Faculty Bibliography

INTRODUCTION/UNASSIGNED:Femoroacetabular Impingement (FAI) is a hip pathology characterized by impingement of the femoral head-neck junction against the acetabular rim, due to abnormalities in bone morphology. FAI is normally diagnosed by manual evaluation of morphologic features on magnetic resonance imaging (MRI). In this study, we assess, for the first time, the feasibility of using radiomics to detect FAI by automatically extracting quantitative features from images. MATERIAL AND METHODS/UNASSIGNED:-value, for a total of 48 subsets. For each subset, a K-nearest neighbor model was trained to differentiate between IJ and HJ using the values of the radiomic features in the subset as input. The training was repeated 100 times, randomly subdividing the data with 75%/25% training/testing. RESULTS/UNASSIGNED:The texture-based gray level features yielded the highest prediction max accuracy (0.972) with the smallest subset of features. This suggests that the gray image values are more homogeneously distributed in the HJ in comparison to IJ, which could be due to stress-related inflammation resulting from impingement. CONCLUSIONS/UNASSIGNED:We showed that radiomics can automatically distinguish IJ from HJ using water-only Dixon MRI. To our knowledge, this is the first application of radiomics for FAI diagnosis. We reported an accuracy greater than 97%, which is higher than the 90% accuracy for detecting FAI reported for standard diagnostic tests (90%). Our proposed radiomic analysis could be combined with methods for automated joint segmentation to rapidly identify patients with FAI, avoiding time-consuming radiological measurements of bone morphology.

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

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/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.

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.

PURPOSE/OBJECTIVE: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: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:mapping data sets, RELAX achieved superior reconstruction quality compared with conventional iterative reconstruction, and similar reconstruction performance to supervised deep learning reconstruction. CONCLUSION/CONCLUSIONS: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.

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.

Non-invasive estimation of cartilage material properties is useful for understanding cartilage health and creating subject-specific computational models. Bi-component T2 mapping measured using Multi-Component Driven Equilibrium Single Shot Observation of T₁ and T₂ (mcDESPOT) is sensitive for detecting cartilage degeneration within the human knee joint, but has not been correlated with cartilage composition and mechanical properties. Therefore, the purpose of this study was to investigate the relationship between bi-component T₂ parameters measured using mcDESPOT at 3.0 T and cartilage composition and mechanical properties. Ex-vivo patellar cartilage specimens harvested from five human cadaveric knees were imaged using mcDESPOT at 3.0 T. Cartilage samples were removed from the patellae, mechanically tested to determine linear modulus and dissipated energy, and chemically tested to determine proteoglycan and collagen content. Parameter maps of single-component T₂ relaxation time (T₂), the T₂ relaxation times of the fast relaxing macromolecular bound water component (T_2F) and slow relaxing bulk water component (T_2S), and the fraction of the fast relaxing macromolecular bound water component (F_F) were compared to mechanical and chemical measures using linear regression. F_F was significantly (p < 0.05) correlated with energy dissipation and linear modulus. T₂ was significantly (p ≤ 0.05) correlated with elastic modulus at 1 Hz and energy dissipated at all frequencies. There were no other significant (p = 0.13-0.97) correlations between mcDESPOT parameters and mechanical properties. F_F was significantly (p = 0.04) correlated with proteoglycan content. There were no other significant (p = 0.19-0.92) correlations between mcDESPOT parameters and proteoglycan or collagen content. This study suggests that F_F measured using mcDESPOT at 3.0 T could be used to non-invasively estimate cartilage proteoglycan content, elastic modulus, and energy dissipation.

Deep learning is one of the most exciting new areas in medical imaging. This review article provides a summary of the current clinical applications of deep learning for lesion detection, progression, and prediction of musculoskeletal disease on radiographs, computed tomography (CT), magnetic resonance imaging (MRI), and nuclear medicine. Deep-learning methods have shown success for estimating pediatric bone age, detecting fractures, and assessing the severity of osteoarthritis on radiographs. In particular, the high diagnostic performance of deep-learning approaches for estimating pediatric bone age and detecting fractures suggests that the new technology may soon become available for use in clinical practice. Recent studies have also documented the feasibility of using deep-learning methods for identifying a wide variety of pathologic abnormalities on CT and MRI including internal derangement, metastatic disease, infection, fractures, and joint degeneration. However, the detection of musculoskeletal disease on CT and especially MRI is challenging, as it often requires analyzing complex abnormalities on multiple slices of image datasets with different tissue contrasts. Thus, additional technical development is needed to create deep-learning methods for reliable and repeatable interpretation of musculoskeletal CT and MRI examinations. Furthermore, the diagnostic performance of all deep-learning methods for detecting and characterizing musculoskeletal disease must be evaluated in prospective studies using large image datasets acquired at different institutions with different imaging parameters and different imaging hardware before they can be implemented in clinical practice. Level of Evidence: 5 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019.

BACKGROUND/UNASSIGNED:Graft placement is a modifiable and often discussed surgical factor in anterior cruciate ligament (ACL) reconstruction (ACLR). However, the sensitivity of functional knee mechanics to variability in graft placement is not well understood. PURPOSE/UNASSIGNED:To (1) investigate the relationship of ACL graft tunnel location and graft angle with tibiofemoral kinematics in patients with ACLR, (2) compare experimentally measured relationships with those observed with a computational model to assess the predictive capabilities of the model, and (3) use the computational model to determine the effect of varying ACL graft tunnel placement on tibiofemoral joint mechanics during walking. STUDY DESIGN/UNASSIGNED:Controlled laboratory study. METHODS/UNASSIGNED:Eighteen participants who had undergone ACLR were tested. Bilateral ACL footprint location and graft angle were assessed using magnetic resonance imaging (MRI). Bilateral knee laxity was assessed at the completion of rehabilitation. Dynamic MRI was used to measure tibiofemoral kinematics and cartilage contact during active knee flexion-extension. Additionally, a total of 500 virtual ACLR models were created from a nominal computational knee model by varying ACL footprint locations, graft stiffness, and initial tension. Laxity tests, active knee extension, and walking were simulated with each virtual ACLR model. Linear regressions were performed between internal knee mechanics and ACL graft tunnel locations and angles for the patients with ACLR and the virtual ACLR models. RESULTS/UNASSIGNED:= 0.56, 0.26, and 0.13). These effects extended to simulations of walking, with a more vertical ACL graft inducing greater anterior tibial translation, ACL loading, and posterior migration of contact on the tibial plateaus. CONCLUSION/UNASSIGNED:This study provides clinical evidence from patients who underwent ACLR and from complementary modeling that functional postoperative knee mechanics are sensitive to graft tunnel locations and graft angle. Of the factors studied, the sagittal angle of the ACL was particularly influential on knee mechanics. CLINICAL RELEVANCE/UNASSIGNED:Early-onset osteoarthritis from altered cartilage loading after ACLR is common. This study shows that postoperative cartilage loading is sensitive to graft angle. Therefore, variability in graft tunnel placement resulting in small deviations from the anatomic ACL angle might contribute to the elevated risk of osteoarthritis after ACLR.