The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset

Reproducibility of Quantitative Double-Echo Steady-State T2 Mapping of Knee Cartilage

BACKGROUND

Cartilage T2 can detect joints at risk of developing osteoarthritis. The quantitative double-echo steady state (qDESS) sequence is attractive for knee cartilage T2 mapping because of its acquisition time of under 5 minutes. Understanding the reproducibility errors associated with qDESS T2 is essential to profiling the technical performance of this biomarker.

PURPOSE

To examine the combined acquisition and segmentation reproducibility of knee cartilage qDESS T2 using two different regional analysis schemes: 1) manual segmentation of subregions loaded during common activities and 2) automatic subregional segmentation.

STUDY TYPE

Prospective.

SUBJECTS

11 uninjured participants (age: 28 ± 3 years; 8 (73%) female).

FIELD STRENGTH/SEQUENCE

3-T, qDESS.

ASSESSMENT

Test-retest T2 maps were acquired twice on the same day and with a 1-week interval between scans. For each acquisition, average cartilage T2 was calculated in four manually segmented regions encompassing tibiofemoral contact areas during common activities and 12 automatically segmented regions from the deep-learning open-source framework for musculoskeletal MRI analysis (DOSMA) encompassing medial and lateral anterior, central, and posterior tibiofemoral regions. Test-retest T2 values from matching regions were used to evaluate reproducibility.

STATISTICAL TESTS

Coefficients of variation (%CV), root-mean-square-average-CV (%RMSA-CV), and intraclass correlation coefficients (ICCs) assessed test-retest T2 reproducibility. The median of test-retest standard deviations was used for T2 precision. Bland-Altman (BA) analyses examined test-retest biases. The smallest detectable difference (SDD) was defined as the BA limit of agreement of largest magnitude. Significance was accepted for P < 0.05.

RESULTS

All cartilage regions across both segmentation schemes demonstrated intraday and interday qDESS T2 CVs and RMSA-CVs of ≤5%. T2 ICC values >0.75 were observed in the majority of regions but were more variable in interday tibial comparisons. Test-retest T2 precision was <1.3 msec. The T2 SDD was 3.8 msec.

DATA CONCLUSION

Excellent CV and RMSA-CV reproducibility may suggest that qDESS T2 increases or decreases >5% (3.8 msec) could represent changes to cartilage composition.

LEVEL OF EVIDENCE: 2

TECHNICAL EFFICACY

Stage 2.

Artificial intelligence to analyze magnetic resonance imaging in rheumatology

Rheumatic disorders present a global health challenge, marked by inflammation and damage to joints, bones, and connective tissues. Accurate, timely diagnosis and appropriate management are crucial for favorable patient outcomes. Magnetic resonance imaging (MRI) has become indispensable in rheumatology, but interpretation remains laborious and variable. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), offers a means to improve and advance MRI analysis. This review examines current AI applications in rheumatology MRI analysis, addressing diagnostic support, disease classification, activity assessment, and progression monitoring. AI demonstrates promise, with high sensitivity, specificity, and accuracy, achieving or surpassing expert performance. The review also discusses clinical implementation challenges and future research directions to enhance rheumatic disease diagnosis and management.

30 Years of MRI-based cartilage & bone morphometry in knee osteoarthritis: From correlation to clinical trials

OBJECTIVE

The first publication on morphometric analysis of articular cartilage using magnetic resonance imaging (MRI) in 1994 set the scene for a game change in osteoarthritis (OA) research. The current review highlights milestones in cartilage and bone morphometry, summarizing the rapid progress made in imaging, its application to understanding joint (patho-)physiology, and its use in interventional clinical trials.

METHODS

Based on a Pubmed search of articles from 1994 to 2023, the authors subjectively selected representative work illustrating important steps in the development or application of magnetic resonance-based cartilage and bone morphometry, with a focus on studies in humans, and on the knee. Research on OA-pathophysiology is addressed only briefly, given length constraints. Compositional and semi-quantitative assessment are not covered here.

RESULTS

The selected articles are presented in historical order as well as by content. We review progress in the technical aspects of image acquisition, segmentation and analysis, advances in understanding tissue growth, physiology, function, and adaptation, and a selection of clinical trials examining the efficacy of interventions on knee cartilage and bone. A perspective is provided of how lessons learned may be applied to future research and clinical management.

CONCLUSIONS

Over the past 30 years, MRI-based morphometry of cartilage and bone has contributed to a paradigm shift in understanding articular tissue physiology and OA pathophysiology, and to the development of new treatment strategies. It is likely that these technologies will continue to play a key role in the development and (accelerated) approval of therapy, potentially targeted to different OA phenotypes.

A perspective on the evolution of semi-quantitative MRI assessment of osteoarthritis: Past, present and future

OBJECTIVE

This perspective describes the evolution of semi-quantitative (SQ) magnetic resonance imaging (MRI) in characterizing structural tissue pathologies in osteoarthritis (OA) imaging research over the last 30 years.

METHODS

Authors selected representative articles from a PubMed search to illustrate key steps in SQ MRI development, validation, and application. Topics include main scoring systems, reading techniques, responsiveness, reliability, technical considerations, and potential impact of artificial intelligence (AI).

RESULTS

Based on original research published between 1993 and 2023, this article introduces available scoring systems, including but not limited to Whole-Organ Magnetic Resonance Imaging Score (WORMS) as the first system for whole-organ assessment of the knee and the now commonly used MRI Osteoarthritis Knee Score (MOAKS) instrument. Specific systems for distinct OA subtypes or applications have been developed as well as MRI scoring instruments for other joints such as the hip, the fingers or thumb base. SQ assessment has proven to be valid, reliable, and responsive, aiding OA investigators in understanding the natural history of the disease and helping to detect response to treatment. AI may aid phenotypic characterization in the future. SQ MRI assessment's role is increasing in eligibility and safety evaluation in knee OA clinical trials.

CONCLUSIONS

Evidence supports the validity, reliability, and responsiveness of SQ MRI assessment in understanding structural aspects of disease onset and progression. SQ scoring has helped explain associations between structural tissue damage and clinical manifestations, as well as disease progression. While AI may support human readers to more efficiently perform SQ assessment in the future, its current application in clinical trials still requires validation and regulatory approval.

A reproducibility study of knee cartilage volume and thickness values derived by fully automatic segmentation based on three-dimensional dual-echo in steady state data from 1.5 T and 3 T magnetic resonance imaging

OBJECTIVE

To evaluate the repeatability of cartilage volume and thickness values at 1.5 T MRI using a fully automatic cartilage segmentation method and reproducibility of the method between 1.5 T and 3 T data.

METHODS

The study included 20 knee joints from 10 healthy subjects with each subject having undergone double-knee MRI. All knees were scanned at 1.5 T and 3 T MR scanners using a three-dimensional (3D) high-resolution dual-echo in steady state (DESS) sequence. Cartilage volume and thickness of 21 subregions were quantified using a fully automatic cartilage segmentation research application (MR Chondral Health, version 3.0, Siemens Healthcare, Erlangen, Germany). The volume and thickness values derived from fully automatically computed segmentation masks were analyzed for the scan-rescan data from the same volunteers. The accuracy of the automatic segmentation of the cartilage in 1.5 T images was evaluated by the dice similarity coefficient (DSC) and Hausdorff distance (HD) using the manually corrected segmentation as a reference. The volume and thickness values calculated from 1.5 T and 3 T were also compared.

RESULTS

No statistically significant differences were found for cartilage thickness or volume across all subregions between the scan-rescanned data at 1.5 T (P > 0.05). The mean DSC between the fully automatic and manually corrected knee cartilage segmentation contours at 1.5 T was 0.9946. The average value of HD was 2.41 mm. Overall, there was no statistically significant difference in the cartilage volume or thickness in most-subregions between the two field strengths (P > 0.05) except for the medial region of femur and tibia. Bland-Altman plot and intraclass correlation coefficient (ICC) showed high consistency between results obtained based on same and different scanning sequences.

CONCLUSION

The cartilage segmentation software had high repeatability for DESS images obtained from the same device. In addition, the overall reproducibility of the images obtained from equipment of two different field strengths was satisfactory.

Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: a multimodal explainable artificial intelligence approach

Current risk scores using clinical risk factors for predicting ischemic heart disease (IHD) events-the leading cause of global mortality-have known limitations and may be improved by imaging biomarkers. While body composition (BC) imaging biomarkers derived from abdominopelvic computed tomography (CT) correlate with IHD risk, they are impractical to measure manually. Here, in a retrospective cohort of 8139 contrast-enhanced abdominopelvic CT examinations undergoing up to 5 years of follow-up, we developed multimodal opportunistic risk assessment models for IHD by automatically extracting BC features from abdominal CT images and integrating these with features from each patient's electronic medical record (EMR). Our predictive methods match and, in some cases, outperform clinical risk scores currently used in IHD risk assessment. We provide clinical interpretability of our model using a new method of determining tissue-level contributions from CT along with weightings of EMR features contributing to IHD risk. We conclude that such a multimodal approach, which automatically integrates BC biomarkers and EMR data, can enhance IHD risk assessment and aid primary prevention efforts for IHD. To further promote research, we release the Opportunistic L3 Ischemic heart disease (OL3I) dataset, the first public multimodal dataset for opportunistic CT prediction of IHD.

Unsupervised domain adaptation for automated knee osteoarthritis phenotype classification

Background

Osteoarthritis (OA) is a global healthcare problem. The increasing population of OA patients demands a greater bandwidth of imaging and diagnostics. It is important to provide automatic and objective diagnostic techniques to address this challenge. This study demonstrates the utility of unsupervised domain adaptation (UDA) for automated OA phenotype classification.

Methods

We collected 318 and 960 three-dimensional double-echo steady-state magnetic resonance images from the Osteoarthritis Initiative (OAI) dataset as the source dataset for phenotype cartilage/meniscus and subchondral bone, respectively. Fifty three-dimensional turbo spin echo (TSE)/fast spin echo (FSE) MR images from our institute were collected as the target datasets. For each patient, the degree of knee OA was initially graded according to the MRI Knee Osteoarthritis Knee Score before being converted to binary OA phenotype labels. The proposed four-step UDA pipeline included (I) pre-processing, which involved automatic segmentation and region-of-interest cropping; (II) source classifier training, which involved pre-training a convolutional neural network (CNN) encoder for phenotype classification using the source dataset; (III) target encoder adaptation, which involved unsupervised adjustment of the source encoder to the target encoder using both the source and target datasets; and (IV) target classifier validation, which involved statistical analysis of the classification performance evaluated by the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity and accuracy. We compared our model on the target data with the source pre-trained model and the model trained with the target data from scratch.

Results

For phenotype cartilage/meniscus, our model has the best performance out of the three models, giving 0.90 [95% confidence interval (CI): 0.79-1.02] of the AUROC score, while the other two model show 0.52 (95% CI: 0.13-0.90) and 0.76 (95% CI: 0.53-0.98). For phenotype subchondral bone, our model gave 0.75 (95% CI: 0.56-0.94) at AUROC, which has a close performance of the source pre-trained model (0.76, 95% CI: 0.55-0.98), and better than the model trained from scratch on the target dataset only (0.53, 95% CI: 0.33-0.73).

Conclusions

By utilising a large, high-quality source dataset for training, the proposed UDA approach enhances the performance of automated OA phenotype classification for small target datasets. As a result, our technique enables improved downstream analysis of locally collected datasets with a small sample size.

Imaging of early-stage osteoarthritis: the needs and challenges for diagnosis and classification

In an effort to boost the development of new management strategies for OA, there is currently a shift in focus towards the diagnosis and treatment of early-stage OA. It is important to distinguish diagnosis from classification of early-stage OA. Diagnosis takes place in clinical practice, whereas classification is a process to stratify participants with OA in clinical research. For both purposes, there is an important opportunity for imaging, especially with MRI. The needs and challenges differ for early-stage OA diagnosis versus classification. Although it fulfils the need of high sensitivity and specificity for making a correct diagnosis, implementation of MRI in clinical practice is challenged by long acquisition times and high costs. For classification in clinical research, more advanced MRI protocols can be applied, such as quantitative, contrast-enhanced, or hybrid techniques, as well as advanced image analysis methods including 3D morphometric assessments of joint tissues and artificial intelligence approaches. It is necessary to follow a step-wise and structured approach that comprises, technical validation, biological validation, clinical validation, qualification, and cost-effectiveness, before new imaging biomarkers can be implemented in clinical practice or clinical research.

Deep learning applications in osteoarthritis imaging

Deep learning (DL) is one of the most exciting new areas in medical imaging. This article will provide a review of current applications of DL in osteoarthritis (OA) imaging, including methods used for cartilage lesion detection, OA diagnosis, cartilage segmentation, and OA risk assessment. DL techniques have been shown to have similar diagnostic performance as human readers for detecting and grading cartilage lesions within the knee on MRI. A variety of DL methods have been developed for detecting and grading the severity of knee OA and various features of knee OA on X-rays using standardized classification systems with diagnostic performance similar to human readers. Multiple DL approaches have been described for fully automated segmentation of cartilage and other knee tissues and have achieved higher segmentation accuracy than currently used methods with substantial reductions in segmentation times. Various DL models analyzing baseline X-rays and MRI have been developed for OA risk assessment. These models have shown high diagnostic performance for predicting a wide variety of OA outcomes, including the incidence and progression of radiographic knee OA, the presence and progression of knee pain, and future total knee replacement. The preliminary results of DL applications in OA imaging have been encouraging. However, many DL techniques require further technical refinement to maximize diagnostic performance. Furthermore, the generalizability of DL approaches needs to be further investigated in prospective studies using large image datasets acquired at different institutions with different imaging hardware before they can be implemented in clinical practice and research studies.

Quantitative measurement of cartilage morphology in osteoarthritis: current knowledge and future directions

Quantitative measures of cartilage morphology ("cartilage morphometry") extracted from high resolution 3D magnetic resonance imaging (MRI) sequences have been shown to be sensitive to osteoarthritis (OA)-related change and also to treatment interventions. Cartilage morphometry is therefore nowadays widely used as outcome measure for observational studies and randomized interventional clinical trials. The objective of this narrative review is to summarize the current status of cartilage morphometry in OA research, to provide insights into aspects relevant for the design of future studies and clinical trials, and to give an outlook on future developments. It covers the aspects related to the acquisition of MRIs suitable for cartilage morphometry, the analysis techniques needed for deriving quantitative measures from the MRIs, the quality assurance required for providing reliable cartilage measures, and the appropriate participant recruitment criteria for the enrichment of study cohorts with knees likely to show structural progression. Finally, it provides an overview over recent clinical trials that relied on cartilage morphometry as a structural outcome measure for evaluating the efficacy of disease-modifying OA drugs (DMOAD).

Large-Scale Analysis of Meniscus Morphology as Risk Factor for Knee Osteoarthritis

OBJECTIVE

Although it is established that structural damage of the meniscus is linked to knee osteoarthritis (OA) progression, the predisposition to future development of OA because of geometric meniscal shapes is plausible and unexplored. This study aims to identify common variations in meniscal shape and determine their relationships to tissue morphology, OA onset, and longitudinal changes in cartilage thickness.

METHODS

A total of 4,790 participants from the Osteoarthritis Initiative data set were studied. A statistical shape model was developed for the meniscus, and shape scores were evaluated between a control group and an OA incidence group. Shape features were then associated with cartilage thickness changes over 8 years to localize the relationship between meniscus shape and cartilage degeneration.

RESULTS

Seven shape features between the medial and lateral menisci were identified to be different between knees that remain normal and those that develop OA. These include length-width ratios, horn lengths, root attachment angles, and concavity. These "at-risk" shapes were linked to unique cartilage thickness changes that suggest a relationship between meniscus geometry and decreased tibial coverage and rotational imbalances. Additionally, strong associations were found between meniscal shape and demographic subpopulations, future tibial extrusion, and meniscal and ligamentous tears.

CONCLUSION

This automatic method expanded upon known meniscus characteristics that are associated with the onset of OA and discovered novel shape features that have yet to be investigated in the context of OA risk.

MRI-based T1rho and T2 cartilage compositional imaging in osteoarthritis: what have we learned and what is needed to apply it clinically and in a trial setting?

Cartilage MRI-based T1rho and T2 compositional measurements have been developed to characterize cartilage matrix quality and diagnose cartilage damage before irreversible defects are found, allowing intervention at an early, potentially reversible disease stage. Over the last 2 decades, this technology was investigated in numerous studies and was validated using specimen studies and arthroscopy; and longitudinal studies documented its ability to predict progression of degenerative disease and radiographic osteoarthritis (OA). While T1rho and T2 measurements have shown promise in early disease stages, several hurdles have been encountered to apply this technology clinically. These include (i) challenges with cartilage segmentation, (ii) long image acquisition times, (iii) a lack of standardization of imaging, and (iv) an absence of reference databases and definitions of abnormal cut-off values. Progress has been made by developing deep-learning based automatic cartilage segmentation and faster imaging methods, enabling the feasibility of T1rho and T2 imaging for clinical and scientific trial applications. Also, the Radiological Society of North America (RSNA) Quantitative Imaging Biomarker Alliance mechanism was used to establish standardized profiles for compositional T1rho and T2 imaging, and multi-center feasibility testing is work in progress. The last hurdles are the development of reference databases and establishing a definition of normal versus abnormal cartilage T1rho and T2 values. Finally, effective treatments for prevention and slowing progression of OA are required in order to establish T1rho and T2 as imaging biomarkers for initiating and monitoring therapies, analogous to the role of dual X-ray absorptiometry (DXA) bone mineral density measurements in the management of osteoporosis. KEY POINTS: • T1rho and T2 cartilage measurements have been validated in characterizing cartilage degenerative change using histology and arthroscopy as a reference. • They have also been shown to predict progression of cartilage degeneration and incidence of radiographic OA. • Advances have been made to facilitate clinical and trial application of T1rho and T2 by improved standardization of imaging and by establishing deep learning-based automatic cartilage segmentation. • Effective treatments with disease-modifying OA specific drugs may establish T1rho and T2 cartilage compositional measurements as biomarkers to initiate and monitor treatment.

Quantitative bone marrow lesion, meniscus, and synovitis measurement: current status

Imaging plays a pivotal role in osteoarthritis research, particularly in epidemiological and clinical trials of knee osteoarthritis (KOA), with the ultimate goal being the development of an effective drug treatment for future prevention or cessation of disease. Imaging assessment methods can be semi-quantitative, quantitative, or a combination, with quantitative methods usually relying on software to assist. The software generally attempts image segmentation (outlining of relevant structures). New techniques using artificial intelligence (AI) or deep learning (DL) are currently a frequent topic of research. This review article provides an overview of the literature to date, focusing primarily on the current status of quantitative software-based assessment techniques of KOA using magnetic resonance (MR) imaging. We will concentrate on the imaging evaluation of three specific structural imaging biomarkers: bone marrow lesions (BMLs), meniscus, and synovitis consisting of effusion synovitis (ES) and Hoffa's synovitis (HS). A brief clinical and imaging background review of osteoarthritis evaluation, particularly relating to these three structural markers, is provided as well as a general summary of the software methods. A summary of the literature with respect to each KOA assessment method will be presented overall as well as with respect to each specific biomarker individually. Novel techniques, as well as future goals and directions using quantitative imaging assessment, will be discussed.

The Stanford Medicine data science ecosystem for clinical and translational research

Objective

To describe the infrastructure, tools, and services developed at Stanford Medicine to maintain its data science ecosystem and research patient data repository for clinical and translational research.

Materials and Methods

The data science ecosystem, dubbed the Stanford Data Science Resources (SDSR), includes infrastructure and tools to create, search, retrieve, and analyze patient data, as well as services for data deidentification, linkage, and processing to extract high-value information from healthcare IT systems. Data are made available via self-service and concierge access, on HIPAA compliant secure computing infrastructure supported by in-depth user training.

Results

The Stanford Medicine Research Data Repository (STARR) functions as the SDSR data integration point, and includes electronic medical records, clinical images, text, bedside monitoring data and HL7 messages. SDSR tools include tools for electronic phenotyping, cohort building, and a search engine for patient timelines. The SDSR supports patient data collection, reproducible research, and teaching using healthcare data, and facilitates industry collaborations and large-scale observational studies.

Discussion

Research patient data repositories and their underlying data science infrastructure are essential to realizing a learning health system and advancing the mission of academic medical centers. Challenges to maintaining the SDSR include ensuring sufficient financial support while providing researchers and clinicians with maximal access to data and digital infrastructure, balancing tool development with user training, and supporting the diverse needs of users.

Conclusion

Our experience maintaining the SDSR offers a case study for academic medical centers developing data science and research informatics infrastructure.

Selecting the best optimizers for deep learning-based medical image segmentation

Purpose

The goal of this work is to explore the best optimizers for deep learning in the context of medical image segmentation and to provide guidance on how to design segmentation networks with effective optimization strategies.

Approach

Most successful deep learning networks are trained using two types of stochastic gradient descent (SGD) algorithms: adaptive learning and accelerated schemes. Adaptive learning helps with fast convergence by starting with a larger learning rate (LR) and gradually decreasing it. Momentum optimizers are particularly effective at quickly optimizing neural networks within the accelerated schemes category. By revealing the potential interplay between these two types of algorithms [LR and momentum optimizers or momentum rate (MR) in short], in this article, we explore the two variants of SGD algorithms in a single setting. We suggest using cyclic learning as the base optimizer and integrating optimal values of learning rate and momentum rate. The new optimization function proposed in this work is based on the Nesterov accelerated gradient optimizer, which is more efficient computationally and has better generalization capabilities compared to other adaptive optimizers.

Results

We investigated the relationship of LR and MR under an important problem of medical image segmentation of cardiac structures from MRI and CT scans. We conducted experiments using the cardiac imaging dataset from the ACDC challenge of MICCAI 2017, and four different architectures were shown to be successful for cardiac image segmentation problems. Our comprehensive evaluations demonstrated that the proposed optimizer achieved better results (over a 2% improvement in the dice metric) than other optimizers in the deep learning literature with similar or lower computational cost in both single and multi-object segmentation settings.

Conclusions

We hypothesized that the combination of accelerated and adaptive optimization methods can have a drastic effect in medical image segmentation performances. To this end, we proposed a new cyclic optimization method (Cyclic Learning/Momentum Rate) to address the efficiency and accuracy problems in deep learning-based medical image segmentation. The proposed strategy yielded better generalization in comparison to adaptive optimizers.

MR-Imaging in Osteoarthritis: Current Standard of Practice and Future Outlook

Osteoarthritis (OA) is a common degenerative joint disease that affects millions of people worldwide. Magnetic resonance imaging (MRI) has emerged as a powerful tool for the evaluation and monitoring of OA due to its ability to visualize soft tissues and bone with high resolution. This review aims to provide an overview of the current state of MRI in OA, with a special focus on the knee, including protocol recommendations for clinical and research settings. Furthermore, new developments in the field of musculoskeletal MRI are highlighted in this review. These include compositional MRI techniques, such as T2 mapping and T1rho imaging, which can provide additional important information about the biochemical composition of cartilage and other joint tissues. In addition, this review discusses semiquantitative joint assessment based on MRI findings, which is a widely used method for evaluating OA severity and progression in the knee. We analyze the most common scoring methods and discuss potential benefits. Techniques to reduce acquisition times and the potential impact of deep learning in MR imaging for OA are also discussed, as these technological advances may impact clinical routine in the future.

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.

Improving Data-Efficiency and Robustness of Medical Imaging Segmentation Using Inpainting-Based Self-Supervised Learning

We systematically evaluate the training methodology and efficacy of two inpainting-based pretext tasks of context prediction and context restoration for medical image segmentation using self-supervised learning (SSL). Multiple versions of self-supervised U-Net models were trained to segment MRI and CT datasets, each using a different combination of design choices and pretext tasks to determine the effect of these design choices on segmentation performance. The optimal design choices were used to train SSL models that were then compared with baseline supervised models for computing clinically-relevant metrics in label-limited scenarios. We observed that SSL pretraining with context restoration using 32 × 32 patches and Poission-disc sampling, transferring only the pretrained encoder weights, and fine-tuning immediately with an initial learning rate of 1 × 10-3 provided the most benefit over supervised learning for MRI and CT tissue segmentation accuracy (p < 0.001). For both datasets and most label-limited scenarios, scaling the size of unlabeled pretraining data resulted in improved segmentation performance. SSL models pretrained with this amount of data outperformed baseline supervised models in the computation of clinically-relevant metrics, especially when the performance of supervised learning was low. Our results demonstrate that SSL pretraining using inpainting-based pretext tasks can help increase the robustness of models in label-limited scenarios and reduce worst-case errors that occur with supervised learning.

The KNee OsteoArthritis Prediction (KNOAP2020) challenge: An image analysis challenge to predict incident symptomatic radiographic knee osteoarthritis from MRI and X-ray images

OBJECTIVES

The KNee OsteoArthritis Prediction (KNOAP2020) challenge was organized to objectively compare methods for the prediction of incident symptomatic radiographic knee osteoarthritis within 78 months on a test set with blinded ground truth.

DESIGN

The challenge participants were free to use any available data sources to train their models. A test set of 423 knees from the Prevention of Knee Osteoarthritis in Overweight Females (PROOF) study consisting of magnetic resonance imaging (MRI) and X-ray image data along with clinical risk factors at baseline was made available to all challenge participants. The ground truth outcomes, i.e., which knees developed incident symptomatic radiographic knee osteoarthritis (according to the combined ACR criteria) within 78 months, were not provided to the participants. To assess the performance of the submitted models, we used the area under the receiver operating characteristic curve (ROCAUC) and balanced accuracy (BACC).

RESULTS

Seven teams submitted 23 entries in total. A majority of the algorithms were trained on data from the Osteoarthritis Initiative. The model with the highest ROCAUC (0.64 (95% confidence interval (CI): 0.57-0.70)) used deep learning to extract information from X-ray images combined with clinical variables. The model with the highest BACC (0.59 (95% CI: 0.52-0.65)) ensembled three different models that used automatically extracted X-ray and MRI features along with clinical variables.

CONCLUSION

The KNOAP2020 challenge established a benchmark for predicting incident symptomatic radiographic knee osteoarthritis. Accurate prediction of incident symptomatic radiographic knee osteoarthritis is a complex and still unsolved problem requiring additional investigation.

Democratization of deep learning for segmenting cartilage from MRIs of human knees: Application to data from the osteoarthritis initiative

In this study, we aimed to democratize access to convolutional neural networks (CNN) for segmenting cartilage volumes, generating state-of-the-art results for specialized, real-world applications in hospitals and research. Segmentation of cross-sectional and/or longitudinal magnetic resonance (MR) images of articular cartilage facilitates both clinical management of joint damage/disease and fundamental research. Manual delineation of such images is a time-consuming task susceptible to high intra- and interoperator variability and prone to errors. Thus, enabling reliable and efficient analyses of MRIs of cartilage requires automated segmentation of cartilage volumes. Two main limitations arise in the development of hospital- or population-specific deep learning (DL) models for image segmentation: specialized knowledge and specialized hardware. We present a relatively easy and accessible implementation of a DL model to automatically segment MRIs of human knees with state-of-the-art accuracy. In representative examples, we trained CNN models in 6-8 h and obtained results quantitatively comparable to state-of-the-art for every anatomical structure. We established and evaluated our methods using two publicly available MRI data sets originating from the Osteoarthritis Initiative, Stryker Imorphics, and Zuse Institute Berlin (ZIB), as representative test cases. We use Google Colabfor editing and adapting the Python codes and selecting the runtime environment leveraging high-performance graphical processing units. We designed our solution for novice users to apply to any data set with relatively few adaptations requiring only basic programming skills. To facilitate the adoption of our methods, we provide a complete guideline for using our methods and software, as well as the software tools themselves. Clinical significance: We establish and detail methods that clinical personal can apply to create their own DL models without specialized knowledge of DL nor specialized hardware/infrastructure and obtain results comparable with the state-of-the-art to facilitate both clinical management of joint damage/disease and fundamental research.

Latest advancements in imaging techniques in OA

The osteoarthritis (OA) research community has been advocating a shift from radiography-based screening criteria and outcome measures in OA clinical trials to a magnetic resonance imaging (MRI)-based definition of eligibility and endpoint. For conventional morphological MRI, various semiquantitative evaluation tools are available. We have lately witnessed a remarkable technological advance in MRI techniques, including compositional/physiologic imaging and automated quantitative analyses of articular and periarticular structures. More recently, additional technologies were introduced, including positron emission tomography (PET)-MRI, weight-bearing computed tomography (CT), photon-counting spectral CT, shear wave elastography, contrast-enhanced ultrasound, multiscale X-ray phase contrast imaging, and spectroscopic photoacoustic imaging of cartilage. On top of these, we now live in an era in which artificial intelligence is increasingly utilized in medicine. Osteoarthritis imaging is no exception. Successful implementation of artificial intelligence (AI) will hopefully improve the workflow of radiologists, as well as the level of precision and reproducibility in the interpretation of images.

Advanced MR Imaging for Knee Osteoarthritis: A Review on Local and Brain Effects

Knee osteoarthritis is one of the leading causes of chronic disability worldwide and is a significant social and economic burden on healthcare systems; hence it has become essential to develop methods to identify patients at risk for developing knee osteoarthritis at an early stage. Standard morphological MRI sequences are focused mostly on alterations seen in advanced stages of osteoarthritis. However, they possess low sensitivity for early, subtle, and potentially reversible changes of the degenerative process. In this review, we have summarized the state of the art with regard to innovative quantitative MRI techniques that exploit objective and quantifiable biomarkers to identify subtle alterations that occur in early stages of osteoarthritis in knee cartilage before any morphological alteration occurs and to capture potential effects on the brain. These novel MRI imaging tools are believed to have great potential for improving the current standard of care, but further research is needed to address limitations before these compositional techniques can be robustly applied in research and clinical settings.

Deep learning-based segmentation of knee MRI for fully automatic subregional morphological assessment of cartilage tissues: Data from the Osteoarthritis Initiative

Morphological changes in knee cartilage subregions are valuable imaging-based biomarkers for understanding progression of osteoarthritis, and they are typically detected from magnetic resonance imaging (MRI). So far, accurate segmentation of cartilage has been done manually. Deep learning approaches show high promise in automating the task; however, they lack clinically relevant evaluation. We introduce a fully automatic method for segmentation and subregional assessment of articular cartilage, and evaluate its predictive power in context of radiographic osteoarthritis progression. Two data sets of 3D double-echo steady-state (DESS) MRI derived from the Osteoarthritis Initiative were used: first, n = 88; second, n = 600, 0-/12-/24-month visits. Our method performed deep learning-based segmentation of knee cartilage tissues, their subregional division via multi-atlas registration, and extraction of subregional volume and thickness. The segmentation model was developed and assessed on the first data set. Subsequently, on the second data set, the morphological measurements from our and the prior methods were analyzed in correlation and agreement, and, eventually, by their discriminative power of radiographic osteoarthritis progression over 12 and 24 months, retrospectively. The segmentation model showed very high correlation (r > 0.934) and agreement (mean difference < 116 mm³ ) in volumetric measurements with the reference segmentations. Comparison of our and manual segmentation methods yielded r = 0.845-0.973 and mean differences = 262-501 mm³ for weight-bearing cartilage volume, and r = 0.770-0.962 and mean differences = 0.513-1.138 mm for subregional cartilage thickness. With regard to osteoarthritis progression, our method found most of the significant associations identified using the manual segmentation method, for both 12- and 24-month subregional cartilage changes. The method may be effectively applied in osteoarthritis progression studies to extract cartilage-related imaging biomarkers.

Validating a Semi-Automated Technique for Segmenting Femoral Articular Cartilage on Ultrasound Images

OBJECTIVE

To validate a semi-automated technique to segment ultrasound-assessed femoral cartilage without compromising segmentation accuracy to a traditional manual segmentation technique in participants with an anterior cruciate ligament injury (ACL).

DESIGN

We recruited 27 participants with a primary unilateral ACL injury at a pre-operative clinic visit. One investigator performed a transverse suprapatellar ultrasound scan with the participant's ACL injured knee in maximum flexion. Three femoral cartilage ultrasound images were recorded. A single expert reader manually segmented the femoral cartilage cross-sectional area in each image. In addition, we created a semi-automatic program to segment the cartilage using a random walker-based method. We quantified the average cartilage thickness and echo-intensity for the manual and semi-automated segmentations. Intraclass correlation coefficients (ICC_2,k) and Bland-Altman plots were used to validate the semi-automated technique to the manual segmentation for assessing average cartilage thickness and echo-intensity. A dice correlation coefficient was used to quantify the overlap between the segmentations created with the semi-automated and manual techniques.

RESULTS

For average cartilage thickness, there was excellent reliability (ICC_2,k = 0.99) and a small mean difference (+0.8%) between the manual and semi-automated segmentations. For average echo-intensity, there was excellent reliability (ICC_2,k = 0.97) and a small mean difference (-2.5%) between the manual and semi-automated segmentations. The average dice correlation coefficient between the manual segmentation and semi-automated segmentation was 0.90, indicating high overlap between techniques.

CONCLUSIONS

Our novel semi-automated segmentation technique is a valid method that requires less technical expertise and time than manual segmentation in patients after ACL injury.

Challenges in ensuring the generalizability of image quantitation methods for MRI

Image quantitation methods including quantitative MRI, multiparametric MRI, and radiomics offer great promise for clinical use. However, many of these methods have limited clinical adoption, in part due to issues of generalizability, that is, the ability to translate methods and models across institutions. Researchers can assess generalizability through measurement of repeatability and reproducibility, thus quantifying different aspects of measurement variance. In this article, we review the challenges to ensuring repeatability and reproducibility of image quantitation methods as well as present strategies to minimize their variance to enable wider clinical implementation. We present possible solutions for achieving clinically acceptable performance of image quantitation methods and briefly discuss the impact of minimizing variance and achieving generalizability towards clinical implementation and adoption.

Utilization of Mid-Thigh Magnetic Resonance Imaging to Predict Lean Body Mass and Knee Extensor Strength in Obese Adults

Purpose

To train and test a machine learning model to automatically measure mid-thigh muscle cross-sectional area (CSA) to provide rapid estimation of appendicular lean mass (ALM) and predict knee extensor torque of obese adults.

Methods

Obese adults [body mass index (BMI) = 30–40 kg/m², age = 30–50 years] were enrolled for this study. Participants received full-body dual-energy X-ray absorptiometry (DXA), mid-thigh MRI, and completed knee extensor and flexor torque assessments via isokinetic dynamometer. Manual segmentation of mid-thigh CSA was completed for all MRI scans. A convolutional neural network (CNN) was created based on the manual segmentation to develop automated quantification of mid-thigh CSA. Relationships were established between the automated CNN values to the manual CSA segmentation, ALM via DXA, knee extensor, and flexor torque.

Results

A total of 47 obese patients were enrolled in this study. Agreement between the CNN-automated measures and manual segmentation of mid-thigh CSA was high (>0.90). Automated measures of mid-thigh CSA were strongly related to the leg lean mass (r = 0.86, p < 0.001) and ALM (r = 0.87, p < 0.001). Additionally, mid-thigh CSA was strongly related to knee extensor strength (r = 0.76, p < 0.001) and moderately related to knee flexor strength (r = 0.48, p = 0.002).

Conclusion

CNN-measured mid-thigh CSA was accurate compared to the manual segmented values from the mid-thigh. These values were strongly predictive of clinical measures of ALM and knee extensor torque. Mid-thigh MRI may be utilized to accurately estimate clinical measures of lean mass and function in obese adults.

Studying osteoarthritis with artificial intelligence applied to magnetic resonance imaging

The 3D nature and soft-tissue contrast of MRI makes it an invaluable tool for osteoarthritis research, by facilitating the elucidation of disease pathogenesis and progression. The recent increasing employment of MRI has certainly been stimulated by major advances that are due to considerable investment in research, particularly related to artificial intelligence (AI). These AI-related advances are revolutionizing the use of MRI in clinical research by augmenting activities ranging from image acquisition to post-processing. Automation is key to reducing the long acquisition times of MRI, conducting large-scale longitudinal studies and quantitatively defining morphometric and other important clinical features of both soft and hard tissues in various anatomical joints. Deep learning methods have been used recently for multiple applications in the musculoskeletal field to improve understanding of osteoarthritis. Compared with labour-intensive human efforts, AI-based methods have advantages and potential in all stages of imaging, as well as post-processing steps, including aiding diagnosis and prognosis. However, AI-based methods also have limitations, including the arguably limited interpretability of AI models. Given that the AI community is highly invested in uncovering uncertainties associated with model predictions and improving their interpretability, we envision future clinical translation and progressive increase in the use of AI algorithms to support clinicians in optimizing patient care.

Osteoarthritis year in review 2021: imaging

PURPOSE

To provide a narrative review of original articles on imaging of osteoarthritis (OA) published between January 1, 2020 and March 31, 2021, with a special focus on imaging of inflammation, imaging of bone, cartilage and bone-cartilage interactions, imaging of peri-articular tissues, imaging scoring methods for OA, and artificial intelligence (AI) applied to OA imaging.

METHODS

The Embase, Pubmed, Medline, Cochrane databases were searched for original research articles in the English language on human, in vivo, imaging of OA published between January 1, 2020 and March 31, 2021. Search terms related to osteoarthritis combined with all imaging modalities and artificial intelligence were applied. A selection of articles reporting on one of the focus topics was discussed further.

RESULTS

The search resulted in 651 articles, of which 214 were deemed relevant to human OA imaging. Among the articles included, the knee joint (69%) and magnetic resonance imaging (MRI) (52%) were the predominant anatomical area and imaging modality studied. There were also a substantial number of papers (n = 46) reporting on AI applications in the field of OA imaging.

CONCLUSION

Imaging continues to play an important role in the assessment of OA. Recent advances in OA imaging include quantitative, non-contrast, and hybrid imaging techniques for improved characterization of multiple tissue processes in OA. In addition, an increasing effort in AI techniques is undertaken to enhance OA imaging acquisition and analysis.

Automated segmentation of articular disc of the temporomandibular joint on magnetic resonance images using deep learning

Temporomandibular disorders are typically accompanied by a number of clinical manifestations that involve pain and dysfunction of the masticatory muscles and temporomandibular joint. The most important subgroup of articular abnormalities in patients with temporomandibular disorders includes patients with different forms of articular disc displacement and deformation. Here, we propose a fully automated articular disc detection and segmentation system to support the diagnosis of temporomandibular disorder on magnetic resonance imaging. This system uses deep learning-based semantic segmentation approaches. The study included a total of 217 magnetic resonance images from 10 patients with anterior displacement of the articular disc and 10 healthy control subjects with normal articular discs. These images were used to evaluate three deep learning-based semantic segmentation approaches: our proposed convolutional neural network encoder-decoder named 3DiscNet (Detection for Displaced articular DISC using convolutional neural NETwork), U-Net, and SegNet-Basic. Of the three algorithms, 3DiscNet and SegNet-Basic showed comparably good metrics (Dice coefficient, sensitivity, and positive predictive value). This study provides a proof-of-concept for a fully automated deep learning-based segmentation methodology for articular discs on magnetic resonance images, and obtained promising initial results, indicating that the method could potentially be used in clinical practice for the assessment of temporomandibular disorders.

Clinical validation of the use of prototype software for automatic cartilage segmentation to quantify knee cartilage in volunteers

Background

The cartilage segmentation algorithms make it possible to accurately evaluate the morphology and degeneration of cartilage. There are some factors (location of cartilage subregions, hydrarthrosis and cartilage degeneration) that may influence the accuracy of segmentation. It is valuable to evaluate and compare the accuracy and clinical value of volume and mean T2* values generated directly from automatic knee cartilage segmentation with those from manually corrected results using prototype software.

Method

Thirty-two volunteers were recruited, all of whom underwent right knee magnetic resonance imaging examinations. Morphological images were obtained using a three-dimensional (3D) high-resolution Double-Echo in Steady-State (DESS) sequence, and biochemical images were obtained using a two-dimensional T2* mapping sequence. Cartilage score criteria ranged from 0 to 2 and were obtained using the Whole-Organ Magnetic Resonance Imaging Score (WORMS). The femoral, patellar, and tibial cartilages were automatically segmented and divided into subregions using the post-processing prototype software. Afterwards, all the subregions were carefully checked and manual corrections were done where needed. The dice coefficient correlations for each subregion by the automatic segmentation were calculated.

Results

Cartilage volume after applying the manual correction was significantly lower than automatic segmentation (P < 0.05). The percentages of the cartilage volume change for each subregion after manual correction were all smaller than 5%. In all the subregions, the mean T2* relaxation time within manual corrected subregions was significantly lower than in regions after automatic segmentation (P < 0.05). The average time for the automatic segmentation of the whole knee was around 6 min, while the average time for manual correction of the whole knee was around 27 min.

Conclusions

Automatic segmentation of cartilage volume has a high dice coefficient correlation and it can provide accurate quantitative information about cartilage efficiently without individual bias.

Advances in knowledge: Magnetic resonance imaging is the most promising method to detect structural changes in cartilage tissue. Unfortunately, due to the structure and morphology of the cartilages obtaining accurate segmentations can be problematic. There are some factors (location of cartilage subregions, hydrarthrosis and cartilage degeneration) that may influence segmentation accuracy. We therefore assessed the factors that influence segmentations error.

Cross-Cohort Automatic Knee MRI Segmentation With Multi-Planar U-Nets

Background

Segmentation of medical image volumes is a time‐consuming manual task. Automatic tools are often tailored toward specific patient cohorts, and it is unclear how they behave in other clinical settings.

Purpose

To evaluate the performance of the open‐source Multi‐Planar U‐Net (MPUnet), the validated Knee Imaging Quantification (KIQ) framework, and a state‐of‐the‐art two‐dimensional (2D) U‐Net architecture on three clinical cohorts without extensive adaptation of the algorithms.

Study Type

Retrospective cohort study.

Subjects

A total of 253 subjects (146 females, 107 males, ages 57 ± 12 years) from three knee osteoarthritis (OA) studies (Center for Clinical and Basic Research [CCBR], Osteoarthritis Initiative [OAI], and Prevention of OA in Overweight Females [PROOF]) with varying demographics and OA severity (64/37/24/53/2 scans of Kellgren and Lawrence [KL] grades 0–4).

Field Strength/Sequence

0.18 T, 1.0 T/1.5 T, and 3 T sagittal three‐dimensional fast‐spin echo T1w and dual‐echo steady‐state sequences.

Assessment

All models were fit without tuning to knee magnetic resonance imaging (MRI) scans with manual segmentations from three clinical cohorts. All models were evaluated across KL grades.

Statistical Tests

Segmentation performance differences as measured by Dice coefficients were tested with paired, two‐sided Wilcoxon signed‐rank statistics with significance threshold α = 0.05.

Results

The MPUnet performed superior or equal to KIQ and 2D U‐Net on all compartments across three cohorts. Mean Dice overlap was significantly higher for MPUnet compared to KIQ and U‐Net on CCBR (0.83±0.04 vs. 0.81±0.06 and 0.82±0.05), significantly higher than KIQ and U‐Net OAI (0.86±0.03 vs. 0.84±0.04 and 0.85±0.03), and not significantly different from KIQ while significantly higher than 2D U‐Net on PROOF (0.78±0.07 vs. 0.77±0.07, P=0.10, and 0.73±0.07). The MPUnet performed significantly better on N=22 KL grade 3 CCBR scans with 0.78±0.06 vs. 0.75±0.08 for KIQ and 0.76±0.06 for 2D U‐Net.

Data Conclusion

The MPUnet matched or exceeded the performance of state‐of‐the‐art knee MRI segmentation models across cohorts of variable sequences and patient demographics. The MPUnet required no manual tuning making it both accurate and easy‐to‐use.

Level of Evidence

3

Technical Efficacy

Stage 2

Automated tibiofemoral joint segmentation based on deeply supervised 2D-3D ensemble U-Net: Data from the Osteoarthritis Initiative

Improving longevity is one of the greatest achievements in humanity. Because of this, the population is growing older, and the ubiquity of knee osteoarthritis (OA) is on the rise. Nonetheless, the understanding and ability to investigate potential precursors of knee OA have been impeded by time-consuming and laborious manual delineation processes which are prone to poor reproducibility. A method for automatic segmentation of the tibiofemoral joint using magnetic resonance imaging (MRI) is presented in this work. The proposed method utilizes a deeply supervised 2D-3D ensemble U-Net, which consists of foreground class oversampling, deep supervision loss branches, and Gaussian weighted softmax score aggregation. It was designed, optimized, and tested on 507 3D double echo steady-state (DESS) MR volumes using a two-fold cross-validation approach. A state-of-the-art segmentation accuracy measured as Dice similarity coefficient (DSC) for the femur bone (98.6 ± 0.27%), tibia bone (98.8 ± 0.31%), femoral cartilage (90.3 ± 2.89%), and tibial cartilage (86.7 ± 4.07%) is achieved. Notably, the proposed method yields sub-voxel accuracy for an average symmetric surface distance (ASD) less than 0.36 mm. The model performance is not affected by the severity of radiographic osteoarthritis (rOA) grades or the presence of pathophysiological changes. The proposed method offers an accurate segmentation with high time efficiency (~62 s) per 3D volume, which is well suited for efficient processing and analysis of the large prospective cohorts of the Osteoarthritis Initiative (OAI).

3D MRI in Osteoarthritis

Osteoarthritis (OA) is among the top 10 burdensome diseases, with the knee the most affected joint. Magnetic resonance imaging (MRI) allows whole-knee assessment, making it ideally suited for imaging OA, considered a multitissue disease. Three-dimensional (3D) MRI enables the comprehensive assessment of OA, including quantitative morphometry of various joint tissues. Manual tissue segmentation on 3D MRI is challenging but may be overcome by advanced automated image analysis methods including artificial intelligence (AI). This review presents examples of the utility of 3D MRI for knee OA, focusing on the articular cartilage, bone, meniscus, synovium, and infrapatellar fat pad, and it highlights several applications of AI that facilitate segmentation, lesion detection, and disease classification.

Multi-muscle deep learning segmentation to automate the quantification of muscle fat infiltration in cervical spine conditions

Muscle fat infiltration (MFI) has been widely reported across cervical spine disorders. The quantification of MFI requires time-consuming and rater-dependent manual segmentation techniques. A convolutional neural network (CNN) model was trained to segment seven cervical spine muscle groups (left and right muscles segmented separately, 14 muscles total) from Dixon MRI scans (n = 17, 17 scans < 2 weeks post motor vehicle collision (MVC), and 17 scans 12 months post MVC). The CNN MFI measures demonstrated high test reliability and accuracy in an independent testing dataset (n = 18, 9 scans < 2 weeks post MVC, and 9 scans 12 months post MVC). Using the CNN in 84 participants with scans < 2 weeks post MVC (61 females, 23 males, age = 34.2 ± 10.7 years) differences in MFI between the muscle groups and relationships between MFI and sex, age, and body mass index (BMI) were explored. Averaging across all muscles, females had significantly higher MFI than males (p = 0.026). The deep cervical muscles demonstrated significantly greater MFI than the more superficial muscles (p < 0.001), and only MFI within the deep cervical muscles was moderately correlated to age (r > 0.300, p ≤ 0.001). CNN's allow for the accurate and rapid, quantitative assessment of the composition of the architecturally complex muscles traversing the cervical spine. Acknowledging the wider reports of MFI in cervical spine disorders and the time required to manually segment the individual muscles, this CNN may have diagnostic, prognostic, and predictive value in disorders of the cervical spine.

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.

MRSaiFE: An AI-based Approach Towards the Real-Time Prediction of Specific Absorption Rate

The purpose of this study is to investigate feasibility of estimating the specific absorption rate (SAR) in MRI in real time. To this goal, SAR maps are predicted from 3T- and 7T-simulated magnetic resonance (MR) images in 10 realistic human body models via a convolutional neural network. Two-dimensional (2-D) U-Net architectures with varying contraction layers and different convolutional filters were designed to estimate the SAR distribution in realistic body models. Sim4Life (ZMT, Switzerland) was used to create simulated anatomical images and SAR maps at 3T and 7T imaging frequencies for Duke, Ella, Charlie, and Pregnant Women (at 3, 7, and 9 month gestational stages) body models. Mean squared error (MSE) was used as the cost function and the structural similarity index (SSIM) was reported. A 2-D U-Net with 4 contracting (and 4 expanding) layers and 64 convolutional filters at the initial stage showed the best compromise to estimate SAR distributions. Adam optimizer outperformed stochastic gradient descent (SGD) for all cases with an average SSIM of 90.5∓3.6 % and an average MSE of 0.7∓0.6% for head images at 7T, and an SSIM of >85.1∓6.2 % and an MSE of 0.4∓0.4% for 3T body imaging. Algorithms estimated the SAR maps for 224×224 slices under 30 ms. The proposed methodology shows promise to predict real-time SAR in clinical imaging settings without using extra mapping techniques or patient-specific calibrations.