Evolutionary Selection and Constraint on Human Knee Chondrocyte Regulation Impacts Osteoarthritis Risk.

During human evolution, the knee adapted to the biomechanical demands of bipedalism by altering chondrocyte developmental programs. This adaptive process was likely not without deleterious consequences to health. Today, osteoarthritis occurs in 250 million people, with risk variants enriched in non-coding sequences near chondrocyte genes, loci that likely became optimized during knee evolution. We explore this relationship by epigenetically profiling joint chondrocytes, revealing ancient selection and recent constraint and drift on knee regulatory elements, which also overlap osteoarthritis variants that contribute to disease heritability by tending to modify constrained functional sequence. We propose a model whereby genetic violations to regulatory constraint, tolerated during knee development, lead to adult pathology. In support, we discover a causal enhancer variant (rs6060369) present in billions of people at a risk locus (GDF5-UQCC1), showing how it impacts mouse knee-shape and osteoarthritis. Overall, our methods link an evolutionarily novel aspect of human anatomy to its pathogenesis.

The RIPK4-IRF6 signalling axis safeguards epidermal differentiation and barrier function.

The integrity of the mammalian epidermis depends on a balance of proliferation and differentiation in the resident population of stem cells1. The kinase RIPK4 and the transcription factor IRF6 are mutated in severe developmental syndromes in humans, and mice lacking these genes display epidermal hyperproliferation and soft-tissue fusions that result in neonatal lethality2-5. Our understanding of how these genes control epidermal differentiation is incomplete. Here we show that the role of RIPK4 in mouse development requires its kinase activity; that RIPK4 and IRF6 expressed in the epidermis regulate the same biological processes; and that the phosphorylation of IRF6 at Ser413 and Ser424 primes IRF6 for activation. Using RNA sequencing (RNA-seq), histone chromatin immunoprecipitation followed by sequencing (ChIP-seq) and assay for transposase-accessible chromatin using sequencing (ATAC-seq) of skin in wild-type and IRF6-deficient mouse embryos, we define the transcriptional programs that are regulated by IRF6 during epidermal differentiation. IRF6 was enriched at bivalent promoters, and IRF6 deficiency caused defective expression of genes that are involved in the metabolism of lipids and the formation of tight junctions. Accordingly, the lipid composition of the stratum corneum of Irf6-/- skin was abnormal, culminating in a severe defect in the function of the epidermal barrier. Collectively, our results explain how RIPK4 and IRF6 function to ensure the integrity of the epidermis and provide mechanistic insights into why developmental syndromes that are characterized by orofacial, skin and genital abnormalities result when this axis goes awry.

Time-of-day effects on motor unit firing and muscle contractile properties in humans.

Intrinsic factors related to neuromuscular function are time-of-day dependent, but diurnal rhythms in neural and muscular components of the human neuromuscular system remain unclear. The present study aimed to investigate the time-of-day effects on neural excitability and muscle contractile properties by assessing the firing properties of tracked motor units and electrically evoked twitch muscle contraction. In 15 young adults (22.9 ± 4.7 yr), neuromuscular function was measured in the morning (10:00), at noon (13:30), in the evening (17:00), and at night (20:30). Four measurements were completed within 24 h. The measurements consisted of maximal voluntary contraction (MVC) strength of knee extension, recording of high-density surface electromyography (HDsEMG) from the vastus lateralis during ramp-up contraction to 50% of MVC, and evoked twitch torque of knee extensors by electrical stimulation. Recorded HDsEMG signals were decomposed to individual motor unit firing behaviors and the same motor units were tracked among the times of day, and recruitment thresholds and firing rates were calculated. The number of detected and tracked motor units was 127. Motor unit firing rates significantly increased from morning to noon, evening, and night (P < 0.01), but there were no significant differences in recruitment thresholds among the times of day (P > 0.05). Also, there were no significant effects of time of day on evoked twitch torque (P > 0.05). Changes in the motor unit firing rate and evoked twitch torque were not significantly correlated (P > 0.05). These findings suggest that neural excitability may be affected by the time of day, but it did not accompany changes in peripheral contractile properties in a diurnal manner.NEW & NOTEWORTHY We investigated the variations of tracked motor unit firing properties and electrically evoked twitch contraction during the day within 24 h. The variation of motor unit firing rate was observed, and tracked motor unit firing rate increased at noon, in the evening, and at night compared with that in the morning. The variation in motor unit firing rate was independent of changes in twitch contraction. Motor unit firing rate may be affected by diurnal rhythms.

Integrating data distribution prior via Langevin dynamics for end-to-end MR reconstruction.

PURPOSE: To develop a novel deep learning-based method inheriting the advantages of data distribution prior and end-to-end training for accelerating MRI. METHODS: Langevin dynamics is used to formulate image reconstruction with data distribution before facilitate image reconstruction. The data distribution prior is learned implicitly through the end-to-end adversarial training to mitigate the hyper-parameter selection and shorten the testing time compared to traditional probabilistic reconstruction. By seamlessly integrating the deep equilibrium model, the iteration of Langevin dynamics culminates in convergence to a fix-point, ensuring the stability of the learned distribution. RESULTS: The feasibility of the proposed method is evaluated on the brain and knee datasets. Retrospective results with uniform and random masks show that the proposed method demonstrates superior performance both quantitatively and qualitatively than the state-of-the-art. CONCLUSION: The proposed method incorporating Langevin dynamics with end-to-end adversarial training facilitates efficient and robust reconstruction for MRI. Empirical evaluations conducted on brain and knee datasets compellingly demonstrate the superior performance of the proposed method in terms of artifact removing and detail preserving.

Improving quantitative MRI using self-supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping.

PURPOSE: This paper proposes a novel self-supervised learning framework that uses model reinforcement, REference-free LAtent map eXtraction with MOdel REinforcement (RELAX-MORE), for accelerated quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll an iterative model-based qMRI reconstruction into a deep learning framework, enabling accelerated MR parameter maps that are highly accurate and robust. METHODS: Unlike conventional deep learning methods which require large amounts of training data, RELAX-MORE is a subject-specific method that can be trained on single-subject data through self-supervised learning, making it accessible and practically applicable to many qMRI studies. Using quantitative T 1 $$ {\mathrm{T}}_1 $$ mapping as an example, the proposed method was applied to the brain, knee and phantom data. RESULTS: The proposed method generates high-quality MR parameter maps that correct for image artifacts, removes noise, and recovers image features in regions of imperfect image conditions. Compared with other state-of-the-art conventional and deep learning methods, RELAX-MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping. CONCLUSION: This work demonstrates the feasibility of a new self-supervised learning method for rapid MR parameter mapping, that is readily adaptable to the clinical translation of qMRI.

Constructing a clinical radiographic knee osteoarthritis database using artificial intelligence tools with limited human labor: A proof of principle.

OBJECTIVE: To create a scalable and feasible retrospective consecutive knee osteoarthritis (OA) radiographic database with limited human labor using commercial and custom-built artificial intelligence (AI) tools. METHODS: We applied four AI tools, two commercially available and two custom-built tools, to analyze 6 years of clinical consecutive knee radiographs from patients aged 35-79 at the University of Copenhagen Hospital, Bispebjerg-Frederiksberg Hospital, Denmark. The tools provided Kellgren-Lawrence (KL) grades, joint space widths, patella osteophyte detection, radiographic view detection, knee joint implant detection, and radiographic marker detection. RESULTS: In total, 25,778 knee radiographs from 8575 patients were included in the database after excluding inapplicable radiographs, and 92.5% of the knees had a complete OA dataset. Using the four AI tools, we saved about 800 hours of radiologist reading time and only manually reviewed 16.0% of the images in the database. CONCLUSIONS: This study shows that clinical knee OA databases can be built using AI with limited human reading time for uniform grading and measurements. The concept is scalable temporally and across geographic regions and could help diversify further OA research by efficiently including radiographic knee OA data from different populations globally. We can prevent data dredging and overfitting OA theories on existing trite cohorts by including various gene pools and continuous expansion of new clinical cohorts. Furthermore, the suggested tools and applied approaches provide an ability to retest previous hypotheses and test new hypotheses on real-life clinical data with current disease prevalence and trends.

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

OBJECTIVE: The first publication on morphometric analysis of articular cartilage using magnetic resonance imaging (MRI) in 1994 set the scene for a game change in osteoarthritis (OA) research. The current review highlights milestones in cartilage and bone morphometry, summarizing the rapid progress made in imaging, its application to understanding joint (patho-)physiology, and its use in interventional clinical trials. METHODS: Based on a Pubmed search of articles from 1994 to 2023, the authors subjectively selected representative work illustrating important steps in the development or application of magnetic resonance-based cartilage and bone morphometry, with a focus on studies in humans, and on the knee. Research on OA-pathophysiology is addressed only briefly, given length constraints. Compositional and semi-quantitative assessment are not covered here. RESULTS: The selected articles are presented in historical order as well as by content. We review progress in the technical aspects of image acquisition, segmentation and analysis, advances in understanding tissue growth, physiology, function, and adaptation, and a selection of clinical trials examining the efficacy of interventions on knee cartilage and bone. A perspective is provided of how lessons learned may be applied to future research and clinical management. CONCLUSIONS: Over the past 30 years, MRI-based morphometry of cartilage and bone has contributed to a paradigm shift in understanding articular tissue physiology and OA pathophysiology, and to the development of new treatment strategies. It is likely that these technologies will continue to play a key role in the development and (accelerated) approval of therapy, potentially targeted to different OA phenotypes.

Is thoracolumbar fascia shear-wave modulus affected by active and passive knee flexion?

The purpose of this study was to examine the effect of passive and active knee flexion efforts on the stiffness of the thoracolumbar (TLF), semitendinosus (STF), and semimembranosus fascia (SMF). Fourteen young healthy males participated in this study. Using ultrasound shear-wave elastography, fascia elastic modulus was measured at rest (passive condition) and during submaximal isometric knee flexion efforts (active condition) with the hip at neutral position and the knee flexed at 0°, 45°, and 90°. Analysis of variance designs indicated that when the knee was passively extended from 90° to 0°, shear modulus of the TLF, SMF, and STF increased significantly (p < 0.05). Similarly, active knee flexion contractions caused a significant increase in TLF, SMF, and STF shear modulus (p < 0.001). Compared to hamstring fascia, the TLF showed greater thickness but a lower shear modulus (p < 0.05) while STF modulus was greater compared that to SMF during active contraction (p < 0.05). These results indicate that exercising the hamstring muscles can remotely influence the stiffness of the fascia which surrounds the lumbar area.

Sensorimotor control in the congenital absence of functional muscle spindles.

Hereditary sensory and autonomic neuropathy type III (HSAN III), also known as familial dysautonomia or Riley-Day syndrome, results from an autosomal recessive genetic mutation that causes a selective loss of specific sensory neurones, leading to greatly elevated pain and temperature thresholds, poor proprioception, marked ataxia and disturbances in blood pressure control. Stretch reflexes are absent throughout the body, which can be explained by the absence of functional muscle spindle afferents - assessed by intraneural microelectrodes inserted into peripheral nerves in the upper and lower limbs. This also explains the greatly compromised proprioception at the knee joint, as assessed by passive joint-angle matching. Moreover, there is a tight correlation between loss of proprioceptive acuity at the knee and the severity of gait impairment. Surprisingly, proprioception is normal at the elbow, suggesting that participants are relying more on sensory cues from the overlying skin; microelectrode recordings have shown that myelinated tactile afferents in the upper and lower limbs appear to be normal. Nevertheless, the lack of muscle spindles does affect sensorimotor control in the upper limb: in addition to poor performance in the finger-to-nose test, manual performance in the Purdue pegboard task is much worse than in age-matched healthy controls. Unlike those rare individuals with large-fibre sensory neuropathy, in which both muscle spindle and cutaneous afferents are absent, those with HSAN III present as a means of assessing sensorimotor control following the selective loss of muscle spindle afferents.

Knee movements cause changes in the firing behaviour of muscle spindles located within the mono-articular ankle extensor soleus in the rat.

We recently showed that within an intact muscle compartment, changing the length of one muscle affects the firing behaviour of muscle spindles located within a neighbouring muscle. The conditions tested, however, involved muscle lengths and relative positions that were beyond physiological ranges. The aim of the present study was to investigate the effects of simulated knee movements on the firing behaviour of muscle spindles located within rat soleus (SO) muscle. Firing from single muscle spindle afferents in SO was measured intra-axonally for different lengths (static) and during lengthening (dynamic) of the lateral gastrocnemius and plantaris muscles. Also, the location of the spindle within the muscle was assessed. Changing the length of synergistic ankle plantar flexors (simulating different static knee positions, between 45 and 130°) affected the force threshold, but not the length threshold, of SO muscle spindles. The effects on type II afferents were substantially (four times) higher than those on type IA afferents. Triangular stretch-shortening of synergistic muscles (simulating dynamic knee joint rotations of 15°) caused sudden changes in the firing rate of SO type IA and II afferents. Lengthening decreased and shortening increased the firing rate, independent of spindle location. This supports our prediction that the major point of application of forces exerted by connections between adjacent muscles is at the distal end of SO. We conclude that muscle spindles provide the CNS with information about the condition of adjacent joints that the muscle does not span.

Vascular dysfunction and the age-related decline in critical power.

Ageing results in lower exercise tolerance, manifested as decreased critical power (CP). We examined whether the age-related decrease in CP occurs independently of changes in muscle mass and whether it is related to impaired vascular function. Ten older (63.1 ± 2.5 years) and 10 younger (24.4 ± 4.0 years) physically active volunteers participated. Physical activity was measured with accelerometry. Leg muscle mass was quantified with dual X-ray absorptiometry. The CP and maximum power during a graded exercise test (PGXT ) of single-leg knee-extension exercise were determined over the course of four visits. During a fifth visit, vascular function of the leg was assessed with passive leg movement (PLM) hyperaemia and leg blood flow and vascular conductance during knee-extension exercise at 10 W, 20 W, slightly below CP (90% CP) and PGXT . Despite not differing in leg lean mass (P = 0.901) and physical activity (e.g., steps per day, P = 0.735), older subjects had ∼30% lower mass-specific CP (old = 3.20 ± 0.94 W kg-1 vs. young = 4.60 ± 0.87 W kg-1 ; P < 0.001). The PLM-induced hyperaemia and leg blood flow and/or conductance were blunted in the old at 20 W, 90% CP and PGXT (P < 0.05). When normalized for leg muscle mass, CP was strongly correlated with PLM-induced hyperaemia (R2  = 0.52; P < 0.001) and vascular conductance during knee-extension exercise at 20 W (R2  = 0.34; P = 0.014) and 90% CP (R2  = 0.39; P = 0.004). In conclusion, the age-related decline in CP is not only an issue of muscle quantity, but also of impaired muscle quality that corresponds to impaired vascular function.

Post-activation potentiation after isometric contractions is strongly related to contraction intensity despite the similar torque-time integral.

Post-activation potentiation (PAP) is defined as an enhanced contractile response of a muscle following its own contractile activity and is influenced by the intensity and duration of the conditioning contraction. The aim of this study was to determine if the combination of intensity and duration, that is, torque-time integral (TTI) is a determinant of PAP amplitude. We compared PAP amplitude following low-to-maximal voluntary conditioning contraction intensities with and without similar TTI in the knee extensors. Twelve healthy males completed two experimental sessions. Femoral nerve stimulation was applied to evoke single twitches on the relaxed quadriceps before and after isometric conditioning contractions of knee extensors. In one session, participants performed conditioning contractions without similar TTI (6 s at 100, 80, 60, 40 and 20% maximal voluntary contraction (MVC)), while they performed conditioning contractions with similar TTI in the other session (6 s at 100%, 7.5 s at 80%, 10 s at 60%, 15 s at 40%, and 30 s at 20% MVC). In both sessions, PAP amplitude was related to conditioning contraction intensity. The higher the conditioning contraction intensity with or without similar TTI, the higher PAP. Significant correlations were found (i) between PAP and conditioning contraction intensity with (r2 = 0.70; P < 0.001) or without similar TTI (r2 = 0.64; P < 0.001), and (ii) between PAP with and without similar TTI (r2 = 0.82; P < 0.001). The results provide evidence that TTI has a minor influence on PAP in the knee extensors. This suggests that to optimize the effect of PAP, it is more relevant to control the intensity of the contraction rather than the TTI.

Combined action observation and mental imagery versus neuromuscular electrical stimulation as novel therapeutics during short-term knee immobilization.

Limb immobilization causes rapid declines in muscle strength and mass. Given the role of the nervous system in immobilization-induced weakness, targeted interventions may be able to preserve muscle strength, but not mass, and vice versa. The purpose of this study was to assess the effects of two distinct interventions during 1 week of knee joint immobilization on muscle strength (isometric and concentric isokinetic peak torque), mass (bioimpedance spectroscopy and ultrasonography), and neuromuscular function (transcranial magnetic stimulation and interpolated twitch technique). Thirty-nine healthy, college-aged adults (21 males, 18 females) were randomized into one of four groups: immobilization only (n = 9), immobilization + action observation/mental imagery (AOMI) (n = 10), immobilization + neuromuscular electrical stimulation (NMES) (n = 12), or control group (n = 8). The AOMI group performed daily video observation and mental imagery of knee extensions. The NMES group performed twice daily stimulation of the quadriceps femoris. Based on observed effect sizes, it appears that AOMI shows promise as a means of preserving voluntary strength, which may be modulated by neural adaptations. Strength increased from PRE to POST in the AOMI group, with +7.2% (Cohen's d = 1.018) increase in concentric isokinetic peak torque at 30°/s. However, NMES did not preserve muscle mass. Though preliminary, our findings highlight the specific nature of clinical interventions and suggest that muscle strength can be independently targeted during rehabilitation. This study was prospectively registered: ClinicalTrials.gov NCT05072652.

Genicular Artery Embolization: A Review of Essential Anatomic Considerations.

Genicular artery embolization is increasingly recognized as a safe and effective treatment option for symptomatic knee osteoarthritis and recurrent hemarthrosis after total knee arthroplasty. Genicular arteries are an essential contributor to vascular supply for the knee joint and demonstrate considerable variability. Familiarity with the anatomy and common variations is critical for preprocedural planning, accurate target selection, and minimizing adverse events in transarterial embolization procedures. This review aimed to provide a detailed discussion of the genicular artery anatomy that is relevant to interventional radiologists performing genicular artery embolization.

Reliability of transcranial magnetic stimulation-evoked responses on knee extensor muscles during cycling.

Transcranial magnetic stimulation (TMS) measures the excitability and inhibition of corticomotor networks. Despite its task-specificity, few studies have used TMS during dynamic movements and the reliability of TMS paired pulses has not been assessed during cycling. This study aimed to evaluate the reliability of motor evoked potentials (MEP) and short- and long-interval intracortical inhibition (SICI and LICI) on vastus lateralis and rectus femoris muscle activity during a fatiguing single-leg cycling task. Nine healthy adults (2 female) performed two identical sessions of counterweighted single-leg cycling at 60% peak power output until failure. Five single pulses and ten paired pulses were delivered to the motor cortex, and two maximal femoral nerve stimulations (Mmax) were administered during two baseline cycling bouts (unfatigued) and every 5 min throughout cycling (fatigued). When comparing both baseline bouts within the same session, MEP·Mmax-1 and LICI (both ICC: >0.9) were rated excellent while SICI was rated good (ICC: 0.7-0.9). At baseline, between sessions, in the vastus lateralis, Mmax (ICC: >0.9) and MEP·Mmax-1 (ICC: 0.7) demonstrated good reliability; LICI was moderate (ICC: 0.5), and SICI was poor (ICC: 0.3). Across the fatiguing task, Mmax demonstrated excellent reliability (ICC > 0.8), MEP·Mmax-1 ranged good to excellent (ICC: 0.7-0.9), LICI was moderate to excellent (ICC: 0.5-0.9), and SICI remained poorly reliable (ICC: 0.3-0.6). These results corroborate the cruciality of retaining mode-specific testing measurements and suggest that during cycling, Mmax, MEP·Mmax-1, and LICI measures are reliable whereas SICI, although less reliable across days, can be reliable within the same session.

Abnormal interlimb coordination of motor developmental delay during infant crawling based on kinematic synergy analysis.

BACKGROUND: Previous studies have reported that abnormal interlimb coordination is a typical characteristic of motor developmental delay (MDD) during human movement, which can be visually manifested as abnormal motor postures. Clinically, the scale assessments are usually used to evaluate interlimb coordination, but they rely heavily on the subjective judgements of therapists and lack quantitative analysis. In addition, although abnormal interlimb coordination of MDD have been studied, it is still unclear how this abnormality is manifested in physiology-related kinematic features. OBJECTIVES: This study aimed to evaluate how abnormal interlimb coordination of MDD during infant crawling was manifested in the stability of joints and limbs, activation levels of synergies and intrasubject consistency from the kinematic synergies of tangential velocities of joints perspective. METHODS: Tangential velocities of bilateral shoulder, elbow, wrist, hip, knee and ankle over time were computed from recorded three-dimensional joint trajectories in 40 infants with MDD [16 infants at risk of developmental delay, 11 infants at high risk of developmental delay, 13 infants with confirmed developmental delay (CDD group)] and 20 typically developing infants during hands-and-knees crawling. Kinematic synergies and corresponding activation coefficients were derived from those joint velocities using the non-negative matrix factorization algorithm. The variability accounted for yielded by those synergies and activation coefficients, and the synergy weightings in those synergies were used to measure the stability of joints and limbs. To quantify the activation levels of those synergies, the full width at half maximum and center of activity of activation coefficients were calculated. In addition, the intrasubject consistency was measured by the cosine similarity of those synergies and activation coefficients. RESULTS: Interlimb coordination patterns during infant crawling were the combinations of four types of single-limb movements, which represent the dominance of each of the four limbs. MDD mainly reduced the stability of joints and limbs, and induced the abnormal activation levels of those synergies. Meanwhile, MDD generally reduced the intrasubject consistency, especially in CDD group. CONCLUSIONS: These features have the potential for quantitatively evaluating abnormal interlimb coordination in assisting the clinical diagnosis and motor rehabilitation of MDD.

Weekly pain trajectories among people with knee or hip osteoarthritis participating in a digitally delivered first-line exercise and education treatment.

OBJECTIVE: Digital self-management programs are increasingly used in the management of osteoarthritis (OA). Little is known about heterogeneous patterns in response to these programs. We describe weekly pain trajectories of people with knee or hip OA over up to 52-week participation in a digital self-management program. METHODS: Observational cohort study among participants enrolled between January 2019 and September 2021 who participated at least 4 and up to 52 weeks in the program (n = 16 274). We measured pain using Numeric Rating Scale (NRS 0-10) and applied latent class growth analysis to identify classes with similar trajectories. Associations between baseline characteristics and trajectory classes were examined using multinomial logistic regression and dominance analysis. RESULTS: We identified 4 pain trajectory classes: "mild-largely improved" (30%), "low moderate-largely improved" (34%), "upper moderate-improved" (24%), and "severe-persistent" (12%). For classes with decreasing pain, the most pain reduction occurred during first 20 weeks and was stable thereafter. Male sex, older age, lower body mass index (BMI), better physical function, lower activity impairment, less anxiety/depression, higher education, knee OA, no walking difficulties, no wish for surgery and higher physical activity, all measured at enrolment, were associated with greater probabilities of membership in "mild-largely improved" class than other classes. Dominance analysis suggested that activity impairment followed by wish for surgery and walking difficulties were the most important predictors of trajectory class membership. CONCLUSIONS: Our results highlight the importance of reaching people with OA for first-line treatment prior to developing severe pain, poor health status and a wish for surgery.

Neoplastic and Non-neoplastic Soft Tissue Lesions Around the Knee.

Neoplastic and non-neoplastic soft tissue masses around the knee are often incidental findings. Most of these lesions are benign with typical imaging characteristics that allow a confident diagnosis. However, some of these incidental neoplastic masses are characterized by morbidity and potential mortality. This review highlights the typical aspects of these lesions, facilitating a correct diagnosis.

Neoplastic and Non-neoplastic Bone Lesions of the Knee.

Numerous anatomical variants are described around the knee, many of which look like bony lesions, so it is important to know them to avoid unnecessary complementary tests and inadequate management. Likewise, several alterations in relation to normal development can also simulate bone lesions.However, numerous pathologic processes frequently affect the knee, including traumatic, inflammatory, infectious, and tumor pathology. Many of these entities show typical radiologic features that facilitate their diagnosis. In other cases, a correct differential diagnosis is necessary for proper clinical management.Despite the availability of increasingly advanced imaging techniques, plain radiography is still the technique of choice in the initial study of many of these pathologies. This article reviews the radiologic characteristics of tumor and nontumor lesions that may appear around the knee to make a correct diagnosis and avoid unnecessary complementary radiologic examinations and inadequate clinical management.

MRI reconstruction with enhanced self-similarity using graph convolutional network.

BACKGROUND: Recent Convolutional Neural Networks (CNNs) perform low-error reconstruction in fast Magnetic Resonance Imaging (MRI). Most of them convolve the image with kernels and successfully explore the local information. Nonetheless, the non-local image information, which is embedded among image patches relatively far from each other, may be lost due to the limitation of the receptive field of the convolution kernel. We aim to incorporate a graph to represent non-local information and improve the reconstructed images by using the Graph Convolutional Enhanced Self-Similarity (GCESS) network. METHODS: First, the image is reconstructed into the graph to extract the non-local self-similarity in the image. Second, GCESS uses spatial convolution and graph convolution to process the information in the image, so that local and non-local information can be effectively utilized. The network strengthens the non-local similarity between similar image patches while reconstructing images, making the reconstruction of structure more reliable. RESULTS: Experimental results on in vivo knee and brain data demonstrate that the proposed method achieves better artifact suppression and detail preservation than state-of-the-art methods, both visually and quantitatively. Under 1D Cartesian sampling with 4 × acceleration (AF = 4), the PSNR of knee data reached 34.19 dB, 1.05 dB higher than that of the compared methods; the SSIM achieved 0.8994, 2% higher than the compared methods. Similar results were obtained for the reconstructed images under other sampling templates as demonstrated in our experiment. CONCLUSIONS: The proposed method successfully constructs a hybrid graph convolution and spatial convolution network to reconstruct images. This method, through its training process, amplifies the non-local self-similarities, significantly benefiting the structural integrity of the reconstructed images. Experiments demonstrate that the proposed method outperforms the state-of-the-art reconstruction method in suppressing artifacts, as well as in preserving image details.