How AI May Transform Musculoskeletal Imaging.

While musculoskeletal imaging volumes are increasing, there is a relative shortage of subspecialized musculoskeletal radiologists to interpret the studies. Will artificial intelligence (AI) be the solution? For AI to be the solution, the wide implementation of AI-supported data acquisition methods in clinical practice requires establishing trusted and reliable results. This implementation will demand close collaboration between core AI researchers and clinical radiologists. Upon successful clinical implementation, a wide variety of AI-based tools can improve the musculoskeletal radiologist's workflow by triaging imaging examinations, helping with image interpretation, and decreasing the reporting time. Additional AI applications may also be helpful for business, education, and research purposes if successfully integrated into the daily practice of musculoskeletal radiology. The question is not whether AI will replace radiologists, but rather how musculoskeletal radiologists can take advantage of AI to enhance their expert capabilities.

Characterization of Age-Related and Sex-Related Differences of Relaxation Parameters in the Intervertebral Disc Using MR-Fingerprinting.

BACKGROUND: Multiparameter characterization using MR fingerprinting (MRF) can quantify multiple relaxation parameters of intervertebral disc (IVD) simultaneously. These parameters may vary by age and sex. PURPOSE: To investigate age- and sex-related differences in the relaxation parameters of the IVD of the lumbar spine using a multiparameter MRF technique. STUDY TYPE: Prospective. SUBJECTS: 17 healthy subjects (8 male; mean age = 34 ± 10 years, range 20-60 years). FIELD STRENGTH/SEQUENCE: 3D-MRF sequence for simultaneous acquisition of proton density, T1 , T2 , and T1ρ maps at 3.0T. ASSESSMENT: Global mean T1 , T2 , and T1ρ of all lumbar IVDs and mean T1 , T2 , and T1ρ of each individual IVD (L1-L5) were measured. Gray level co-occurrence matrix was used to quantify textural features (median, contrast, correlation, energy, and homogeneity) from T1 , T2 , and T1ρ maps. STATISTICAL TESTS: Spearman rank correlations (R) evaluated the association between age and T1 , T2 , and T1ρ of IVD. Mann-Whitney U-tests evaluated differences between males and females in T1 , T2 , and T1ρ of IVD. Statistical significance was defined as P-value <0.05. RESULTS: There was a significant negative correlation between age and global mean values of all IVDs for T1 (R = -0.637), T2 (R = -0.509), and T1ρ (R = -0.726). For individual IVDs, there was a significant negative correlation between age and mean T1 at all IVD segments (R range = -0.530 to -0.708), between age and mean T2 at L2-L3, L3-L4, and L4-L5 (R range = -0.493 to 0.640), and between age and mean T1ρ at all segments except L1-L2 (R range = -0.632 to -0.763). There were no significant differences between sexes in global mean T1 , T2, and T1ρ (P-value = 0.23-0.76) The texture features with the highest significant correlations with age for all IVDs were global T1ρ mean (R = -0.726), T1 energy (R = -0.681), and T1 contrast (R = 0.709). CONCLUSION: This study showed that the 3D-MRF technique has potential to characterize age-related differences in T1 , T2, or T1ρ of IVD in healthy subjects. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 1.

Imaging Biomarkers of Osteoarthritis.

Currently no disease-modifying osteoarthritis drug has been approved for the treatment of osteoarthritis (OA) that can reverse, hold, or slow the progression of structural damage of OA-affected joints. The reasons for failure are manifold and include the heterogeneity of structural disease of the OA joint at trial inclusion, and the sensitivity of biomarkers used to measure a potential treatment effect.This article discusses the role and potential of different imaging biomarkers in OA research. We review the current role of radiography, as well as advances in quantitative three-dimensional morphological cartilage assessment and semiquantitative whole-organ assessment of OA. Although magnetic resonance imaging has evolved as the leading imaging method in OA research, recent developments in computed tomography are also discussed briefly. Finally, we address the experience from the Foundation for the National Institutes of Health Biomarker Consortium biomarker qualification study and the future role of artificial intelligence.

Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade.

This article will provide a perspective review of the most extensively investigated deep learning (DL) applications for musculoskeletal disease detection that have the best potential to translate into routine clinical practice over the next decade. Deep learning methods for detecting fractures, estimating pediatric bone age, calculating bone measurements such as lower extremity alignment and Cobb angle, and grading osteoarthritis on radiographs have been shown to have high diagnostic performance with many of these applications now commercially available for use in clinical practice. Many studies have also documented the feasibility of using DL methods for detecting joint pathology and characterizing bone tumors on magnetic resonance imaging (MRI). However, musculoskeletal disease detection on MRI is difficult as it requires multi-task, multi-class detection of complex abnormalities on multiple image slices with different tissue contrasts. The generalizability of DL methods for musculoskeletal disease detection on MRI is also challenging due to fluctuations in image quality caused by the wide variety of scanners and pulse sequences used in routine MRI protocols. The diagnostic performance of current DL methods for musculoskeletal disease detection must be further evaluated in well-designed prospective studies using large image datasets acquired at different institutions with different imaging parameters and imaging hardware before they can be fully implemented in clinical practice. Future studies must also investigate the true clinical benefits of current DL methods and determine whether they could enhance quality, reduce error rates, improve workflow, and decrease radiologist fatigue and burnout with all of this weighed against the costs.

MRI radiomics for hamstring strain injury identification and return to sport classification: a pilot study.

OBJECTIVE: To determine if MRI-based radiomics from hamstring muscles are related to injury and if the features could be used to perform a time to return to sport (RTS) classification. We hypothesize that radiomics from hamstring muscles, especially T2-weighted and diffusion tensor imaging-based features, are related to injury and can be used for RTS classification. SUBJECTS AND METHODS: MRI data from 32 athletes at the University of Wisconsin-Madison that sustained a hamstring strain injury were collected. Diffusion tensor imaging and T1- and T2-weighted images were processed, and diffusion maps were calculated. Radiomics features were extracted from the four hamstring muscles in each limb and for each MRI modality, individually. Feature selection was performed and multiple support vector classifiers were cross-validated to differentiate between involved and uninvolved limbs and perform binary (≤ or > 25 days) and multiclass (< 14 vs. 14-42 vs. > 42 days) classification of RTS. RESULT: The combination of radiomics features from all diffusion tensor imaging and T2-weighted images provided the most accurate differentiation between involved and uninvolved limbs (AUC ≈ 0.84 ± 0.16). For the binary RTS classification, the combination of all extracted radiomics offered the most accurate classification (AUC ≈ 0.95 ± 0.15). While for the multiclass RTS classification, the combination of features from all the diffusion tensor imaging maps provided the most accurate classification (weighted one vs. rest AUC ≈ 0.81 ± 0.16). CONCLUSION: This pilot study demonstrated that radiomics features from hamstring muscles are related to injury and have the potential to predict RTS.

Diffusion tensor imaging of hamstring muscles after acute strain injury and throughout recovery in collegiate athletes.

OBJECTIVE: To identify the region of interest (ROI) to represent injury and observe between-limb diffusion tensor imaging (DTI) microstructural differences in muscle following hamstring strain injury. MATERIALS AND METHODS: Participants who sustained a hamstring strain injury prospectively underwent 3T-MRI of bilateral thighs using T1, T2, and diffusion-weighted imaging at time of injury (TOI), return to sport (RTS), and 12 weeks after RTS (12wks). ROIs were using the hyperintense region on a T2-weighted sequence: edema, focused edema, and primary muscle injured excluding edema (no edema). Linear mixed-effects models were used to compare diffusion parameters between ROIs and timepoints and limbs and timepoints. RESULTS: Twenty-four participants (29 injuries) were included. A significant ROI-by-timepoint interaction was detected for all diffusivity measures. The edema and focused edema ROIs demonstrated increased diffusion at TOI compared to RTS for all diffusivity measures (p-values < 0.006), except λ1 (p-values = 0.058-0.12), and compared to 12wks (p-values < 0.02). In the no edema ROI, differences in diffusivity measures were not observed (p-values > 0.82). At TOI, no edema ROI diffusivity measures were lower than the edema ROI (p-values < 0.001) but not at RTS or 12wks (p-values > 0.69). A significant limb-by-timepoint interaction was detected for all diffusivity measures with increased diffusion in the involved limb at TOI (p-values < 0.001) but not at RTS or 12wks (p-values > 0.42). Significant differences in fractional anisotropy over time or between limbs were not detected. CONCLUSION: Hyperintensity on T2-weighted imaging used to define the injured region holds promise in describing muscle microstructure following hamstring strain injury by demonstrating between-limb differences at TOI but not at follow-up timepoints.

Emerging Technology in Musculoskeletal MRI and CT.

This article provides a focused overview of emerging technology in musculoskeletal MRI and CT. These technological advances have primarily focused on decreasing examination times, obtaining higher quality images, providing more convenient and economical imaging alternatives, and improving patient safety through lower radiation doses. New MRI acceleration methods using deep learning and novel reconstruction algorithms can reduce scanning times while maintaining high image quality. New synthetic techniques are now available that provide multiple tissue contrasts from a limited amount of MRI and CT data. Modern low-field-strength MRI scanners can provide a more convenient and economical imaging alternative in clinical practice, while clinical 7.0-T scanners have the potential to maximize image quality. Three-dimensional MRI curved planar reformation and cinematic rendering can provide improved methods for image representation. Photon-counting detector CT can provide lower radiation doses, higher spatial resolution, greater tissue contrast, and reduced noise in comparison with currently used energy-integrating detector CT scanners. Technological advances have also been made in challenging areas of musculoskeletal imaging, including MR neurography, imaging around metal, and dual-energy CT. While the preliminary results of these emerging technologies have been encouraging, whether they result in higher diagnostic performance requires further investigation.

Age and gender differences in lumbar intervertebral disk strain using mechanical loading magnetic resonance imaging.

The objective of the current study was to investigate age- and gender-related differences in lumbar intervertebral disk (IVD) strain with the use of static mechanical loading and continuous three-dimensional (3D) golden-angle radial sparse parallel (GRASP) MRI. A continuous 3D-GRASP stack-of-stars trajectory of the lumbar spine was performed on a 3-T scanner with static mechanical loading. Compressed sensing reconstruction, motion deformation maps, and Lagrangian strain maps during loading and recovery in the X-, Y-, and Z-directions were calculated for segmented IVD segments from L1/L2 to L5/S1. Mean IVD height was measured at rest. Spearman coefficients were used to evaluate the associations between age and global IVD height and global IVD strain. Mann-Whitney tests were used to compare global IVD height and global IVD strain in males and females. The prospective study enrolled 20 healthy human volunteers (10 males, 10 females; age 34.6 ± 11.4 [mean ± SD], range 22-56 years). Significant increases in compressive strain were observed with age, as evidenced by negative correlations between age and global IVD strain during loading (ρ = -0.76, p = 0.0046) and recovery (ρ = -0.68, p = 0.0251) in the loading X-direction. There was no significant correlation between age and global IVD height, global IVD strain during loading and recovery in the Y-direction, and global IVD strain during loading and recovery in the Z-direction. There were no significant differences between males and females in global IVD height and global IVD strain during loading and recovery in the X-, Y-, and Z-directions. It was concluded that our study demonstrated the significant role aging plays in internal dynamic strains in the lumbar IVD during loading and recovery. Older healthy individuals have reduced IVD stiffness and greater IVD compression during static mechanical loading of the lumbar spine. The GRASP-MRI technique demonstrates the feasibility to identify changes in IVD mechanical properties with early IVD degeneration due to aging.

Age-Dependent Changes in Knee Cartilage T1 , T2 , and T1p Simultaneously Measured Using MRI Fingerprinting.

BACKGROUND: Magnetic resonance fingerprinting (MRF) techniques have been recently described for simultaneous multiparameter cartilage mapping of the knee although investigation of their ability to detect early cartilage degeneration remains limited. PURPOSE: To investigate age-dependent changes in knee cartilage T1 , T2 , and T1p relaxation times measured using a three-dimensional (3D) MRF sequence in healthy volunteers. STUDY TYPE: Prospective. SUBJECTS: The study group consisted of 24 healthy asymptomatic human volunteers (15 males with mean age 34.9 ± 14.4 years and 9 females with mean age 44.5 ± 13.1 years). FIELD STRENGTH/SEQUENCE: A 3.0 T gradient-echo-based 3D-MRF sequence was used to simultaneously create proton density-weighted images and T1 , T2 , and T1p maps of knee cartilage. ASSESSMENT: Mean global cartilage and regional cartilage (lateral femur, lateral tibia, medial femur, medial tibia, and patella) T1 , T2 , and T1ρ relaxation times of the knee were measured. STATISTICAL TESTS: Kruskal-Wallis tests were used to compared cartilage T1 , T2 , and T1ρ relaxation times between different age groups, while Spearman correlation coefficients was used to determine the association between age and cartilage T1 , T2 , and T1ρ relaxation times. The value of P < 0.05 was considered statistically significant. RESULTS: Higher age groups showed higher global and regional cartilage T1 , T2 , and T1ρ . There was a significant difference between age groups in global cartilage T2 and T1ρ but no significant difference (P = 0.13) in global cartilage T1. Significant difference was also present between age groups in cartilage T2 and T1ρ for medial femur cartilage and medial tibia cartilage. There were significant moderate correlations between age and T2 and T1ρ for global cartilage (R2  = 0.63-0.64), medial femur cartilage (R2  = 0.50-0.56), and medial tibia cartilage (R2  = 0.54-0.66). CONCLUSION: Cartilage T2 and T1p relaxation times simultaneously measured using a 3D-MRF sequence in healthy volunteers showed age-dependent changes in knee cartilage, primarily within the medial compartment.

Repeatability of Quantitative Knee Cartilage T1 , T2 , and T1ρ Mapping With 3D-MRI Fingerprinting.

BACKGROUND: Three-dimensional MR fingerprinting (3D-MRF) techniques have been recently described for simultaneous multiparametric mapping of knee cartilage. However, investigation of repeatability remains limited. PURPOSE: To assess the intra-day and inter-day repeatabilities of knee cartilage T1 , T2 , and T1ρ maps using a 3D-MRF sequence for simultaneous measurement. STUDY TYPE: Prospective. SUBJECTS: Fourteen healthy subjects (35.4 ± 9.3 years, eight males), scanned on Day 1 and Day 7. FIELD STRENGTH/SEQUENCE: 3 T/3D-MRF, T1 , T2 , and T1ρ maps. ASSESSMENT: The acquisition of 3D-MRF cartilage (simultaneous acquisition of T1 , T2 , and T1ρ maps) were acquired using a dictionary pattern-matching approach. Conventional cartilage T1 , T2 , and T1ρ maps were acquired using variable flip angles and a modified 3D-Turbo-Flash sequence with different echo and spin-lock times, respectively, and were fitted using mono-exponential models. Each sequence was acquired on Day 1 and Day 7 with two scans on each day. STATISTICAL TESTS: The mean and SD for cartilage T1 , T2 , and T1ρ were calculated in five manually segmented regions of interest (ROIs), including lateral femur, lateral tibia, medial femur, medial tibia, and patella cartilages. Intra-subject and inter-subject repeatabilities were assessed using coefficient of variation (CV) and intra-class correlation coefficient (ICC), respectively, on the same day and among different days. Regression and Bland-Altman analysis were performed to compare maps between the conventional and 3D-MRF sequences. RESULTS: The CV in all ROIs was lower than 7.4%, 8.4%, and 7.5% and the ICC was higher than 0.56, 0.51, and 0.52 for cartilage T1 , T2 , and T1ρ , respectively. The MRF results had a good agreement with the conventional methods with a linear regression slope >0.61 and R2 > 0.59. CONCLUSION: The 3D-MRF sequence had high intra-subject and inter-subject repeatabilities for simultaneously measuring knee cartilage T1 , T2 , and T1ρ with good agreement with conventional sequences. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 1.

Age and Gender-Dependence of Single-and Bi-Exponential T1ρ MR Parameters in Knee Ligaments.

BACKGROUND: There is limited understanding of differences in the composition and structure of ligaments between healthy males and females, and individuals of different ages. Females present higher risk for ligament injuries than males and there are conflicting reports on its cause. This study looks into T1ρ parameters for an explanation as it relates to proteoglycan, collagen, and water content in these tissues. PURPOSE: To investigate gender-related and age-related differences in T1ρ parameters in knee joint ligaments in healthy volunteers using a T1ρ -prepared zero echo-time (ZTE)-based pointwise-encoding time-reduction with radial acquisition (T1ρ -PETRA) sequence. STUDY TYPE: Prospective. POPULATION: The study group consisted of 22 healthy subjects (11 females, ages: 41 ± 18 years, and 11 males, ages: 41 ± 14 years) with no known inflammation, trauma, or pain in the knee joint. FIELD STRENGTH/SEQUENCE: A T1ρ -prepared 3D-PETRA sequence was used to acquire fat-suppressed images with varying spin-lock lengths (TSLs) of the knee joint at 3T. ASSESSMENT: Monoexponential, biexponential, and stretched-exponential 3D-PETRA-T1ρ parameters were measured in the anterior cruciate ligament (ACL), posterior cruciate ligament (PCL), and patellar tendon (PT) by manually drawing ROIs over the entirety of the tissues. STATISTICAL TESTS: Mann-Whitney U-tests were used to compare 3D-PETRA-T1ρ parameters in the ACL, PCL, and PT between males and females. Spearman correlation coefficients were used to determine the association between age and T1ρ parameters. Statistical significance was defined as P < 0.05. RESULTS: Significant correlations with age were found the three ligaments with most of the measured T1ρ parameters (rs = 0.28-0.74) with the exception of the short fraction in the PCL (P = 0.18), and the short relaxation time in the ACL (P = 0.58) and in the PCL (P = 0.14). DATA CONCLUSION: 3D-PETRA-T1ρ can detect age-related differences in monoexponential, biexponential, and stretched-exponential T1ρ parameters in three ligaments of healthy volunteers, which are thought to be related to changes in tissue composition and structure during the aging process. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 1.

Updates on Compositional MRI Mapping of the Cartilage: Emerging Techniques and Applications.

Osteoarthritis (OA) is a widely occurring degenerative joint disease that is severely debilitating and causes significant socioeconomic burdens to society. Magnetic resonance imaging (MRI) is the preferred imaging modality for the morphological evaluation of cartilage due to its excellent soft tissue contrast and high spatial resolution. However, its utilization typically involves subjective qualitative assessment of cartilage. Compositional MRI, which refers to the quantitative characterization of cartilage using a variety of MRI methods, can provide important information regarding underlying compositional and ultrastructural changes that occur during early OA. Cartilage compositional MRI could serve as early imaging biomarkers for the objective evaluation of cartilage and help drive diagnostics, disease characterization, and response to novel therapies. This review will summarize current and ongoing state-of-the-art cartilage compositional MRI techniques and highlight emerging methods for cartilage compositional MRI including MR fingerprinting, compressed sensing, multiexponential relaxometry, improved and robust radio-frequency pulse sequences, and deep learning-based acquisition, reconstruction, and segmentation. The review will also briefly discuss the current challenges and future directions for adopting these emerging cartilage compositional MRI techniques for use in clinical practice and translational OA research studies. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

Genicular Artery Embolization for Treatment of Knee Osteoarthritis: Interim Analysis of a Prospective Pilot Trial Including Effect on Serum Osteoarthritis-Associated Biomarkers.

PURPOSE: To characterize the safety, efficacy, and potential role of genicular artery embolization (GAE) as a disease-modifying treatment for symptomatic knee osteoarthritis (OA). MATERIALS AND METHODS: This is an interim analysis of a prospective, single-arm clinical trial of patients with symptomatic knee OA who failed conservative therapy for greater than 3 months. Sixteen patients who underwent GAE using 250-µm microspheres and had at least 1 month of follow-up were included. Six patients completed the 12-month follow-up, and 10 patients remain enrolled. Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) was evaluated at baseline and at 1, 3, and 12 months. Serum and plasma samples were collected for biomarker analysis. The primary end point was the percentage of patients who achieved the minimal clinically important difference (MCID) for WOMAC pain score at 12 months. Baseline and follow-up outcomes were analyzed using the Wilcoxon matched-pairs signed-rank test. RESULTS: Technical success of the procedure was 100%, with no major adverse events. The MCID was achieved in 5 of the 6 (83%) patients at 12 months. The mean WOMAC pain score decreased from 8.6 ± 2.7 at baseline to 4.9 ± 2.7 (P = .001), 4.4 ± 2.8 (P < .001), and 4.7 ± 2.7 (P = .094) at 1, 3, and 12 months, respectively. There was a statistically significant decrease in nerve growth factor (NGF) levels at 12 months. The remaining 8 biomarkers showed no significant change at 12 months. CONCLUSIONS: GAE is a safe and efficacious treatment for symptomatic knee OA. Decreased NGF levels after GAE may contribute to pain reduction and slowing of cartilage degeneration.

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.

2D versus 3D MRI of osteoarthritis in clinical practice and research.

Accurately detecting and characterizing articular cartilage defects is critical in assessing patients with osteoarthritis. While radiography is the first-line imaging modality, magnetic resonance imaging (MRI) is the most accurate for the noninvasive assessment of articular cartilage. Multiple semiquantitative grading systems for cartilage lesions in MRI were developed. The Outerbridge and modified Noyes grading systems are commonly used in clinical practice and for research. Other useful grading systems were developed for research, many of which are joint-specific. Both two-dimensional (2D) and three-dimensional (3D) pulse sequences are used to assess cartilage morphology and biochemical composition. MRI techniques for morphological assessment of articular cartilage can be categorized into 2D and 3D FSE/TSE spin-echo and gradient-recalled echo sequences. T2 mapping is most commonly used to qualitatively assess articular cartilage microstructural composition and integrity, extracellular matrix components, and water content. Quantitative techniques may be able to label articular cartilage alterations before morphological defects are visible. Accurate detection and characterization of shallow low-grade partial and small articular cartilage defects are the most challenging for any technique, but where high spatial resolution 3D MRI techniques perform best. This review article provides a practical overview of commonly used 2D and 3D MRI techniques for articular cartilage assessments in osteoarthritis.

Artificial intelligence in musculoskeletal imaging: a perspective on value propositions, clinical use, and obstacles.

Artificial intelligence and deep learning (DL) offer musculoskeletal radiology exciting possibilities in multiple areas, including image reconstruction and transformation, tissue segmentation, workflow support, and disease detection. Novel DL-based image reconstruction algorithms correcting aliasing artifacts, signal loss, and noise amplification with previously unobtainable effectiveness are prime examples of how DL algorithms deliver promised value propositions in musculoskeletal radiology. The speed of DL-based tissue segmentation promises great efficiency gains that may permit the inclusion of tissue compositional-based information routinely into radiology reports. Similarly, DL algorithms give rise to a myriad of opportunities for workflow improvements, including intelligent and adaptive hanging protocols, speech recognition, report generation, scheduling, precertification, and billing. The value propositions of disease-detecting DL algorithms include reduced error rates and increased productivity. However, more studies using authentic clinical workflow settings are necessary to fully understand the value of DL algorithms for disease detection in clinical practice. Successful workflow integration and management of multiple algorithms are critical for translating the value propositions of DL algorithms into clinical practice but represent a major roadblock for which solutions are critically needed. While there is no consensus about the most sustainable business model, radiology departments will need to carefully weigh the benefits and disadvantages of each commercially available DL algorithm. Although more studies are needed to understand the value and impact of DL algorithms on clinical practice, DL technology will likely play an important role in the future of musculoskeletal imaging.

Deep learning approach to predict pain progression in knee osteoarthritis.

OBJECTIVE: To develop and evaluate deep learning (DL) risk assessment models for predicting pain progression in subjects with or at risk of knee osteoarthritis (OA). MATERIALS AND METHODS: The incidence and progression cohorts of the Osteoarthritis Initiative, a multi-center longitudinal study involving 9348 knees in 4674 subjects with or at risk of knee OA that began in 2004 and is ongoing, were used to conduct this retrospective analysis. A subset of knees without and with pain progression (defined as a 9-point or greater increase in pain score between baseline and two or more follow-up time points over the first 48 months) was randomly stratified into training (4200 knees with a mean age of 61.0 years and 60% female) and hold-out testing (500 knees with a mean age of 60.8 years and 60% female) datasets. A DL model was developed to predict pain progression using baseline knee radiographs. An artificial neural network was used to develop a traditional risk assessment model to predict pain progression using demographic, clinical, and radiographic risk factors. A combined model was developed to combine demographic, clinical, and radiographic risk factors with DL analysis of baseline knee radiographs. Area under the curve (AUC) analysis was performed using the hold-out testing dataset to evaluate model performance. RESULTS: The traditional model had an AUC of 0.692 (66.9% sensitivity and 64.1% specificity). The DL model had an AUC of 0.770 (76.7% sensitivity and 70.5% specificity), which was significantly higher (p < 0.001) than the traditional model. The combined model had an AUC of 0.807 (72.3% sensitivity and 80.9% specificity), which was significantly higher (p < 0.05) than the traditional and DL models. CONCLUSIONS: DL models using baseline knee radiographs had higher diagnostic performance for predicting pain progression than traditional models using demographic, clinical, and radiographic risk factors.

Magnetic resonance parameter mapping using model-guided self-supervised deep learning.

PURPOSE: To develop a model-guided self-supervised deep learning MRI reconstruction framework called reference-free latent map extraction (RELAX) for rapid quantitative MR parameter mapping. METHODS: Two physical models are incorporated for network training in RELAX, including the inherent MR imaging model and a quantitative model that is used to fit parameters in quantitative MRI. By enforcing these physical model constraints, RELAX eliminates the need for full sampled reference data sets that are required in standard supervised learning. Meanwhile, RELAX also enables direct reconstruction of corresponding MR parameter maps from undersampled k-space. Generic sparsity constraints used in conventional iterative reconstruction, such as the total variation constraint, can be additionally included in the RELAX framework to improve reconstruction quality. The performance of RELAX was tested for accelerated T1 and T2 mapping in both simulated and actually acquired MRI data sets and was compared with supervised learning and conventional constrained reconstruction for suppressing noise and/or undersampling-induced artifacts. RESULTS: In the simulated data sets, RELAX generated good T1 /T2 maps in the presence of noise and/or undersampling artifacts, comparable to artifact/noise-free ground truth. The inclusion of a spatial total variation constraint helps improve image quality. For the in vivo T1 /T2 mapping data sets, RELAX achieved superior reconstruction quality compared with conventional iterative reconstruction, and similar reconstruction performance to supervised deep learning reconstruction. CONCLUSION: This work has demonstrated the initial feasibility of rapid quantitative MR parameter mapping based on self-supervised deep learning. The RELAX framework may also be further extended to other quantitative MRI applications by incorporating corresponding quantitative imaging models.

3D MRI of Articular Cartilage.

Osteoarthritis, characterized by the breakdown of articular cartilage and other joint structures, is one of the most prevalent and disabling chronic diseases in the United States. Magnetic resonance imaging is a commonly used imaging modality to evaluate patients with joint pain. Both two-dimensional fast spin-echo sequences (2D-FSE) and three-dimensional (3D) sequences are used in clinical practice to evaluate articular cartilage. The 3D sequences have many advantages compared with 2D-FSE sequences, such as their high in-plane spatial resolution, thin continuous slices that reduce the effects of partial volume averaging, and ability to create multiplanar reformat images following a single acquisition. This article reviews the different 3D imaging techniques available for evaluating cartilage morphology, illustrates the strengths and weaknesses of 3D approaches compared with 2D-FSE approaches for cartilage imaging, and summarizes the diagnostic performance of 2D-FSE and 3D sequences for detecting cartilage lesions within the knee and hip joints.

State of the Art: Imaging of Osteoarthritis-Revisited 2020.

Osteoarthritis (OA) is a highly prevalent chronic condition with marked implications for affected individuals and public health care. There are available treatments to manage pain and symptoms but no effective treatment for OA. In the past 10 years, joint imaging, particularly MRI, has evolved rapidly due to technical advances and their application to clinical research, which has led to abundant evidence regarding the natural history of the disease. Radiography remains the primary imaging modality in clinical practice for the diagnosis and follow-up of OA. The many developments in MRI techniques capable of assessing cartilage morphologic features and the methods for evaluating its biochemical composition will be discussed. Advances in quantitative morphologic cartilage assessment and semiquantitative whole-organ assessment will be reviewed, as will other modalities such as US, CT and CT arthrography, and nuclear medicine techniques that play a complementary role. Various therapeutic approaches and ongoing developments, including the impact of artificial intelligence on the field of OA imaging, will also be discussed.