Improving the Generalizability of Deep Learning for T2-Lesion Segmentation of Gliomas in the Post-Treatment Setting.

Although fully automated volumetric approaches for monitoring brain tumor response have many advantages, most available deep learning models are optimized for highly curated, multi-contrast MRI from newly diagnosed gliomas, which are not representative of post-treatment cases in the clinic. Improving segmentation for treated patients is critical to accurately tracking changes in response to therapy. We investigated mixing data from newly diagnosed (n = 208) and treated (n = 221) gliomas in training, applying transfer learning (TL) from pre- to post-treatment imaging domains, and incorporating spatial regularization for T2-lesion segmentation using only T2 FLAIR images as input to improve generalization post-treatment. These approaches were evaluated on 24 patients suspected of progression who had received prior treatment. Including 26% of treated patients in training improved performance by 13.9%, and including more treated and untreated patients resulted in minimal changes. Fine-tuning with treated glioma improved sensitivity compared to data mixing by 2.5% (p < 0.05), and spatial regularization further improved performance when used with TL by 95th HD, Dice, and sensitivity (6.8%, 0.8%, 2.2%; p < 0.05). While training with ≥60 treated patients yielded the majority of performance gain, TL and spatial regularization further improved T2-lesion segmentation to treated gliomas using a single MR contrast and minimal processing, demonstrating clinical utility in response assessment.

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

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

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.

Synthetic Inflammation Imaging with PatchGAN Deep Learning Networks.

Background: Gadolinium (Gd)-enhanced Magnetic Resonance Imaging (MRI) is crucial in several applications, including oncology, cardiac imaging, and musculoskeletal inflammatory imaging. One use case is rheumatoid arthritis (RA), a widespread autoimmune condition for which Gd MRI is crucial in imaging synovial joint inflammation, but Gd administration has well-documented safety concerns. As such, algorithms that could synthetically generate post-contrast peripheral joint MR images from non-contrast MR sequences would have immense clinical utility. Moreover, while such algorithms have been investigated for other anatomies, they are largely unexplored for musculoskeletal applications such as RA, and efforts to understand trained models and improve trust in their predictions have been limited in medical imaging. Methods: A dataset of 27 RA patients was used to train algorithms that synthetically generated post-Gd IDEAL wrist coronal T1-weighted scans from pre-contrast scans. UNets and PatchGANs were trained, leveraging an anomaly-weighted L1 loss and global generative adversarial network (GAN) loss for the PatchGAN. Occlusion and uncertainty maps were also generated to understand model performance. Results: UNet synthetic post-contrast images exhibited stronger normalized root mean square error (nRMSE) than PatchGAN in full volumes and the wrist, but PatchGAN outperformed UNet in synovial joints (UNet nRMSEs: volume = 6.29 ± 0.88, wrist = 4.36 ± 0.60, synovial = 26.18 ± 7.45; PatchGAN nRMSEs: volume = 6.72 ± 0.81, wrist = 6.07 ± 1.22, synovial = 23.14 ± 7.37; n = 7). Occlusion maps showed that synovial joints made substantial contributions to PatchGAN and UNet predictions, while uncertainty maps showed that PatchGAN predictions were more confident within those joints. Conclusions: Both pipelines showed promising performance in synthesizing post-contrast images, but PatchGAN performance was stronger and more confident within synovial joints, where an algorithm like this would have maximal clinical utility. Image synthesis approaches are therefore promising for RA and synthetic inflammatory imaging.

Trajectory of knee health in runners with and without heightened osteoarthritis risk: the TRAIL prospective cohort study protocol.

INTRODUCTION: Running is one of the most popular recreational activities worldwide, due to its low cost and accessibility. However, little is known about the impact of running on knee joint health in runners with and without a history of knee surgery. The primary aim of this longitudinal cohort study is to compare knee joint structural features on MRI and knee symptoms at baseline and 4-year follow-up in runners with and without a history of knee surgery. Secondary aims are to explore the relationships between training load exposures (volume and/or intensity) and changes in knee joint structure and symptoms over 4 years; explore the relationship between baseline running biomechanics, and changes in knee joint structure and symptoms over 4 years. In addition, we will explore whether additional variables confound, modify or mediate these associations, including sex, baseline lower-limb functional performance, knee muscle strength, psychological and sociodemographic factors. METHODS AND ANALYSIS: A convenience sample of at least 200 runners (sex/gender balanced) with (n=100) and without (n=100) a history of knee surgery will be recruited. Primary outcomes will be knee joint health (MRI) and knee symptoms (baseline; 4 years). Exposure variables for secondary outcomes include training load exposure, obtained daily throughout the study from wearable devices and three-dimensional running biomechanics (baseline). Additional variables include lower limb functional performance, knee extensor and flexor muscle strength, biomarkers, psychological and sociodemographic factors (baseline). Knowledge and beliefs about osteoarthritis will be obtained through predefined questions and semi-structured interviews with a subset of participants. Multivariable logistic and linear regression models, adjusting for potential confounding factors, will explore changes in knee joint structural features and symptoms, and the influence of potential modifiers and mediators. ETHICS AND DISSEMINATION: Approved by the La Trobe University Ethics Committee (HEC-19524). Findings will be disseminated to stakeholders, peer-review journals and conferences.

A More Posterior Tibial Tubercle (Decreased Sagittal Tibial Tubercle-Trochlear Groove Distance) Is Significantly Associated With Patellofemoral Joint Degenerative Cartilage Change: A Deep Learning Analysis.

PURPOSE: To perform patellofemoral joint (PFJ) geometric measurements on knee magnetic resonance imaging scans and determine their relations with chondral lesions in a multicenter cohort using deep learning. METHODS: The sagittal tibial tubercle-trochlear groove (sTTTG) distance, tibial tubercle-trochlear groove distance, trochlear sulcus angle, trochlear depth, Caton-Deschamps Index (CDI), and flexion angle were measured by use of deep learning-generated segmentations on a subset of the Osteoarthritis Initiative study with radiologist-graded PFJ cartilage grades (n = 2,461). Kruskal-Wallis H tests were performed to compare differences in PFJ morphology between subjects without PFJ osteoarthritis (OA) and those with PFJ OA. PFJ morphology was correlated with secondary outcomes of mean patellar cartilage thickness and mean patellar cartilage T2 relaxation time using linear regression models controlling for age, sex, and body mass index. RESULTS: A total of 1,626 knees did not have PFJ OA, whereas 835 knees had PFJ OA. Knees without PFJ OA had an increased (anterior) sTTTG distance (mean ± standard deviation, 11.1 ± 12.8 mm) compared with knees with PFJ OA (8.4 ± 12.7 mm) (P < .001), indicating a more posterior tibial tubercle in subjects with PFJ OA. Knees without PFJ OA had a decreased sulcus angle (127.4° ± 7.1° vs 128.0° ± 8.4°, P = .01) and increased trochlear depth (9.1 ± 1.7 mm vs 9.0 ± 2.0 mm, P = .03) compared with knees with PFJ OA. Decreased patellar cartilage thickness was associated with decreased trochlear depth (ß = 0.12, P = .002) and increased CDI (ß = -0.07, P < .001). Increased patellar cartilage T2 relaxation time was correlated with decreased sTTTG distance (ß = -0.08, P = .01), decreased sulcus angle (ß = -0.12, P = .04), and decreased CDI (ß = -0.12, P < .001). CONCLUSIONS: PFJ OA, patellar cartilage thickness, and patellar cartilage T2 relaxation time were shown to be associated with the underlying geometries within the PFJ. This large longitudinal study highlights that a decreased sTTTG distance (i.e., a more posterior tibial tubercle) is significantly associated with PFJ degenerative cartilage change. LEVEL OF EVIDENCE: Level III, retrospective comparative prognostic trial.

Baseline cartilage T1ρ and T2 predicted patellofemoral joint cartilage lesion progression and patient-reported outcomes after ACL reconstruction.

This study aims to determine if baseline T1ρ and T2 will predict cartilage morphological lesion progression in the patellofemoral joint (PFJ) and patient-reported outcomes at 2-year after anterior cruciate ligament (ACL) reconstruction (ACLR). Thirty-nine ACL-injured patients were studied at baseline and two-year after ACLR. 3 T MR T1ρ and T2 images and Knee Injury and Osteoarthritis Outcome Score (KOOS) were acquired at both time points. Voxel-based relaxometry (VBR) technique was used to detect local cartilage abnormalities. Patients were divided into progression and non-progression groups based on changes of the whole-organ magnetic resonance imaging scoring (WORMS) grading of cartilage in PFJ from baseline to 2-year, and into lower (more pain) and higher (less pain) KOOS pain groups based on 2-year KOOS pain scores, separately. Voxel-based analyses of covariance were used to compare T1ρ and T2 values at baseline between the defined groups. Using VBR analysis, the progression group at 2-year showed higher T1ρ and T2 compared with the non-progression group at baseline, with the medial femoral condyle showing the largest areas with significant differences. At two-year, 56% of patients were able to recover with respect to KOOS pain. The lower KOOS pain group at 2-year showed significantly elevated T1ρ and T2 in the patella at baseline compared with the higher KOOS pain group. In conclusion, baseline T1ρ and T2 mapping, combined with VBR analysis, may help identify ACLR patients at high risk of developing progressive PFJ cartilage lesions and worse clinical symptoms 2-year after surgery.

The Use of Multiple Imaging Studies Before Shoulder Stabilization Surgery Is Increasing.

Purpose: To determine the incidence of preoperative shoulder imaging, explore the prevalence of obtaining multiple advanced imaging studies, and identify patient characteristics associated with specific imaging studies before anterior versus posterior shoulder stabilization surgery. Methods: The PearlDiver database was queried for patients who underwent anterior or posterior shoulder stabilization surgery from 2010 to 2019. The incidence of imaging studies within a year of surgery was collected. Patient characteristics were compared between groups using one-way analysis of variance or χ2 test. Results: In total, 10,252 patients underwent anterior shoulder stabilization surgery, and 1,108 patients underwent posterior shoulder stabilization surgery. Imaging use before anterior and posterior shoulder stabilization surgery included plain radiographs (69%, 70%, respectively), magnetic resonance imaging (MRI; 43%, 33%), and computed tomography (CT; 22%, 22%). In total, 1,098 patients (11%) received MRI and CT before anterior stabilization surgery and 85 patients (8%) received MRI and CT before posterior stabilization surgery. Over time, the incidence of obtaining MRI and CT increased before anterior (z = 2.54, P = .011) and posterior (z = 2.36, P = .018) stabilization surgery. Conclusions: This study highlights the increasing use of multiple imaging studies before shoulder stabilization surgery over recent years, including plain radiographs, MRI, and CT imaging. In total, 45% of anterior shoulder stabilization patients and 41% of posterior shoulder stabilization patients obtained more than 1 imaging study within a year of surgery, with a recent increase in patients obtaining both MR and CT scans preoperatively. Statement of Clinical Relevance: The increasing use of multiple preoperative imaging studies observed in this study highlights an opportunity for new imaging technology to streamline and improve the preoperative workup.

Posterior Tibial Slope, Notch Width, Condylar Morphology, Trochlear Inclination, and Tibiofemoral Mismatch Predict Outcomes Following Anterior Cruciate Ligament Reconstruction.

PURPOSE: To provide a comprehensive summary of the available literature on the influence of bone morphology on outcomes after anterior cruciate ligament reconstruction (ACLR). METHODS: Our protocol was prospectively registered with PROSPERO (International Prospective Register of Systematic Reviews) and followed PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. The PubMed, Embase, and MEDLINE databases were searched for studies investigating knee morphologic features and outcomes after ACLR. Articles were screened and references lists were reviewed to identify relevant studies, after which methodologic quality was assessed for each study included in this review. Because of significant variability in terminology and methodology between studies, no meta-analyses were conducted. RESULTS: Systematically screening a total of 19,647 studies identified from the search revealed 24 studies that met the inclusion and exclusion criteria. Among tibial shape features identified as predictors of poor outcomes after ACLR, increased posterior tibial slope was most common (16 studies). Other features such as increased tibial plateau area (1 study), decreased medial plateau width (1 study), and increased medial plateau height (1 study) were also associated with poor outcomes. For the femur, features related to notch width and condylar morphology were most common (4 studies and 7 studies, respectively). An increased condylar offset ratio, increased lateral femoral condylar ratio, and larger notch width were each found to be associated with negative ACLR outcomes, including increased cartilage degeneration, worse patient-reported outcomes, and graft failure. CONCLUSIONS: Posterior tibial slope, notch width, condylar morphology, trochlear inclination, and tibiofemoral mismatch are associated with and predictive of outcomes after ACLR. LEVEL OF EVIDENCE: Level IV, systematic review of Level II-IV studies.

Improving the noninvasive classification of glioma genetic subtype with deep learning and diffusion-weighted imaging.

BACKGROUND: Diagnostic classification of diffuse gliomas now requires an assessment of molecular features, often including IDH-mutation and 1p19q-codeletion status. Because genetic testing requires an invasive process, an alternative noninvasive approach is attractive, particularly if resection is not recommended. The goal of this study was to evaluate the effects of training strategy and incorporation of biologically relevant images on predicting genetic subtypes with deep learning. METHODS: Our dataset consisted of 384 patients with newly diagnosed gliomas who underwent preoperative MRI with standard anatomical and diffusion-weighted imaging, and 147 patients from an external cohort with anatomical imaging. Using tissue samples acquired during surgery, each glioma was classified into IDH-wildtype (IDHwt), IDH-mutant/1p19q-noncodeleted (IDHmut-intact), and IDH-mutant/1p19q-codeleted (IDHmut-codel) subgroups. After optimizing training parameters, top performing convolutional neural network (CNN) classifiers were trained, validated, and tested using combinations of anatomical and diffusion MRI with either a 3-class or tiered structure. Generalization to an external cohort was assessed using anatomical imaging models. RESULTS: The best model used a 3-class CNN containing diffusion-weighted imaging as an input, achieving 85.7% (95% CI: [77.1, 100]) overall test accuracy and correctly classifying 95.2%, 88.9%, 60.0% of the IDHwt, IDHmut-intact, and IDHmut-codel tumors. In general, 3-class models outperformed tiered approaches by 13.5%-17.5%, and models that included diffusion-weighted imaging were 5%-8.8% more accurate than those that used only anatomical imaging. CONCLUSION: Training a classifier to predict both IDH-mutation and 1p19q-codeletion status outperformed a tiered structure that first predicted IDH-mutation, then 1p19q-codeletion. Including apparent diffusion coefficient (ADC), a surrogate marker of cellularity, more accurately captured differences between subgroups.

Editorial Commentary: Can We Evaluate Glenoid Bone With Magnetic Resonance Imaging? Yes, If You Have the Right Sequence.

Glenoid bone loss must be recognized when treating patients with shoulder instability to appropriately determine surgical treatment with either a soft-tissue stabilization or bony augmentation procedure. Three-dimensional reconstructions from computed tomography scans currently are the clinical gold standard for accurately evaluating glenoid bone loss. Novel advances in magnetic resonance imaging sequences and processing may allow for obtaining complete bony information from a single preoperative imaging study.

Incremental inputs improve the automated detection of implant loosening using machine-learning algorithms.

AIMS: The aim of this study was to evaluate the ability of a machine-learning algorithm to diagnose prosthetic loosening from preoperative radiographs and to investigate the inputs that might improve its performance. METHODS: A group of 697 patients underwent a first-time revision of a total hip (THA) or total knee arthroplasty (TKA) at our institution between 2012 and 2018. Preoperative anteroposterior (AP) and lateral radiographs, and historical and comorbidity information were collected from their electronic records. Each patient was defined as having loose or fixed components based on the operation notes. We trained a series of convolutional neural network (CNN) models to predict a diagnosis of loosening at the time of surgery from the preoperative radiographs. We then added historical data about the patients to the best performing model to create a final model and tested it on an independent dataset. RESULTS: The convolutional neural network we built performed well when detecting loosening from radiographs alone. The first model built de novo with only the radiological image as input had an accuracy of 70%. The final model, which was built by fine-tuning a publicly available model named DenseNet, combining the AP and lateral radiographs, and incorporating information from the patient's history, had an accuracy, sensitivity, and specificity of 88.3%, 70.2%, and 95.6% on the independent test dataset. It performed better for cases of revision THA with an accuracy of 90.1%, than for cases of revision TKA with an accuracy of 85.8%. CONCLUSION: This study showed that machine learning can detect prosthetic loosening from radiographs. Its accuracy is enhanced when using highly trained public algorithms, and when adding clinical data to the algorithm. While this algorithm may not be sufficient in its present state of development as a standalone metric of loosening, it is currently a useful augment for clinical decision making. Cite this article: Bone Joint J 2020;102-B(6 Supple A):101-106.

Altered tibiofemoral position following ACL reconstruction is associated with cartilage matrix changes: A voxel-based relaxometry analysis.

The purpose of this study was to analyze the relationship between postsurgical tibial translation (TT) and tibial rotation (TR) with cartilage matrix changes using quantitative magnetic resonance imaging, specifically voxel-based relaxometry with T1ρ and T2 mapping sequences. Knee magnetic resonance imaging's (MRI's) of 51 patients with unilateral anterior cruciate ligament injury, no concomitant ligamentous injury, history of osteoarthritis (OA), and previous knee surgery were scanned prior to surgery. Thirty-four patients completed follow-up MRI scans at 6-month, 1- and 2-year post-reconstruction and were included in this study. Knee biomechanics, T1ρ, and T2 were calculated using an in-house Matlab program. Compared to the contralateral knee, the injured knee demonstrated significantly increased anterior TT at baseline (P < .001), 6-month (P < .001), 1- (P = .001), and 2-year (P < .001). Furthermore, patients were divided into groups based on TT at 6-month. When compared to patients with normal TT, those with increased anterior TT at 6-month displayed significantly longer T1ρ and T2 relaxation times in 10.4% and 7.4% of the voxels in the injured medial tibia at 1-year, respectively, as well as 12.4% and 9.8% of the voxels in the injured medial tibia at 2-year, respectively. Our results demonstrate an association between abnormal tibiofemoral position and early degradative changes to the articular cartilage matrix of the injured knee. Clinical significance: These findings suggest that altered tibiofemoral position following ACL reconstruction is associated with early degeneration of knee cartilage. Future prospective studies employing longer follow-up times are warranted to evaluate the relationship between abnormal tibiofemoral position and the early onset of posttraumatic OA.

Computer-Aided Detection AI Reduces Interreader Variability in Grading Hip Abnormalities With MRI.

BACKGROUND: Accurate interpretation of hip MRI is time-intensive and difficult, prone to inter- and intrareviewer variability, and lacks a universally accepted grading scale to evaluate morphological abnormalities. PURPOSE: To 1) develop and evaluate a deep-learning-based model for binary classification of hip osteoarthritis (OA) morphological abnormalities on MR images, and 2) develop an artificial intelligence (AI)-based assist tool to find if using the model predictions improves interreader agreement in hip grading. STUDY TYPE: Retrospective study aimed to evaluate a technical development. POPULATION: A total of 764 MRI volumes (364 patients) obtained from two studies (242 patients from LASEM [FORCe] and 122 patients from UCSF), split into a 65-25-10% train, validation, test set for network training. FIELD STRENGTH/SEQUENCE: 3T MRI, 2D T2 FSE, PD SPAIR. ASSESSMENT: Automatic binary classification of cartilage lesions, bone marrow edema-like lesions, and subchondral cyst-like lesions using the MRNet, interreader agreement before and after using network predictions. STATISTICAL TESTS: Receiver operating characteristic (ROC) curve, area under curve (AUC), specificity and sensitivity, and balanced accuracy. RESULTS: For cartilage lesions, bone marrow edema-like lesions and subchondral cyst-like lesions the AUCs were: 0.80 (95% confidence interval [CI] 0.65, 0.95), 0.84 (95% CI 0.67, 1.00), and 0.77 (95% CI 0.66, 0.85), respectively. The sensitivity and specificity of the radiologist for binary classification were: 0.79 (95% CI 0.65, 0.93) and 0.80 (95% CI 0.59, 1.02), 0.40 (95% CI -0.02, 0.83) and 0.72 (95% CI 0.59, 0.86), 0.75 (95% CI 0.45, 1.05) and 0.88 (95% CI 0.77, 0.98). The interreader balanced accuracy increased from 53%, 71% and 56% to 60%, 73% and 68% after using the network predictions and saliency maps. DATA CONCLUSION: We have shown that a deep-learning approach achieved high performance in clinical classification tasks on hip MR images, and that using the predictions from the deep-learning model improved the interreader agreement in all pathologies. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 1 J. Magn. Reson. Imaging 2020;52:1163-1172.

Principal Component Analysis of Simultaneous PET-MRI Reveals Patterns of Bone-Cartilage Interactions in Osteoarthritis.

BACKGROUND: Bone-cartilage interactions have been implicated in causing osteoarthritis (OA). PURPOSE: To use [18 F]-NaF PET-MRI to 1) develop automatic image processing code in MatLab to create a model of bone-cartilage interactions and 2) find associations of bone-cartilage interactions with known manifestations of OA. STUDY TYPE: Prospective study aimed to evaluate a data analysis method. POPULATION: Twenty-nine patients with knee pain or joint stiffness. FIELD STRENGTH/SEQUENCE: 3T MRI (GE), 3D CUBE FSE, 3D combined T1 ρ/T2 MAPSS, [18F]-sodium fluoride, SIGNA TOF (OSEM). ASSESSMENT: Correlation between MRI (cartilage) and PET (bone) quantitative parameters, bone-cartilage interactions model described by modes of variation as derived by principal component analysis (PCA), WORMS scoring on cartilage lesions, bone marrow abnormalities, subchondral cysts. STATISTICAL TESTS: Linear regression, Pearson correlation. RESULTS: Mode 1 was a positive predictor of the bone abnormality score (P = 0.0003, P = 0.001, P = 0.0007) and the cartilage lesion score (P = 0.03, P = 0.01, P = 0.02) in the femur, tibia, and patella, respectively. For the cartilage lesion scores, mode 5 was the most important positive predictor in the femur (P = 3.9E-06), and mode 2 were predictors, significant negative predictor in the tibia (P = 0.007). In the patella, mode 1 was a significant positive predictor of the bone abnormality score (P = 0.0007). DATA CONCLUSION: By successfully building an automatic code to create a bone-cartilage interface, we were able to observe dynamic relationships between biochemical changes in the cartilage accompanied with bone remodeling, extended to the whole knee joint instead of simple colocalized observations, shedding light on the interactions that occur between bone and cartilage in OA. Evidence Level: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2020;52:1462-1474.

Development and Validation of a Multitask Deep Learning Model for Severity Grading of Hip Osteoarthritis Features on Radiographs.

Background A multitask deep learning model might be useful in large epidemiologic studies wherein detailed structural assessment of osteoarthritis still relies on expert radiologists' readings. The potential of such a model in clinical routine should be investigated. Purpose To develop a multitask deep learning model for grading radiographic hip osteoarthritis features on radiographs and compare its performance to that of attending-level radiologists. Materials and Methods This retrospective study analyzed hip joints seen on weight-bearing anterior-posterior pelvic radiographs from participants in the Osteoarthritis Initiative (OAI). Participants were recruited from February 2004 to May 2006 for baseline measurements, and follow-up was performed 48 months later. Femoral osteophytes (FOs), acetabular osteophytes (AOs), and joint-space narrowing (JSN) were graded as absent, mild, moderate, or severe according to the Osteoarthritis Research Society International atlas. Subchondral sclerosis and subchondral cysts were graded as present or absent. The participants were split at 80% (n = 3494), 10% (n = 437), and 10% (n = 437) by using split-sample validation into training, validation, and testing sets, respectively. The multitask neural network was based on DenseNet-161, a shared convolutional features extractor trained with multitask loss function. Model performance was evaluated in the internal test set from the OAI and in an external test set by using temporal and geographic validation consisting of routine clinical radiographs. Results A total of 4368 participants (mean age, 61.0 years ± 9.2 [standard deviation]; 2538 women) were evaluated (15 364 hip joints on 7738 weight-bearing anterior-posterior pelvic radiographs). The accuracy of the model for assessing these five features was 86.7% (1333 of 1538) for FOs, 69.9% (1075 of 1538) for AOs, 81.7% (1257 of 1538) for JSN, 95.8% (1473 of 1538) for subchondral sclerosis, and 97.6% (1501 of 1538) for subchondral cysts in the internal test set, and 82.7% (86 of 104) for FOS, 65.4% (68 of 104) for AOs, 80.8% (84 of 104) for JSN, 88.5% (92 of 104) for subchondral sclerosis, and 91.3% (95 of 104) for subchondral cysts in the external test set. Conclusion A multitask deep learning model is a feasible approach to reliably assess radiographic features of hip osteoarthritis. © RSNA, 2020 Online supplemental material is available for this article.

Six-month post-surgical elevations in cartilage T1rho relaxation times are associated with functional performance 2 years after ACL reconstruction.

The current study looks to: (i) investigate postural stability following anterior cruciate ligament (ACL) reconstruction, as assessed by Y-Balance Test, by comparing single-leg balance of the injured limb against those of controls and the uninjured limb; (ii) analyze the relationship between postural stability symmetry with localized cartilage matrix changes and the Knee Injury and Osteoarthritis Outcome Score (KOOS). Bilateral knee MRI of 36 patients who underwent ACL reconstruction were performed before surgery, 6 months, 1 year, and 2 years, postoperatively. Postural stability was evaluated based on Y-Balance Test at 1 and 2 years. ACL patients were also split into three groups based on postural stability symmetry at 2 years and symmetry thresholds associated with elevated risks of lower extremity injury. Voxel-based relaxometry employing analysis of covariance was used to analyze localized differences in cartilage composition at all time-points (using quantitative magnetic resonance [MR] T1ρ and T2 mapping) between the three groups. The ACL patients displayed no significant deficits in postural stability. Compared with symmetric patients, those with asymmetric postural stability at 2 years had significantly prolonged cartilage T1ρ-indicating deterioration of the cartilage matrix-specifically in the injured knee's medial tibia as early as 6-month post-reconstruction. Prolonged T1ρ in asymmetric patients persisted up to 2 years, where the group also reported worse KOOS. Our results demonstrate an association between early stages of cartilage matrix deterioration and postural stability symmetry that may manifest in elevated lower extremity injury risk and worse patient-reported outcomes. Quantitative MR, in combination with local analysis performed with voxel-based relaxometry, is a tool to further study this relationship. © 2019 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 38:1132-1140, 2020.

Deep Learning for Lesion Detection, Progression, and Prediction of Musculoskeletal Disease.

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 2020;52:1607-1619.

Anatomic shoulder parameters and their relationship to the presence of degenerative rotator cuff tears and glenohumeral osteoarthritis: a systematic review and meta-analysis.

BACKGROUND: Scapular anatomy, as measured by the acromial index (AI), critical shoulder angle (CSA), lateral acromial angle (LAA), and glenoid inclination (GI), has emerged as a possible contributor to the development of degenerative shoulder conditions such as rotator cuff tears and glenohumeral osteoarthritis. The purpose of this study was to investigate the published literature on influences of scapular morphology on the development of degenerative shoulder conditions. METHODS: A systematic review of the Embase and PubMed databases was performed to identify published studies on the potential influence of scapular bony morphology on the development of degenerative rotator cuff tears and glenohumeral osteoarthritis. The studies were reviewed by 2 authors. The findings were summarized for various anatomic parameters. A meta-analysis was completed for parameters reported in more than 5 related publications. RESULTS: A total of 660 unique titles and 55 potentially relevant abstracts were reviewed with 30 published articles identified for inclusion. The AI, CSA, LAA, and GI were the most commonly reported bony measurements. Increased CSA and AI correlated with rotator cuff tears, whereas lower CSA appeared to be related to the presence of glenohumeral osteoarthritis. Decreased LAA correlated with degenerative rotator cuff tears. Five articles reported on the GI with mixed results on shoulder pathology. DISCUSSION: Degenerative rotator cuff tears appear to be significantly associated with the AI, CSA, and LAA. There does not appear to be a significant relationship between the included shoulder parameters and the development of osteoarthritis.

Structural Changes over a Short Period Are Associated with Functional Assessments in Rheumatoid Arthritis.

OBJECTIVE: To investigate the correlation between changes in radiological quantitative assessment with changes in clinical and functional assessment from baseline to 3 months in patients with rheumatoid arthritis (RA). METHODS: Twenty-eight patients with RA [methotrexate (MTX) and anti-tumor necrosis factor-α (TNF-α) group with high disease activity (n = 18); and MTX group with low disease activity (n = 10)] underwent assessments at baseline and 3 months: clinical [28-joint count Disease Activity Score (DAS28)], functional [Health Assessment Questionnaire (HAQ) and Michigan Hand Outcome Questionnaire (MHQ)], and imaging-based [3 Tesla magnetic resonance imaging (MRI) and high-resolution peripheral quantitative computed tomography (HR-pQCT)]. MR images were evaluated semiquantitatively [RA MRI scoring (RAMRIS)] and quantitatively for the volume of synovitis and bone marrow edema (BME) lesions. Erosion volumes were measured using HR-pQCT. RESULTS: After 3 months, the anti-TNF-α group demonstrated an improvement in disease activity through DAS28, HAQ, and MHQ. MRI showed significant decreases in synovitis and BME volume for the anti-TNF-α group, and significant increases in the MTX group. HR-pQCT showed significant decreases in bone erosion volume for the anti-TNF-α group, and significant increases in the MTX group. No significance was observed using RAMRIS. Changes in synovitis, BME, and erosion volumes, but not RAMRIS, were significantly correlated with changes in DAS28, HAQ, and MHQ. CONCLUSION: Quantitative measures were more sensitive than semiquantitative grading when evaluating structural and inflammatory changes with treatment, and were associated with patient clinical and functional outcomes. Multimodality imaging with 3T MRI and HR-pQCT may provide promising biomarkers that help determine disease progression and therapy response.