Knee Images Research Articles

Beyond the patella: Treatment of cam femoroacetabular impingement syndrome improves anterior knee pain

ObjectivesThis study aimed to investigate if there is a relationship between cam femoroacetabular impingement syndrome (cam-FAIS) and chronic anterior knee pain (AKP). MethodsThis is a pilot retrospective review of 12 AKP patients with no structural anomalies in the patellofemoral joint and no skeletal malalignment in the lower limbs. All the patients were resistant to proper conservative treatment for AKP (AKP-R). Subsequently, these patients developed pain in the ipsilateral hip several months later, and upon evaluation, were diagnosed with cam-FAIS. Arthroscopic femoral osteoplasty and labral repair were performed and clinical follow-up of hip and knee pain and function (Kujala Score and Non-arthritic Hip Score -NAHS-) was carried out. ResultsAll the patients showed improvement in the knee and hip pain scores with a statistically significant clinical difference in all of them at 69 months follow up (range: 18 to 115) except one patient without improvement in the groin VAS score post-operatively. Visual analogical scale (VAS) of knee pain improved from 6.3 (range: 5 to 8) to a postoperative 0.5 (range: 0 to 3.5), (p ​< ​0.001). The VAS of groin pain improved from 4.4 (range: 2 to 8) to a postoperative 0.9 (range: 0 to 3), (p ​< ​0.001). NAHS improved from a preoperative 67.9 (range: 28.7 to 100) to a postoperative 88 (range: 70 to 100), (p ​< ​0.015) and knee Kujala's score improved from a preoperative 48.7 (range: 22 to 71) to a postoperative 96 (range: 91 to 100), (p ​< ​0.001). ConclusionThis study's principal finding suggests an association between cam-FAIS and AKP-R in young patients who exhibit normal knee imaging and lower limbs skeletal alignment. Addressing cam-FAIS in these cases leads to resolution of both groin and knee pain, resulting in improved functional outcomes for both joints. Study designRetrospective cohort series with a single contemporaneous long-term follow-up. Level of EvidenceIV.

Automated system for classifying uni-bicompartmental knee osteoarthritis by using redefined residual learning with convolutional neural network

Knee Osteoarthritis (OA) is one of the most common joint diseases that may cause physical disability associated with a significant personal and socioeconomic burden. X-ray imaging is the cheapest and most common method to detect Knee (OA). Accurate classification of knee OA can help physicians manage treatment efficiently and slow knee OA progression. This study aims to classify knee OA X-ray images according to anatomical types, such as uni or bicompartmental. The study proposes a deep learning model for classifying uni or bicompartmental knee OA based on redefined residual learning with CNN. The proposed model was trained, validated, and tested on a dataset containing 733 knee X-ray images (331 normal Knee images, 205 unicompartmental, and 197 bicompartmental knee images). The results show 61.81 % and 68.33 % for accuracy and specificity, respectively. Then, the performance of the proposed model was compared with different pre-trained CNNs. The proposed model achieved better results than all pre-trained CNNs.

Artificial intelligence–assisted ultrasound imaging in hemophilia: research, development, and evaluation of hemarthrosis and synovitis detection

BackgroundJoint bleeding can lead to synovitis and arthropathy in people with hemophilia, reducing quality of life. Although early diagnosis is associated with improved therapeutic outcomes, diagnostic ultrasonography requires specialist experience. Artificial intelligence (AI) algorithms may support ultrasonography diagnoses. ObjectivesThis study will research, develop, and evaluate the diagnostic precision of an AI algorithm for detecting the presence or absence of hemarthrosis and synovitis in people with hemophilia. MethodsElbow, knee, and ankle ultrasound images were obtained from people with hemophilia from January 2010 to March 2022. The images were used to train and test the AI models to estimate the presence/absence of hemarthrosis and synovitis. The primary endpoint was the area under the curve for the diagnostic precision to diagnose hemarthrosis and synovitis. Other endpoints were the rate of accuracy, precision, sensitivity, and specificity. ResultsOut of 5649 images collected, 3435 were used for analysis. The area under the curve for hemarthrosis detection for the elbow, knee, and ankle joints was ≥0.87 and for synovitis, it was ≥0.90. The accuracy and precision for hemarthrosis detection were ≥0.74 and ≥0.67, respectively, and those for synovitis were ≥0.83 and ≥0.74, respectively. Analysis across people with hemophilia aged 10 to 60 years showed consistent results. ConclusionAI models have the potential to aid diagnosis and enable earlier therapeutic interventions, helping people with hemophilia achieve healthy and active lives. Although AI models show potential in diagnosis, evidence is unclear on required control for abnormal findings. Long-term observation is crucial for assessing impact on joint health.

Water-Fat Separation for the Knee on a 50 mT Portable MRI Scanner.

The Dixon method is frequently employed in clinical and scientific research for fat suppression, because it has lower sensitivity to static magnetic field inhomogeneity compared to chemical shift selective saturation or its variants and maintains image signal-to-noise ratio (SNR). Recently, research on very-low-field (VLF < 100 mT) magnetic resonance imaging (MRI) has regained popularity. However, there is limited literature on water-fat separation in VLF MRI. Here, we present a modified two-point Dixon method specifically designed for VLF MRI. Most experiments were performed on a homemade 50 mT portable MRI scanner. The receiving coil adopted a homemade quadrature receiving coil. The data were acquired using spin-echo and gradient-echo sequences. We considered the T2* effect, and added priori information to existing two-point Dixon method. Then, the method used regional iterative phasor extraction (RIPE) to extract the error phasor. Finally, least squares solutions for water and fat were obtained and fat signal fraction was calculated. For phantom evaluation, water-only and fat-only images were obtained and the local fat signal fractions were calculated, with two samples being 0.94 and 0.93, respectively. For knee imaging, cartilage, muscle and fat could be clearly distinguished. The water-only images were able to highlight areas such as cartilage that could not be easily distinguished without separation. This work has demonstrated the feasibility of using a 50 mT MRI scanner for water-fat separation. To the best of our knowledge, this is the first reported result of water-fat separation at a 50 mT portable MRI scanner.

Automating Linear and Angular Measurements for the Hip and Knee After Computed Tomography: Validation of a Three-Stage Deep Learning and Computer Vision-Based Pipeline for Pathoanatomic Assessment

BackgroundVariability in the bony morphology of pathologic hips/knees is a challenge in automating preoperative computed tomography (CT) scan measurements. With the increasing prevalence of CT for advanced preoperative planning, processing this data represents a critical bottleneck in presurgical planning, research, and development. The purpose of this study was to demonstrate a reproducible and scalable methodology for analyzing CT-based anatomy to process hip and knee anatomy for perioperative planning and execution. MethodsOne hundred patients with preoperative CT scans undergoing total knee arthroplasty for osteoarthritis were processed. A two-step deep learning pipeline of classification and segmentation models was developed that identifies landmark images and then generates contour representations. We utilized an open-source computer vision library to compute measurements. Classification models were assessed by accuracy, precision, and recall. Segmentation models were evaluated using dice and mean Intersection over Union (IOU) metrics. Contour measurements were compared against manual measurements to validate posterior condylar axis angle, sulcus angle, trochlear groove-tibial tuberosity distance, acetabular anteversion, and femoral version. ResultsClassifiers identified landmark images with accuracy of 0.91 and 0.88 for hip and knee models, respectively. Segmentation models demonstrated mean IOU scores above 0.95 with the highest dice coefficient of 0.957 [0.954-0.961] (UNet3+) and the highest mean IOU of 0.965 [0.961-0.969] (Attention U-Net). There were no statistically significant differences for the measurements taken automatically vs manually (P > 0.05). Average time for the pipeline to preprocess (48.65 +/− 4.41 sec), classify/retrieve landmark images (8.36 +/− 3.40 sec), segment images (<1 sec), and obtain measurements was 2.58 (+/− 1.92) minutes. ConclusionsA fully automated three-stage deep learning and computer vision-based pipeline of classification and segmentation models accurately localized, segmented, and measured landmark hip and knee images for patients undergoing total knee arthroplasty. Incorporation of clinical parameters, like patient-reported outcome measures and instability risk, will be important considerations alongside anatomic parameters.

Artificial intelligence for detection of effusion and lipo-hemarthrosis in X-rays and CT of the knee

BackgroundTraumatic knee injuries are challenging to diagnose accurately through radiography and to a lesser extent, through CT, with fractures sometimes overlooked. Ancillary signs like joint effusion or lipo-hemarthrosis are indicative of fractures, suggesting the need for further imaging. Artificial Intelligence (AI) can automate image analysis, improving diagnostic accuracy and help prioritizing clinically important X-ray or CT studies. ObjectiveTo develop and evaluate an AI algorithm for detecting effusion of any kind in knee X-rays and selected CT images and distinguishing between simple effusion and lipo-hemarthrosis indicative of intra-articular fractures. MethodsThis retrospective study analyzed post traumatic knee imaging from January 2016 to February 2023, categorizing images into lipo-hemarthrosis, simple effusion, or normal. It utilized the FishNet-150 algorithm for image classification, with class activation maps highlighting decision-influential regions. The AI's diagnostic accuracy was validated against a gold standard, based on the evaluations made by a radiologist with at least four years of experience. ResultsAnalysis included CT images from 515 patients and X-rays from 637 post traumatic patients, identifying lipo-hemarthrosis, simple effusion, and normal findings. The AI showed an AUC of 0.81 for detecting any effusion, 0.78 for simple effusion, and 0.83 for lipo-hemarthrosis in X-rays; and 0.89, 0.89, and 0.91, respectively, in CTs. ConclusionThe AI algorithm effectively detects knee effusion and differentiates between simple effusion and lipo-hemarthrosis in post-traumatic patients for both X-rays and selected CT images further studies are needed to validate these results.

Gaussian Aquila optimizer based dual convolutional neural networks for identification and grading of osteoarthritis using knee joint images

Degenerative musculoskeletal disease known as Osteoarthritis (OA) causes serious pain and abnormalities for humans and on detecting at an early stage, timely treatment shall be initiated to the patients at the earliest to overcome this pain. In this research study, X-ray images are captured from the humans and the proposed Gaussian Aquila Optimizer based Dual Convolutional Neural Networks is employed for detecting and classifying the osteoarthritis patients. The new Gaussian Aquila Optimizer (GAO) is devised to include Gaussian mutation at the exploitation stage of Aquila optimizer, which results in attaining the best global optimal value. Novel Dual Convolutional Neural Network (DCNN) is devised to balance the convolutional layers in each convolutional model and the weight and bias parameters of the new DCNN model are optimized using the developed GAO. The novelty of the proposed work lies in evolving a new optimizer, Gaussian Aquila Optimizer for parameter optimization of the devised DCNN model and the new DCNN model is structured to minimize the computational burden incurred in spite of it possessing dual layers but with minimal number of layers. The knee dataset comprises of total 2283 knee images, out of which 1267 are normal knee images and 1016 are the osteoarthritis images with an image of 512 × 512-pixel width and height respectively. The proposed novel GAO-DCNN system attains the classification results of 98.25% of sensitivity, 98.93% of specificity and 98.77% of classification accuracy for abnormal knee case–knee joint images. Experimental simulation results carried out confirms the superiority of the developed hybrid GAO-DCNN over the existing deep learning neural models form previous literature studies.

The Dejour classification for trochlear dysplasia shows slight interobserver and substantial intraobserver reliability.

Trochlear dysplasia is one of the main risk factors for recurrent patellar dislocation. The Dejour classification identifies four categories that can be used to classify trochlear dysplasia. The purpose of this study is to evaluate the inter- and intraobserver reliability of the Dejour classification for trochlear dysplasia. The hypothesis was that both intra- and interobserver reliability would be at least moderate. This is a cross-sectional, reliability study. Twenty-eight examiners from the International Patellofemoral Study Group 2022 meeting evaluated lateral radiographs of the knee and axial magnetic resonance images from 15 cases of patellofemoral instability with trochlear dysplasia. They classified each case according to Dejour's classification for trochlear dysplasia (A-D). There were three rounds: one with only computed radiograph (CR), one with only magnetic resonance imaging (MRI) and one with both. Inter- and intraobserver reliability were calculated using κ coefficient (0-1). The mean age of patients was: 14.6 years; 60% were female and 53% had open physis. The interobserver reliability κ probabilities were 0.2 (CR), 0.13 (MRI) and 0.12 (CR and MRI). The intraobserver reliability κ probabilities were 0.45 (CR), 0.44 (MRI) and 0.65 (CR and MRI). The Dejour classification for trochlear dysplasia has slight interobserver reliability and substantial intraobserver reliability. Level I.

MR-based Bony 3D models enable radiation-free preoperative patient-specific analysis and 3D printing for SCFE patients.

Slipped capital femoral epiphyses (SCFE) is a common pediatric hip disease with the risk of osteoarthritis and impingement deformities, and 3D models could be useful for patient-specific analysis. Therefore, magnetic resonance imaging (MRI) bone segmentation and feasibility of 3D printing and of 3D ROM simulation using MRI-based 3D models were investigated. A retrospective study involving 22 symptomatic patients (22 hips) with SCFE was performed. All patients underwent preoperative hip MR with pelvic coronal high-resolution images (T1 images). Slice thickness was 0.8-1.2 mm. Mean age was 12 ± 2 years (59% male patients). All patients underwent surgical treatment. Semi-automatic MRI-based bone segmentation with manual corrections and 3D printing of plastic 3D models was performed. Virtual 3D models were tested for computer-assisted 3D ROM simulation of patients with knee images and were compared to asymptomatic contralateral hips with unilateral SCFE (15 hips, control group). MRI-based bone segmentation was feasible (all patients, 100%, in 4.5 h, mean 272 ± 52 min). Three-dimensional printing of plastic 3D models was feasible (all patients, 100%) and was considered helpful for deformity analysis by the treating surgeons for severe and moderate SCFE. Three-dimensional ROM simulation showed significantly (p < 0.001) decreased flexion (48 ± 40°) and IR in 90° of flexion (-14 ± 21°, IRF-90°) for severe SCFE patients with MRI compared to control group (122 ± 9° and 36 ± 11°). Slip angle improved significantly (p < 0.001) from preoperative 54 ± 15° to postoperative 4 ± 2°. MRI-based 3D models were feasible for SCFE patients. Three-dimensional models could be useful for severe SCFE patients for preoperative 3D printing and deformity analysis and for ROM simulation. This could aid for patient-specific diagnosis, treatment decisions, and preoperative planning. MRI-based 3D models are radiation-free and could be used instead of CT-based 3D models in the future.

Comparison of five different fluoroscopic methods for identifying the MPFL femoral footprint

PurposeThe success of medial patellofemoral ligament (MPFL) reconstruction is closely linked to the precise positioning of the femoral tunnel. Intraoperative fluoroscopy is commonly utilized to identify the MPFL footprint. This study aimed to ascertain the most accurate fluoroscopic method among the five previously described methods used to determine the MPFL femoral footprint.Materials and methodsUsing 44 well-preserved dry femur bones, the MPFL femoral insertion site was demarcated using anatomical bony landmarks, namely the center of the saddle sulcus between the medial epicondyle, adductor tubercle and gastrocnemius tubercle. Fluoroscopic true lateral knee images were acquired and measurements taken, referencing established methods by Schottle et al., Redfern et al., Wijdicks et al., Barnett et al., and Kaipel et al. The distance between anatomic and fluoroscopic MPFL footprints was then measured on digital fluoroscopic images. The accuracy of the locations was compared using a margin of error of 5 and 7 mm.ResultsThe Schottle method consistently emerged superior, showcasing the smallest mean distance (3.2 ± 1.2 mm) between the anatomic and radiographic MPFL footprints and a high in-point detection rate of 90.9% under 5 mm criteria. While the Redfern method displayed perfect accuracy (100%) within the 7 mm criteria, the Schottle method also performed 97.7% accuracy.ConclusionsFor intraoperative identification of the MPFL footprint using fluoroscopy, the Schottle method is the most consistent and accurate among the assessed methods. Thus, its accuracy in detecting the MPFL footprint makes it recommended for MPFLR to ensure optimal outcomes.Level of evidenceLevel IV, cadaveric study.

Knee cartilage MR images segmentation based on multi-dimensional hybrid convolutional neural network

Accurate segmentation of knee cartilage in MR images is crucial for early diagnosis and treatment of knee conditions. Manual segmentation is time-consuming, leading researchers to explore automatic deep learning methods. However, the choice between 2D and 3D networks for organ segmentation remains debated. In this paper, we propose a hybrid 2D and 3D deep neural network approach, named UVNet, which combines the strengths of both techniques to enhance segmentation performance. Within this network structure, the 3D segmentation network serves as the backbone for feature extraction, while the 2D segmentation network functions as an information supplement network. Local and global MIP images are generated by employing various maximum intensity projection modes of knee MRI volumes as input for the information supplement network. By constructing a local and global MIP feature fusion module, the supplementary information obtained from the 2D segmentation network is fully integrated into the backbone network. We assess the quality of the proposed method using the Osteoarthritis Initiative (OAI) dataset and the 2010 Grand Challenge Knee Image Segmentation (SKI-10) dataset, comparing it to the Baseline Network and other advanced 2D and 3D segmentation methods. The experiments demonstrate that UVNet achieves competitive performance in the aforementioned two cartilage segmentation tasks.

The medial knee gap measured on ultrasound images is wider during a valgus stress test compared to the anterior medial knee rotation test

AbstractObjectivesPatients with injuries to the deep fibers of the medial collateral ligament (dMCL) have a worse prognosis than patients with injuries to the superficial fibers (sMCL). The anterior medial (ANTMED) rotation test has been developed to differentiate between injuries to the dMCL and sMCL. The current study tested the hypothesis that the width of the medial knee gap would be greater during the valgus stress test than the ANTMED rotation test.MethodsFifty‐three participants were included in the study. Participants did not have a history of knee injury. Ultrasound images of the participants' medial knees were collected during the valgus stress test and the ANTMED rotation test. Repeated measures ANOVA was used to test differences in the medial knee gap between the tests, stress condition, and side.ResultsNo difference between the tests in the medial knee joint gap width in the no‐stress condition. The increase in the joint gap width was greater during the valgus stress test than the ANTMED rotation test. The medial knee gap increased during both the valgus stress (4.0 ± 0.12 mm) and the ANTMED rotation test (2.9 ± 0.12 mm).ConclusionsA greater increase in the medial knee gap was seen during the valgus stress test compared to the ANTMED rotation test. Knee external rotation increases the tension within the dMCL. Increased tension in the dMCL could explain the test differences in the increase in the joint gap found in the current study. The ANTMED rotation test may prove useful to identify injury to the dMCL.

Machine learning diagnosis of active Juvenile Idiopathic Arthritis on blood pool [ 99M Tc] Tc-MDP scintigraphy images.

Neural network has widely been applied for medical classifications and disease diagnosis. This study employs deep learning to best discriminate Juvenile Idiopathic Arthritis (JIA), a pediatric chronic joint inflammatory disease, from healthy joints by exploring blood pool images of 2phase [ 99m Tc] Tc-MDP bone scintigraphy. Self-deigned multi-input Convolutional Neural Network (CNN) in addition to three available pre-trained models including VGG16, ResNet50 and Xception are applied on 1304 blood pool images of 326 healthy and known JIA children and adolescents (aged 1-16). The self-designed model ROC analysis shows diagnostic efficiency with Area Under the Curve (AUC) 0.82 and 0.86 for knee and ankle joints, respectively. Among the three pertained models, VGG16 ROC analysis reveals AUC 0.76 and 0.81 for knee and ankle images, respectively. The self-designed model shows best performance on blood pool scintigraph diagnosis of patients with JIA. VGG16 was the most efficient model rather to other pre-trained networks. This study can pave the way of artificial intelligence (AI) application in nuclear medicine for the diagnosis of pediatric inflammatory disease.

Impact of Electronic Collimation on Reducing Unnecessary Patient Dose in Digital Radiography.

In radiology, optimizing radiation protection is crucial, and field collimation plays a critical role in minimizing patient dose. As technology has evolved, electronic collimation has become the preferred method due to its effectiveness in digital imaging systems, replacing traditional film-screen systems. The current study aimed to investigate the prevalence of cropping in digital radiography and its potential impact on patient radiation dose because of improper collimation practices. This retrospective analysis was conducted on digital X-ray machine images. Quality control tests were performed to ensure equipment accuracy, and image cropping was then measured by analyzing archived images. Finally, the cropped image fraction and associated unnecessary radiation doses were calculated. Quality control tests confirmed that all imaging equipment was functioned within acceptable alignment and angle tolerances. The analysis of 911 images revealed a high prevalence of cropping (82%), with significant variation across different projections. Lateral knee images exhibited the highest cropping rate (96.2%), while abdominal images had the lowest (36.1%). Electronic image cropping can lead radiologic technologists to inaccurately define the primary radiation field, affecting image quality and potentially increasing patient radiation exposure. Based on the obtained results, proper collimation can reduce the average Dose Area Product (DAP) by 29.01%. This approach not only enhances patient safety but also minimizes unnecessary radiation exposure and potentially reduces healthcare costs.

Synthetic Knee MRI T1p Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis Biomarkers.

A 2D U-Net was trained to generate synthetic T1p maps from T2 maps for knee MRI to explore the feasibility of domain adaptation for enriching existing datasets and enabling rapid, reliable image reconstruction. The network was developed using 509 healthy contralateral and injured ipsilateral knee images from patients with ACL injuries and reconstruction surgeries acquired across three institutions. Network generalizability was evaluated on 343 knees acquired in a clinical setting and 46 knees from simultaneous bilateral acquisition in a research setting. The deep neural network synthesized high-fidelity reconstructions of T1p maps, preserving textures and local T1p elevation patterns in cartilage with a normalized mean square error of 2.4% and Pearson's correlation coefficient of 0.93. Analysis of reconstructed T1p maps within cartilage compartments revealed minimal bias (-0.10 ms), tight limits of agreement, and quantification error (5.7%) below the threshold for clinically significant change (6.42%) associated with osteoarthritis. In an out-of-distribution external test set, synthetic maps preserved T1p textures, but exhibited increased bias and wider limits of agreement. This study demonstrates the capability of image synthesis to reduce acquisition time, derive meaningful information from existing datasets, and suggest a pathway for standardizing T1p as a quantitative biomarker for osteoarthritis.

Advancing Wearable Electromagnetic Knee Imaging: A Comprehensive Review of Systems, Frameworks, Key Challenges, and Future Directions

Advancing Wearable Electromagnetic Knee Imaging: A Comprehensive Review of Systems, Frameworks, Key Challenges, and Future Directions

11 C]-PBR28 positron emission tomography signal as an imaging marker of joint inflammation in knee osteoarthritis.

Although inflammation is known to play a role in knee osteoarthritis (KOA), inflammation-specific imaging is not routinely performed. In this article, we evaluate the role of joint inflammation, measured using [ 11 C]-PBR28, a radioligand for the inflammatory marker 18-kDa translocator protein (TSPO), in KOA. Twenty-one KOA patients and 11 healthy controls (HC) underwent positron emission tomography/magnetic resonance imaging (PET/MRI) knee imaging with the TSPO ligand [ 11 C]-PBR28. Standardized uptake values were extracted from regions-of-interest (ROIs) semiautomatically segmented from MRI data, and compared across groups (HC, KOA) and subgroups (unilateral/bilateral KOA symptoms), across knees (most vs least painful), and against clinical variables (eg, pain and Kellgren-Lawrence [KL] grades). Overall, KOA patients demonstrated elevated [ 11 C]-PBR28 binding across all knee ROIs, compared with HC (all P 's < 0.005). Specifically, PET signal was significantly elevated in both knees in patients with bilateral KOA symptoms (both P 's < 0.01), and in the symptomatic knee ( P < 0.05), but not the asymptomatic knee ( P = 0.95) of patients with unilateral KOA symptoms. Positron emission tomography signal was higher in the most vs least painful knee ( P < 0.001), and the difference in pain ratings across knees was proportional to the difference in PET signal ( r = 0.74, P < 0.001). Kellgren-Lawrence grades neither correlated with PET signal (left knee r = 0.32, P = 0.19; right knee r = 0.18, P = 0.45) nor pain ( r = 0.39, P = 0.07). The current results support further exploration of [ 11 C]-PBR28 PET signal as an imaging marker candidate for KOA and a link between joint inflammation and osteoarthritis-related pain severity.

New concept of orthosis treatment for knee osteoarthritis: Clinical and radiological outcomes.

Given the increasing numbers of young patients with knee osteoarthritis there is a need for treatments that can postpone a joint prosthesis (total knee replacement). As an alternative to the effective yet invasive knee joint distraction procedure, a knee orthosis was developed aiming to unload the affected knee and improving synovial fluid flow. The aim of this study was to examine the effectiveness of using a load-reducing orthosis for two months on functioning, pain, and disease progression (e.g. amount of damaged cartilage) in patients with symptomatic osteoarthritis of the knee for at least one year. This is an interventional single-center pilot study. Ten patients with symptomatic osteoarthritis of one knee (5males/5 females; median age 57; age range 42-59) used a custom-made orthosis for 60 days during daily life activities that involved knee loading (e.g. standing, walking, but not during stair climbing). Cycling was not allowed. Clinical outcomes were assessed up to 24 months after intervention at 6 timepoints using patient reported-outcome measures Western Ontario and McMaster Universities Osteoarthritis (WOMAC) range 0-100; Visual Analogue Scale (VAS), range 0-100 for pain. Minimum joint space width (mJSW) was assessed using knee images digital analysis (KIDA) and articular cartilage volume with magnetic resonance imaging (MRI) using custom software at baseline and at 12 and 24 months follow-up. Clinically beneficial effects were found for functioning (WOMAC improvement compared to baseline ranged between 18 points at 3 months follow-up and 31 points at 12 months follow-up, with only the 24-months follow-up (improvement of 27 points) not reaching statistical significance (p< 0.05)) and for pain (VAS improvement compared to baseline at follow-up time points ranged between 41-56 points; all p< 0.05). No improvements in mJSW- or MRI-derived parameters were found. This study demonstrates that use of a custom-made knee-unloading orthosis for 60 days can result in improved functional ability and decrease in pain in relatively young patients with knee osteoarthritis. No effect on disease progression could be evidenced.

Magnetic resonance imaging of knees: a novel approach to predict recombinant human growth hormone therapy response in short-stature children in late puberty.

There is no appropriate tool to predict recombinant human growth hormone (rhGH) response before therapy initiation in short-stature children in late puberty. The current study aimed to explore the associations between magnetic resonance imaging (MRI) stages of the knee growth plates and rhGH response in short-stature children in late puberty. In this prospective cohort study, short-stature children in late puberty were treated with rhGH and followed up for 6 months. We proposed a novel knee MRI staging system according to the growth plate states of distal femurs or proximal tibias and divided the participants into three groups: unclosed growth plate group, marginally closed growth plate group, and nearly closed growth plate group. The primary outcomes were height gain and growth velocity (GV), which were assessed three months later. Fifty participants were enrolled, including 23 boys and 27 girls. GV and height gain after 6 months of rhGH therapy decreased successively in the three groups with an increased degree of growth plate fusion, especially when grouped by proximal tibias (GV1-3 mon from 9.38 to 6.08 to 4.56cm/year, GV4-6 mon from 6.75 to 4.92 to 3.25cm/year, and height gain from 4.03 to 2.75 to 1.95cm, all P < 0.001). Moreover, the MRI stages of growth plates independently served as a significant variable for GV and height gain after therapy, especially when grouped by proximal tibias (all P < 0.01). The MRI staging method is expected to be an effective tool for predicting rhGH response before therapy initiation in short-stature children in late puberty.

Highly accelerated knee magnetic resonance imaging using deep neural network (DNN)–based reconstruction: prospective, multi-reader, multi-vendor study

In this prospective, multi-reader, multi-vendor study, we evaluated the performance of a commercially available deep neural network (DNN)–based MR image reconstruction in enabling accelerated 2D fast spin-echo (FSE) knee imaging. Forty-five subjects were prospectively enrolled and randomly divided into three 3T MRIs. Conventional 2D FSE and accelerated 2D FSE sequences were acquired for each subject, and the accelerated FSE images were reconstructed and enhanced with DNN–based reconstruction software (FSE-DNN). Quantitative assessments and diagnostic performances were independently evaluated by three musculoskeletal radiologists. For statistical analyses, paired t-tests, and Pearson’s correlation were used for image quality comparison and inter-reader agreements. Accelerated FSE-DNN reduced scan times by 41.0% on average. FSE-DNN showed better SNR and CNR (p < 0.001). Overall image quality of FSE-DNN was comparable (p > 0.05), and diagnostic performances of FSE-DNN showed comparable lesion detection. Two of cartilage lesions were under-graded or over-graded (n = 2) while there was no significant difference in other image sets (n = 43). Overall inter-reader agreement between FSE-conventional and FSE-DNN showed good agreement (R2 = 0.76; p < 0.001). In conclusion, DNN-based reconstruction can be applied to accelerated knee imaging in multi-vendor MRI scanners, with reduced scan time and comparable image quality. This study suggests the potential for DNN-accelerated knee MRI in clinical practice.