to evaluate the applicability of a previously developed semi-automatic method for segmenting tibial and femoral cartilage to serve as input geometry for finite element (FE) models. Knee joints from seven volunteers were first imaged using a clinical computed tomography (CT) with contrast enhancement and then segmented with semi-automatic and manual methods. In both segmentations, knee joint models with fibril-reinforced poroviscoelastic (FRPVE) properties were generated and the mechanical responses of articular cartilage were computed during physiologically relevant loading. The mean differences in the absolute values of maximum principal stress, maximum principal strain, and fibril strain between the models generated from semi-automatic and manual segmentations were <1 MPa, <0.72% and <0.40%, respectively. Furthermore, contact areas, contact forces, average pore pressures, and average maximum principal strains were not statistically different between the models (p >0.05). This semi-automatic method speeded up the segmentation process by over 90% and there were only negligible differences in the results provided by the models utilizing either manual or semi-automatic segmentations. Thus, the presented CT imaging-based segmentation method represents a novel tool for application in FE modeling in the clinic when a physician needs to evaluate knee joint function.

Automated multi-atlas segmentation of gluteus maximus from Dixon and T1-weighted magnetic resonance images

OBJECTIVE

To design, develop and evaluate an automated multi-atlas method for segmentation and volume quantification of gluteus maximus from Dixon and T1-weighted images.

MATERIALS AND METHODS

The multi-atlas segmentation method uses an atlas library constructed from 15 Dixon MRI scans of healthy subjects. A non-rigid registration between each atlas and the target, followed by majority voting label fusion, is used in the segmentation. We propose a region of interest (ROI) to standardize the measurement of muscle bulk. The method was evaluated using the dice similarity coefficient (DSC) and the relative volume difference (RVD) as metrics, for Dixon and T1-weighted target images.

RESULTS

The mean(± SD) DSC was 0.94 ± 0.01 for Dixon images, while 0.93 ± 0.02 for T1-weighted. The RVD between the automated and manual segmentation had a mean(± SD) value of 1.5 ± 4.3% for Dixon and 1.5 ± 4.8% for T1-weighted images. In the muscle bulk ROI, the DSC was 0.95 ± 0.01 and the RVD was 0.6 ± 3.8%.

CONCLUSION

The method allows an accurate fully automated segmentation of gluteus maximus for Dixon and T1-weighted images and provides a relatively accurate volume measurement in shorter times (~ 20 min) than the current gold-standard manual segmentations (2 h). Visual inspection of the segmentation would be required when higher accuracy is needed.

Knee menisci segmentation and relaxometry of 3D ultrashort echo time cones MR imaging using attention U-Net with transfer learning

PURPOSE

To develop a deep learning-based method for knee menisci segmentation in 3D ultrashort echo time (UTE) cones MR imaging, and to automatically determine MR relaxation times, namely the T1, T1ρ , and T 2 ∗ parameters, which can be used to assess knee osteoarthritis (OA).

METHODS

Whole knee joint imaging was performed using 3D UTE cones sequences to collect data from 61 human subjects. Regions of interest (ROIs) were outlined by 2 experienced radiologists based on subtracted T1ρ -weighted MR images. Transfer learning was applied to develop 2D attention U-Net convolutional neural networks for the menisci segmentation based on each radiologist's ROIs separately. Dice scores were calculated to assess segmentation performance. Next, the T1, T1ρ , T 2 ∗ relaxations, and ROI areas were determined for the manual and automatic segmentations, then compared.

RESULTS

The models developed using ROIs provided by 2 radiologists achieved high Dice scores of 0.860 and 0.833, while the radiologists' manual segmentations achieved a Dice score of 0.820. Linear correlation coefficients for the T1, T1ρ , and T 2 ∗ relaxations calculated using the automatic and manual segmentations ranged between 0.90 and 0.97, and there were no associated differences between the estimated average meniscal relaxation parameters. The deep learning models achieved segmentation performance equivalent to the inter-observer variability of 2 radiologists.

CONCLUSION

The proposed deep learning-based approach can be used to efficiently generate automatic segmentations and determine meniscal relaxations times. The method has the potential to help radiologists with the assessment of meniscal diseases, such as OA.

Current applications and future directions of deep learning in musculoskeletal radiology

Deep learning with convolutional neural networks (CNN) is a rapidly advancing subset of artificial intelligence that is ideally suited to solving image-based problems. There are an increasing number of musculoskeletal applications of deep learning, which can be conceptually divided into the categories of lesion detection, classification, segmentation, and non-interpretive tasks. Numerous examples of deep learning achieving expert-level performance in specific tasks in all four categories have been demonstrated in the past few years, although comprehensive interpretation of imaging examinations has not yet been achieved. It is important for the practicing musculoskeletal radiologist to understand the current scope of deep learning as it relates to musculoskeletal radiology. Interest in deep learning from researchers, radiology leadership, and industry continues to increase, and it is likely that these developments will impact the daily practice of musculoskeletal radiology in the near future.

Quantification in Musculoskeletal Imaging Using Computational Analysis and Machine Learning: Segmentation and Radiomics

Although still limited in clinical practice, quantitative analysis is expected to increase the value of musculoskeletal (MSK) imaging. Segmentation aims at isolating the tissues and/or regions of interest in the image and is crucial to the extraction of quantitative features such as size, signal intensity, or image texture. These features may serve to support the diagnosis and monitoring of disease. Radiomics refers to the process of extracting large amounts of features from radiologic images and combining them with clinical, biological, genetic, or any other type of complementary data to build diagnostic, prognostic, or predictive models. The advent of machine learning offers promising prospects for automatic segmentation and integration of large amounts of data. We present commonly used segmentation methods and describe the radiomics pipeline, highlighting the challenges to overcome for adoption in clinical practice. We provide some examples of applications from the MSK literature.

pyKNEEr: An image analysis workflow for open and reproducible research on femoral knee cartilage

Transparent research in musculoskeletal imaging is fundamental to reliably investigate diseases such as knee osteoarthritis (OA), a chronic disease impairing femoral knee cartilage. To study cartilage degeneration, researchers have developed algorithms to segment femoral knee cartilage from magnetic resonance (MR) images and to measure cartilage morphology and relaxometry. The majority of these algorithms are not publicly available or require advanced programming skills to be compiled and run. However, to accelerate discoveries and findings, it is crucial to have open and reproducible workflows. We present pyKNEEr, a framework for open and reproducible research on femoral knee cartilage from MR images. pyKNEEr is written in python, uses Jupyter notebook as a user interface, and is available on GitHub with a GNU GPLv3 license. It is composed of three modules: 1) image preprocessing to standardize spatial and intensity characteristics; 2) femoral knee cartilage segmentation for intersubject, multimodal, and longitudinal acquisitions; and 3) analysis of cartilage morphology and relaxometry. Each module contains one or more Jupyter notebooks with narrative, code, visualizations, and dependencies to reproduce computational environments. pyKNEEr facilitates transparent image-based research of femoral knee cartilage because of its ease of installation and use, and its versatility for publication and sharing among researchers. Finally, due to its modular structure, pyKNEEr favors code extension and algorithm comparison. We tested our reproducible workflows with experiments that also constitute an example of transparent research with pyKNEEr, and we compared pyKNEEr performances to existing algorithms in literature review visualizations. We provide links to executed notebooks and executable environments for immediate reproducibility of our findings.

Automated postoperative muscle assessment of hip arthroplasty patients using multimodal imaging joint segmentation

BACKGROUND AND OBJECTIVE

In patients treated with hip arthroplasty, the muscular condition and presence of inflammatory reactions are assessed using magnetic resonance imaging (MRI). As MRI lacks contrast for bony structures, computed tomography (CT) is preferred for clinical evaluation of bone tissue and orthopaedic surgical planning. Combining the complementary information of MRI and CT could improve current clinical practice for diagnosis, monitoring and treatment planning. In particular, the different contrast of these modalities could help better quantify the presence of fatty infiltration to characterise muscular condition and assess implant failure. In this work, we combine CT and MRI for joint bone and muscle segmentation and we propose a novel Intramuscular Fat Fraction estimation method for the quantification of muscle atrophy.

METHODS

Our multimodal framework is able to segment healthy and pathological musculoskeletal structures as well as implants, and develops into three steps. First, input images are pre-processed to improve the low quality of clinically acquired images and to reduce the noise associated with metal artefact. Subsequently, CT and MRI are non-linearly aligned using a novel approach which imposes rigidity constraints on bony structures to ensure realistic deformation. Finally, taking advantage of a multimodal atlas we created for this task, a multi-atlas based segmentation delineates pelvic bones, abductor muscles and implants on both modalities jointly. From the obtained segmentation, a multimodal estimation of the Intramuscular Fat Fraction can be automatically derived.

RESULTS

Evaluation of the segmentation in a leave-one-out cross-validation study on 22 hip sides resulted in an average Dice score of 0.90 for skeletal and 0.84 for muscular structures. Our multimodal Intramuscular Fat Fraction was benchmarked on 27 different cases against a standard radiological score, showing stronger association than a single modality approach in a one-way ANOVA F-test analysis.

CONCLUSIONS

The proposed framework represents a promising tool to support image analysis in hip arthroplasty, being robust to the presence of implants and associated image artefacts. By allowing for the automated extraction of a muscle atrophy imaging biomarker, it could quantitatively inform the decision-making process about patient's management.

Artificial Intelligence in Musculoskeletal Imaging: Current Status and Future Directions

OBJECTIVE. The objective of this article is to show how artificial intelligence (AI) has impacted different components of the imaging value chain thus far as well as to describe its potential future uses. CONCLUSION. The use of AI has the potential to greatly enhance every component of the imaging value chain. From assessing the appropriateness of imaging orders to helping predict patients at risk for fracture, AI can increase the value that musculoskeletal imagers provide to their patients and to referring clinicians by improving image quality, patient centricity, imaging efficiency, and diagnostic accuracy.

Impact of the rise of artificial intelligence in radiology: What do radiologists think?

PURPOSE

The purpose of this study was to assess the perception, knowledge, wishes and expectations of a sample of French radiologists towards the rise of artificial intelligence (AI) in radiology.

MATERIAL AND METHOD

A general data protection regulation-compliant electronic survey was sent by e-mail to the 617 radiologists registered in the French departments of Nord and Pas-de-Calais (93 radiology residents and 524 senior radiologists), from both public and private institutions. The survey included 42 questions focusing on AI in radiology, and data were collected between January 16^th and January 31^st, 2019. The answers were analyzed together by a senior radiologist and a radiology resident.

RESULTS

A total of 70 radiology residents and 200 senior radiologists participated to the survey, which corresponded to a response rate of 43.8% (270/617). One hundred ninety-eight radiologists (198/270; 73.3%) estimated they had received insufficient previous information on AI. Two hundred and fifty-five respondents (255/270; 94.4%) would consider attending a generic continuous medical education in this field and 187 (187/270; 69.3%) a technically advanced training on AI. Two hundred and fourteen respondents (214/270; 79.3%) thought that AI will have a positive impact on their future practice. The highest expectations were the lowering of imaging-related medical errors (219/270; 81%), followed by the lowering of the interpretation time of each examination (201/270; 74.4%) and the increase in the time spent with patients (141/270; 52.2%).

CONCLUSION

While respondents had the feeling of receiving insufficient previous information on AI, they are willing to improve their knowledge and technical skills on this field. They share an optimistic view and think that AI will have a positive impact on their future practice. A lower risk of imaging-related medical errors and an increase in the time spent with patients are among their main expectations.

SUSAN: segment unannotated image structure using adversarial network

PURPOSE

To describe and evaluate a segmentation method using joint adversarial and segmentation convolutional neural network to achieve accurate segmentation using unannotated MR image datasets.

THEORY AND METHODS

A segmentation pipeline was built using joint adversarial and segmentation network. A convolutional neural network technique called cycle-consistent generative adversarial network (CycleGAN) was applied as the core of the method to perform unpaired image-to-image translation between different MR image datasets. A joint segmentation network was incorporated into the adversarial network to obtain additional functionality for semantic segmentation. The fully automated segmentation method termed as SUSAN was tested for segmenting bone and cartilage on 2 clinical knee MR image datasets using images and annotated segmentation masks from an online publicly available knee MR image dataset. The segmentation results were compared using quantitative segmentation metrics with the results from a supervised U-Net segmentation method and 2 registration methods. The Wilcoxon signed-rank test was used to evaluate the value difference of quantitative metrics between different methods.

RESULTS

The proposed method SUSAN provided high segmentation accuracy with results comparable to the supervised U-Net segmentation method (most quantitative metrics having P > 0.05) and significantly better than a multiatlas registration method (all quantitative metrics having P < 0.001) and a direct registration method (all quantitative metrics having P< 0.0001) for the clinical knee image datasets. SUSAN also demonstrated the applicability for segmenting knee MR images with different tissue contrasts.

CONCLUSION

SUSAN performed rapid and accurate tissue segmentation for multiple MR image datasets without the need for sequence specific segmentation annotation. The joint adversarial and segmentation network and training strategy have promising potential applications in medical image segmentation.

Translation of morphological and functional musculoskeletal imaging

In an effort to develop quantitative biomarkers for degenerative joint disease and fill the void that exists for diagnosing, monitoring, and assessing the extent of whole joint degeneration, the past decade has been marked by a greatly increased role of noninvasive imaging. This coupled with recent advances in image processing and deep learning opens new possibilities for promising quantitative techniques. The clinical translation of quantitative imaging was previously hampered by tedious non-scalable and subjective image analysis. Osteoarthritis (OA) diagnosis using X-rays can be automated by the use of deep learning models and pilot studies showed feasibility of using similar techniques to reliably segment multiple musculoskeletal tissues and detect and stage the severity of morphological abnormalities in magnetic resonance imaging (MRI). Automation and more advanced feature extraction techniques have applications on larger more heterogeneous samples. Analyses based on voxel based relaxometry have shown local patterns in relaxation time elevations and local correlations with outcome variables. Bone cartilage interactions are also enhanced by the analysis of three-dimensional bone morphology and the potential for the assessment of metabolic activity with simultaneous Positron Emission Tomography (PET)/MR systems. Novel techniques in image processing and deep learning are augmenting imaging to be a source of quantitative and reliable data and new multidimensional analytics allow us to exploit the interactions of data from various sources. In this review, we aim to summarize recent advances in quantitative imaging, the application of image processing and deep learning techniques to study knee and hip OA. ©2018 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res XX:XX-XX, 2018.

Method for Segmentation of Knee Articular Cartilages Based on Contrast-Enhanced CT Images

Segmentation of contrast-enhanced computed tomography (CECT) images enables quantitative evaluation of morphology of articular cartilage as well as the significance of the lesions. Unfortunately, automatic segmentation methods for CECT images are currently lacking. Here, we introduce a semiautomated technique to segment articular cartilage from in vivo CECT images of human knee. The segmented cartilage geometries of nine knee joints, imaged using a clinical CT-scanner with an intra-articular contrast agent, were compared with manual segmentations from CT and magnetic resonance (MR) images. The Dice similarity coefficients (DSCs) between semiautomatic and manual CT segmentations were 0.79-0.83 and sensitivity and specificity values were also high (0.76-0.86). When comparing semiautomatic and manual CT segmentations, mean cartilage thicknesses agreed well (intraclass correlation coefficient = 0.85-0.93); the difference in thickness (mean ± SD) was 0.27 ± 0.03 mm. Differences in DSC, when MR segmentations were compared with manual and semiautomated CT segmentations, were statistically insignificant. Similarly, differences in volume were not statistically significant between manual and semiautomatic CT segmentations. Semiautomation decreased the segmentation time from 450 ± 190 to 42 ± 10 min per joint. The results reveal that the proposed technique is fast and reliable for segmentation of cartilage. Importantly, this is the first study presenting semiautomated segmentation of cartilage from CECT images of human knee joint with minimal user interaction.

Use of 2D U-Net Convolutional Neural Networks for Automated Cartilage and Meniscus Segmentation of Knee MR Imaging Data to Determine Relaxometry and Morphometry

Purpose To analyze how automatic segmentation translates in accuracy and precision to morphology and relaxometry compared with manual segmentation and increases the speed and accuracy of the work flow that uses quantitative magnetic resonance (MR) imaging to study knee degenerative diseases such as osteoarthritis (OA). Materials and Methods This retrospective study involved the analysis of 638 MR imaging volumes from two data cohorts acquired at 3.0 T: (a) spoiled gradient-recalled acquisition in the steady state T1ρ-weighted images and (b) three-dimensional (3D) double-echo steady-state (DESS) images. A deep learning model based on the U-Net convolutional network architecture was developed to perform automatic segmentation. Cartilage and meniscus compartments were manually segmented by skilled technicians and radiologists for comparison. Performance of the automatic segmentation was evaluated on Dice coefficient overlap with the manual segmentation, as well as by the automatic segmentations' ability to quantify, in a longitudinally repeatable way, relaxometry and morphology. Results The models produced strong Dice coefficients, particularly for 3D-DESS images, ranging between 0.770 and 0.878 in the cartilage compartments to 0.809 and 0.753 for the lateral meniscus and medial meniscus, respectively. The models averaged 5 seconds to generate the automatic segmentations. Average correlations between manual and automatic quantification of T1ρ and T2 values were 0.8233 and 0.8603, respectively, and 0.9349 and 0.9384 for volume and thickness, respectively. Longitudinal precision of the automatic method was comparable with that of the manual one. Conclusion U-Net demonstrates efficacy and precision in quickly generating accurate segmentations that can be used to extract relaxation times and morphologic characterization and values that can be used in the monitoring and diagnosis of OA. © RSNA, 2018 Online supplemental material is available for this article.

Current Applications and Future Impact of Machine Learning in Radiology

Recent advances and future perspectives of machine learning techniques offer promising applications in medical imaging. Machine learning has the potential to improve different steps of the radiology workflow including order scheduling and triage, clinical decision support systems, detection and interpretation of findings, postprocessing and dose estimation, examination quality control, and radiology reporting. In this article, the authors review examples of current applications of machine learning and artificial intelligence techniques in diagnostic radiology. In addition, the future impact and natural extension of these techniques in radiology practice are discussed.

A Novel Method to Predict Knee Osteoarthritis Progression on MRI Using Machine Learning Methods

This paper explored the hidden biomedical information from knee magnetic resonance (MR) images for osteoarthritis (OA) prediction. We have computed the cartilage damage index (CDI) information from 36 informative locations on tibiofemoral cartilage compartment from 3-D MR imaging and used principal component analysis (PCA) analysis to process the feature set. Four machine learning methods (artificial neural network (ANN), support vector machine, random forest, and naïve Bayes) were employed to predict the progression of OA, which was measured by the change of Kellgren and Lawrence (KL) grade, Joint Space Narrowing on Medial compartment (JSM) grade, and Joint Space Narrowing on Lateral compartment (JSL) grade. To examine the different effects of medial and lateral informative locations, we have divided the 36-D feature set into a 18-D medial feature set and a 18-D lateral feature set and run the experiment on four classifiers separately. Experiment results showed that the medial feature set generated better prediction performance than the lateral feature set, while using the total 36-D feature set generated the best. PCA analysis is helpful in feature space reduction and performance improvement. For KL grade prediction, the best performance was achieved by ANN with AUC = 0.761 and F-measure = 0.714. For JSM grade prediction, the best performance was achieved by random forest with AUC = 0.785 and F-measure = 0.743, while for JSL grade prediction, the best performance was achieved by ANN with AUC = 0.695 and F-measure = 0.796. As experiment results showing that the informative locations on medial compartment provide more distinguishing features than informative locations on the lateral compartment, it could be considered to select more points from the medial compartment while reducing the number of points from the lateral compartment to improve clinical CDI design.

Inter- and intra-observer variability of an anatomical landmark-based, manual segmentation method by MRI for the assessment of skeletal muscle fat content and area in subjects from the general population

OBJECTIVES

Changes in skeletal muscle composition, such as fat content and mass, may exert unique metabolic and musculoskeletal risks; however, the reproducibility of their assessment is unknown. We determined the variability of the assessment of skeletal muscle fat content and area by MRI in a population-based sample.

METHODS

A random sample from a prospective, community-based cohort study (KORA-FF4) was included. Skeletal muscle fat content was quantified as proton-density fat fraction (PDFF) and area as cross-sectional area (CSA) in multi-echo Dixon sequences (TR 8.90 ms, six echo times, flip angle 4°) by a standardized, anatomical landmark-based, manual skeletal muscle segmentation at level L3 vertebra by two independent observers. Reproducibility was assessed by intraclass correlation coefficients (ICC), scatter and Bland-Altman plots.

RESULTS

From 50 subjects included (mean age 56.1 ± 8.8 years, 60.0% males, mean body mass index 28.3 ± 5.2) 2'400 measurements were obtained. Interobserver agreement was excellent for all muscle compartments (PDFF: ICC0.99, CSA: ICC0.98) with only minor absolute and relative differences (-0.2 ± 0.5%, 31 ± 44.7 mm²; -2.6 ± 6.4% and 2.7 ± 3.9%, respectively). Intra-observer reproducibility was similarly excellent (PDFF: ICC1.0, 0.0 ± 0.4%, 0.4%; CSA: ICC1.0, 5.5 ± 25.3 mm², 0.5%, absolute and relative differences, respectively). All agreement was independent of age, gender, body mass index, body height and visceral adipose tissue (ICC0.96-1.0). Furthermore, PDFF reproducibility was independent of CSA (ICC0.93-0.99).  Conclusions:  Quantification of skeletal muscle fat content and area by MRI using an anatomical landmark-based, manual skeletal muscle segmentation is highly reproducible. Advances in knowledge: An anatomical landmark-based, manual skeletal muscle segmentation provides high reproducibility of skeletal muscle fat content and area and may therefore serve as a robust proxy for myosteatosis and sarcopenia in large cohort studies.

Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging

PURPOSE

To describe and evaluate a new fully automated musculoskeletal tissue segmentation method using deep convolutional neural network (CNN) and three-dimensional (3D) simplex deformable modeling to improve the accuracy and efficiency of cartilage and bone segmentation within the knee joint.

METHODS

A fully automated segmentation pipeline was built by combining a semantic segmentation CNN and 3D simplex deformable modeling. A CNN technique called SegNet was applied as the core of the segmentation method to perform high resolution pixel-wise multi-class tissue classification. The 3D simplex deformable modeling refined the output from SegNet to preserve the overall shape and maintain a desirable smooth surface for musculoskeletal structure. The fully automated segmentation method was tested using a publicly available knee image data set to compare with currently used state-of-the-art segmentation methods. The fully automated method was also evaluated on two different data sets, which include morphological and quantitative MR images with different tissue contrasts.

RESULTS

The proposed fully automated segmentation method provided good segmentation performance with segmentation accuracy superior to most of state-of-the-art methods in the publicly available knee image data set. The method also demonstrated versatile segmentation performance on both morphological and quantitative musculoskeletal MR images with different tissue contrasts and spatial resolutions.

CONCLUSION

The study demonstrates that the combined CNN and 3D deformable modeling approach is useful for performing rapid and accurate cartilage and bone segmentation within the knee joint. The CNN has promising potential applications in musculoskeletal imaging. Magn Reson Med 79:2379-2391, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Segmentation of hip cartilage in compositional magnetic resonance imaging: A fast, accurate, reproducible, and clinically viable semi-automated methodology

Manual segmentation is a significant obstacle in the analysis of compositional MRI for clinical decision-making and research. Our aim was to produce a fast, accurate, reproducible, and clinically viable semi-automated method for segmentation of hip MRI. We produced a semi-automated segmentation method for cartilage segmentation of hip MRI sequences consisting of a two step process: (i) fully automated hierarchical partitioning of the data volume generated using a bespoke segmentation approach applied recursively, followed by (ii) user selection of the regions of interest using a region editor. This was applied to dGEMRIC scans at 3T taken from a prospective longitudinal study of individuals considered at high-risk of developing osteoarthritis (SibKids) which were also manually segmented for comparison. Fourteen hips were segmented both manually and using our semi-automated method. Per hip, processing time for semi-automated and manual segmentation was 10-15, and 60-120 min, respectively. Accuracy and Dice similarity coefficient (DSC) for the comparison of semi-automated and manual segmentations was 0.9886 and 0.8803, respectively. Intra-observer and inter-observer reproducibility of the semi-automated segmentation method gave an accuracy of 0.9997 and 0.9991, and DSC of 0.9726 and 0.9354, respectively. We have proposed a fast, accurate, reproducible, and clinically viable semi-automated method for segmentation of hip MRI sequences. This enables accurate anatomical and biochemical measurements to be obtained quickly and reproducibly. This is the first such method that shows clinical applicability, and could have large ramifications for the use of compositional MRI in research and clinically. © 2018 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res.

Muscle Atrophy Measurement as Assessment Method for Low Back Pain Patients

Low back pain is one of the most common pain disorders defined as pain, muscle tension, or stiffness localized below the costal margin and above the inferior gluteal folds, sometimes with accompanying leg pain. The meaning of the symptomatic atrophy of paraspinal muscles and some pelvic muscles has been proved. Nowadays, a need for new diagnostic tools for specific examination of low back pain patients is posited, and it has been proposed that magnetic resonance imaging assessment toward muscle atrophy may provide some additional information enabling the subclassification of that group of patients.

WRIST: A WRist Image Segmentation Toolkit for carpal bone delineation from MRI

Segmentation of the carpal bones from 3D imaging modalities, such as magnetic resonance imaging (MRI), is commonly performed for in vivo analysis of wrist morphology, kinematics, and biomechanics. This crucial task is typically carried out manually and is labor intensive, time consuming, subject to high inter- and intra-observer variability, and may result in topologically incorrect surfaces. We present a method, WRist Image Segmentation Toolkit (WRIST), for 3D semi-automated, rapid segmentation of the carpal bones of the wrist from MRI. In our method, the boundary of the bones were iteratively found using prior known anatomical constraints and a shape-detection level set. The parameters of the method were optimized using a training dataset of 48 manually segmented carpal bones and evaluated on 112 carpal bones which included both healthy participants without known wrist conditions and participants with thumb basilar osteoarthritis (OA). Manual segmentation by two expert human observers was considered as a reference. On the healthy subject dataset we obtained a Dice overlap of 93.0 ± 3.8, Jaccard Index of 87.3 ± 6.2, and a Hausdorff distance of 2.7 ± 3.4 mm, while on the OA dataset we obtained a Dice overlap of 90.7 ± 8.6, Jaccard Index of 83.0 ± 10.6, and a Hausdorff distance of 4.0 ± 4.4 mm. The short computational time of 20.8 s per bone (or 5.1 s per bone in the parallelized version) and the high agreement with the expert observers gives WRIST the potential to be utilized in musculoskeletal research.

Application of a semi-automatic cartilage segmentation method for biomechanical modeling of the knee joint

Manual segmentation of articular cartilage from knee joint 3D magnetic resonance images (MRI) is a time consuming and laborious task. Thus, automatic methods are needed for faster and reproducible segmentations. In the present study, we developed a semi-automatic segmentation method based on radial intensity profiles to generate 3D geometries of knee joint cartilage which were then used in computational biomechanical models of the knee joint. Six healthy volunteers were imaged with a 3T MRI device and their knee cartilages were segmented both manually and semi-automatically. The values of cartilage thicknesses and volumes produced by these two methods were compared. Furthermore, the influences of possible geometrical differences on cartilage stresses and strains in the knee were evaluated with finite element modeling. The semi-automatic segmentation and 3D geometry construction of one knee joint (menisci, femoral and tibial cartilages) was approximately two times faster than with manual segmentation. Differences in cartilage thicknesses, volumes, contact pressures, stresses, and strains between segmentation methods in femoral and tibial cartilage were mostly insignificant (p > 0.05) and random, i.e. there were no systematic differences between the methods. In conclusion, the devised semi-automatic segmentation method is a quick and accurate way to determine cartilage geometries; it may become a valuable tool for biomechanical modeling applications with large patient groups.

Tissue segmentation: a crucial tool for quantitative MRI and visualization of anatomical structures

Automatic or semi-automatic segmentation of tissue types or organs is well established for X-ray-based computed tomography, with its fixed grey-scale and tissue classes with well-established ranges of Hounsfield units. MRI is much more powerful with regard to soft tissue contrast and quantitative assessment of tissue properties (e.g., perfusion, diffusion, fat content), but the principle of signal generation and recording in MRI leads to inherent problems if simple threshold based segmentation procedures are applied. In this editorial in the special issue of MAGMA on tissue segmentation, a number of relevant methodical, scientific, and clinical aspects of reliable tissue segmentation using data recording by MRI are reported and discussed.

Longitudinal study using voxel-based relaxometry: Association between cartilage T1ρ and T2 and patient reported outcome changes in hip osteoarthritis

PURPOSE

To study the local distribution of hip cartilage T_1ρ and T₂ relaxation times and their association with changes in patient reported outcome measures (PROMs) using a fully automatic, local, and unbiased method in subjects with and without hip osteoarthritis (OA).

MATERIALS AND METHODS

The 3 Tesla MRI studies of the hip were obtained for 37 healthy controls and 16 subjects with radiographic hip OA. The imaging protocol included a three-dimensional (3D) SPGR sequence and a combined 3D T_1ρ and T₂ sequence. Quantitative cartilage analysis was compared between a traditional region of interest (ROI)-based method and a fully automatic voxel-based relaxometry (VBR) method. Additionally, VBR was used to assess local T_1ρ and T₂ differences between subjects with and without OA, and to evaluate the association between T_1ρ and T₂ and 18-month changes PROMs.

RESULTS

Results for the two methods were consistent in the acetabular (R = 0.79; coefficients of variation [CV] = 2.9%) and femoral cartilage (R = 0.90; CV = 2.6%). VBR revealed local patterns of T_1ρ and T₂ elevation in OA subjects, particularly in the posterosuperior acetabular cartilage (T_1ρ : P = 0.02; T₂ : P = 0.038). Overall, higher T_1ρ and T₂ values at baseline, particularly in the anterosuperior acetabular cartilage (T_1ρ : Rho = -0.42; P = 0.002; T₂ : Rho = -0.44; P = 0.002), were associated with worsening PROMS at 18-month follow-up.

CONCLUSION

VBR is an accurate and robust method for quantitative MRI analysis in hip cartilage. VBR showed the capability to detect local variations in T_1ρ and T₂ values in subjects with and without osteoarthritis, and voxel based correlations demonstrated a regional dependence between baseline T_1ρ and T₂ values and changes in PROMs.

LEVEL OF EVIDENCE

1 J. MAGN. RESON. IMAGING 2017;45:1523-1533.