Kellgren-Lawrence Research Articles

KOC_Net: Impact of the Synthetic Minority Over-Sampling Technique with Deep Learning Models for Classification of Knee Osteoarthritis Using Kellgren–Lawrence X-Ray Grade

One of the most common diseases afflicting humans is knee osteoarthritis (KOA). KOA occurs when the knee joint cartilage breaks down, and knee bones start rubbing together. The diagnosis of KOA is a lengthy process, and missed diagnosis can have serious consequences. Therefore, the diagnosis of KOA at an initial stage is crucial which prevents the patients from Severe complications. KOA identification using deep learning (DL) algorithms has gained popularity during the past few years. By applying knee X-ray images and the Kellgren–Lawrence (KL) grading system, the objective of this study was to develop a DL model for detecting KOA. This study proposes a novel model based on CNN called knee osteoarthritis classification network (KOC_Net). The KOC_Net model contains 05 convolutional blocks, and each convolutional block has three components such as Convlotuioanl2D, ReLU, and MaxPooling 2D. The KOC_Net model is evaluated on two publicly available benchmark datasets which consist of X-ray images of KOA based on the KL grading system. Additionally, we applied contrast-limited adaptive histogram equalization (CLAHE) methods to enhance the contrast of the images and utilized SMOTE Tomek to deal with the problem of minority classes. For the diagnosis of KOA, the classification performance of the proposed KOC_Net model is compared with baseline deep networks, namely Dense Net-169, Vgg-19, Xception, and Inception-V3. The proposed KOC_Net was able to classify KOA into 5 distinct groups (including Moderate, Minimal, Severe, Doubtful, and Healthy), with an AUC of 96.71%, accuracy of 96.51%, recall of 91.95%, precision of 90.25%, and F1-Score of 96.70%. Dense Net-169, Vgg-19, Xception, and Inception-V3 have relative accuracy rates of 84.97%, 81.08%, 87.06%, and 83.62%. As demonstrated by the results, the KOC_Net model provides great assistance to orthopedics in making diagnoses of KOA.

Development and accuracy of an artificial intelligence model for predicting the progression of hip osteoarthritis using plain radiographs and clinical data: a retrospective study

BackgroundPredicting the progression of hip osteoarthritis (OA) remains challenging, and no reliable predictive method has been established. This study aimed to develop an artificial intelligence (AI) model to predict hip OA progression via plain radiographs and patient data and to determine its accuracy.MethodsThis retrospective study utilized anteroposterior pelvic radiographs of consecutive patients with hip OA who underwent primary unilateral total hip arthroplasty. Radiographs diagnosed with Kellgren–Lawrence (KL) grade 0–2 were extracted from 361 patients and 1697 images. This AI model was developed to predict whether OA would progress from KL grade 0–2 to KL grade ≥ 3 within n years (n = 3, 4, 5). A gradient-boosting decision tree approach was utilized according to feature extractions obtained by a convolutional neural network from radiographs and patient data (height, body weight, sex, age, and KL grade given by an orthopedic surgeon) with five-fold cross-validation. The model performance was assessed using accuracy, specificity, sensitivity, and the area under the receiver operating characteristic curve (AUC).ResultsThe mean accuracy, specificity, sensitivity, and AUC of our prediction model were, respectively, 81.8%, 88.0%, 66.7%, and 0.836 for 3 years; 79.8%, 85.0%, 71.6%, and 0.836 for 4 years; and 78.5%, 80.4%, 76.9%, and 0.846 for 5 years.ConclusionsThe proposed AI model performed adequately in predicting hip OA progression and may be clinically applicable with additional datasets and validation.

No difference in osteoarthritis, but less graft failures after 5 years, comparing anatomic double-bundle to anatomic single-bundle ACL reconstruction.

The purpose of this study was to compare the incidence of knee osteoarthritis (OA) between the anatomic single-bundle (SB) and anatomic double-bundle (DB) anterior cruciate ligament (ACL) reconstruction technique after 5-year follow-up (FU). Secondary objectives were to compare patient-reported outcome measures (PROMs), clinical examination, activity level, functional tests and graft failures between the two groups. The study was a secondary analysis after 5-year FU of a randomized controlled trial (RCT) (Clinical Trials NCT01033188). One hundred and twenty patients between 18 and 40 years were randomized to either anatomic SB or anatomic DB reconstruction. The Kellgren-Lawrence (KL) classification grade ≥2 and the Osteoarthritis Research Society International (OARSI) atlas criteria score ≥2 were used for defining OA. Additionally, PROMs were obtained and clinical examinations of the knees were performed. Finally, the number of patients experiencing graft failure in each group was recorded. Radiographic imaging was performed in 39 patients in the SB group and in 37 patients in the DB group. Four patients (10%) in the SB group and two (5%) in the DB group developed osteoarthritis according to the KL classification (p = 0.28). Five (13%) in the SB group and three (8%) in the DB group developed osteoarthritis according to the OARSI atlas criteria (p = 0.59; difference 5.0% [95% confidence interval, CI: -0.10 to 0.20]). There were no significant differences in the PROMs, clinical examinations, activity levels, or functional tests when comparing the two groups. Of initially 62 SB patients, 14 (23%) experienced graft failure compared to 4 (7%) of the 58 DB patients (p = 0.015; difference 0.016 [95% CI: 0.03-0.29]). At 5-year FU, there were no significant differences in the incidence of OA, PROMS, or other clinical findings comparing the anatomic DB to anatomic SB ACL reconstructed patients. There were fewer graft failures among patients treated with anatomic DB ACL reconstruction. II.

The role of lncRNA TSIX in osteoarthritis pathogenesis: mechanistic insights and clinical biomarker potential

BackgroundThis study seeks to elucidate the expressions of lncRNA TSIX in Osteoarthritis (OA) and to explore its mechanisms in regulating OA progression.MethodsRT-qPCR was employed to analyze the expression of TSIX in OA patients classified by Kellgren-Lawrence (K-L) grades. Receiver operator characteristic (ROC) was conducted to evaluate the diagnostic value of TSIX. Correlation between TSIX levels and clinical scores such as Lysholm and visual analogue scale (VAS) score was evaluated using Pearson method. IL-1β-induced SW1353 cells served as an in vitro model. The cell function were assessed by flow cytometry and cell counting kit-8 (CCK-8) assay. The relationship between TSIX and miR-320a was verified by luciferase reporting system, while bioinformatics approaches were utilized to predict the downstream target genes of miR-320a.ResultsThe findings revealed that TSIX level in OA patients was elevated compared to that of the control group, with a notable progressive increase in TSIX expression correlated with higher K-L grades. In OA patients, the Lysholm score showed a negative correlation with TSIX expression, while the VAS score displayed a positive correlation with TSIX levels. Cell studies demonstrated that inhibition of TSIX enhanced cell viability and mitigated IL-1β-induced apoptosis by targeting miR-320a, in addition to promoting Aggrecan and Collagen II secretion. Luciferase reporter assay further validated the targeting interaction among TSIX, miR-320a, and PTEN.ConclusionsThis study demonstrated an increased expression of TSIX in OA patients. It suggests that TSIX may play a role in chondrocyte dysfunction during OA by modulating the miR-320a/PTEN axis.

Impact of Structural Severity on Outcomes in Knee Osteoarthritis: An Analysis of Data from Phase 2 and Phase 3 Lorecivivint Clinical Trials.

Developing knee osteoarthritis (OA) treatments is challenging due to assessing pain and joint structure outcomes within a highly heterogeneous disease. Lorecivivint (LOR), an intra-articular (IA) CLK/DYRK inhibitor, modulates Wnt and inflammatory pathways. This review analysis of LOR 0.07 mg trial data aims to describe the potential impact of baseline joint structure on OA pain response. Two Phase 2 and two Phase 3 trials enrolled knee OA patients with Kellgren-Lawrence (KL) Grades 2-3 and Pain Numeric Rating Scale (NRS [0-10]) ≥4 to ≤ 8 in target knee. Cumulative frequency distribution plots by KL grade summarized the percentages of patients with medial joint space width (medial JSW) < 3 mm. Osteoarthritis Research Society International Joint Space Narrowing grades and treatment responses in trials capturing Pain NRS were similarly summarized. Pain outcome changes were estimated using baseline adjusted ANCOVA. Compared with phase 2 trials, the phase 3 trials had an increased proportion of patients with baseline medial JSW < 3 mm. LOR demonstrated beneficial treatment effects vs placebo in KL 2 subgroups, which were found to have higher proportions of baseline medial JSW > 3 mm, apart from one Phase 3 trial with advanced structural knee OA. Baseline medial JSWs were heterogeneous across trials despite KL inclusion criteria. LOR demonstrated greater symptomatic improvements in patients with less structurally advanced disease, indicative of an association between OA structural damage and pain. Early treatment interventions may improve outcomes and provide insight for future OA trial inclusion criteria development. OA-02, NCT02536833; OA-04, NCT03122860; OA-10, NCT04385303; OA-11, NCT03928184.

Effect of patient specificity on predicting knee cartilage degeneration in obese adults: Musculoskeletal finite-element modeling of data from the CAROT trial.

Obesity is a known risk factor for development of osteoarthritis (OA). Numerical tools like finite-element (FE) models combined with degenerative algorithms have been developed to understand the interplay between OA and obesity. Inthisstudy,we aimed to predict knee cartilage degeneration in a cohort of obese adults to investigate the importance of patient-specific information on degeneration predictions. We used a validated FE modeling approach and three different age-dependent functions (step-wise, exponential, and linear) to simulate cartilage degradation under overloading in the knee joint. Gait motion analysis and magnetic resonance imaging data from 115 obese individuals with knee OA were used for musculoskeletal and FE modeling. Cartilage degeneration predictions were contrasted with Kellgren-Lawrence (KL)and Boston-Leeds Osteoarthritis Knee Score (BLOKS) grades. The findings show that overall, the similarities between numerical predictions and clinical measures were better for the medial (average area under the curve(AUC) = 0.62) compared to the lateral compartment (average AUC = 0.52) of the knee. Classification results for KL grades, full patient-specific models and patient-specific geometry with generic gait data showed higher AUC values (AUC = 0.71 and AUC = 0.68, respectively) compared to generic geometry and patient-specific gait (AUC = 0.48). For BLOKS grades, AUC values for both full patient-specific models and for patient-specific geometry with generic gait locomotion were higher (AUC = 0.66 and AUC = 0.64, respectively) compared to when the generic geometry and patient-specific gait were used (AUC = 0.53). In summary, our study highlights the importance of considering individual information in knee OA prediction. Nevertheless, our findings suggest that personalized gait play a smaller role in the OA prediction and classification capacity than personalized joint geometry.

Association of cartilage [formula omitted] and [formula omitted] relaxation time measurement with hip osteoarthritis progression: A 5-year longitudinal study using voxel-based relaxometry and Z-score normalization

ObjectiveTo study the longitudinal changes of cartilage T1ρ and T2 relaxation time measurements in hip-OA patients. MethodsA calibration study compared two scanner data, Scanner-1 (GE Discovery MR750 3.0T) with unilateral acquisition protocol and Scanner-2 (GE Signa Premier 3.0T) with bilateral acquisition protocol, using nine subjects(average age ​= ​40.33 ​± ​13.53 years, 5 females), including one hip-OA subject. Quantified parameters from the Scanner-2 were adjusted using voxel-based relaxometry(VBR) and Z-score normalization to reduce the inter-scanner variability. Eighteen hip-OA Subjects (age ​= ​53.11 ​± ​14.96 years, 12 females) were recruited to the longitudinal variability study from 2016, comprising five assessments at 1-year intervals. Baseline to 3rd-year data used unilateral acquisition with Scanner-1, while 4th-year data used bilateral acquisition with Scanner-2. A linear mixed-effects model(LME) assessed trajectory analyses, with acquisition year, age, sex, body mass index(BMI), and Kellgren-Lawrence(KL) score as predictor variables and cartilage mean T1ρ and T2 values as outcomes. ResultsVBR analysis after Z-score normalization showed that only a few of the whole cartilage voxels had significant differences in T1ρ(femur-2.36 ​% and acetabular-3.23 ​%) and T2 (femur-2.30 ​% and acetabular-2.94 ​%) values between the scanners. The LME analysis showed that the BMI predictor variable was significantly correlated with the femur T1ρ (p ​< ​0.0001) and T2 (p ​< ​0.0001) and acetabular T1ρ (p ​< ​0.0001) and T2 (p ​< ​0.0001) cartilage region. ConclusionThe calibration study demonstrated the effectiveness of VBR and Z-score normalization in reducing inter-scanner variability. The longitudinal study revealed a significant correlation between T1ρ and T2 values of the cartilage and BMI; also the T1ρ and T2 values increased over time in some of the cartilage subregions.

Influencing factors analysis of asymmetry in knee adduction moment among patients with unilateral knee osteoarthritis

BackgroundThe knee adduction moment(KAM) of both lower limbs in patients with unilateral knee osteoarthritis(KOA) exhibits asymmetry during walking, but the factors influencing this asymmetry remain unclear. This study aimed to explore the influencing factors of KAM asymmetry in patients with unilateral KOA.MethodsA total of 148 patients with unilateral medial compartment KOA were selected for this retrospective study, and general data such as gender, age, and duration of disease were collected. The hip-knee-ankle (HKA) angle, degree of pain, and knee-extension muscle strength on the affected side were assessed through radiographic outcomes, the visual analog scale(VAS), and the Biodex isokinetic system. The peak KAM of both lower limbs was analyzed using a BTS motion-capture system and force platform. The asymmetry index(ASI) of KAM was calculated, and the patients were further categorized into the KAM symmetry group(ASI value ≤ 10%) and the KAM asymmetry group(ASI value>10%).Binary logistic regression analysis was employed to analyze the factors influencing the asymmetry of KAM.Results90 patients were categorized into the KAM asymmetry group, representing 60.8% of the cohort. A significant difference in the ASI value of KAM was observed between the two groups. Correlation analysis identified nine factors, including sex, age, and BMI, that were positively correlated with the ASI value of KAM. In contrast, knee-extension muscle strength and per-capita monthly household income were negatively correlated with the ASI value of KAM. Regression analysis revealed that being female(OR = 1.752), older age(OR = 2.472), increased BMI(OR = 1.535), larger varus angle(OR = 3.965), higher VAS score(OR = 2.617), Kellgren-Lawrence(K-L) grade IV(OR = 4.474), history of knee joint trauma(OR = 5.684), and living in a rural location(OR = 1.554) increased the risk of KAM asymmetry. Conversely, increased knee-extension muscle strength(OR = 0.758) and a per-capita monthly household income of 3000 ~ 6000 yuan(OR = 0.814) decreased the risk of KAM asymmetry.ConclusionFemale gender, older age, increased BMI, larger varus angle, higher VAS score, K-L grade IV, history of knee joint trauma, and living in a rural location are identified as risk factors for KAM asymmetry. Conversely, increased knee-extension muscle strength and a per-capita monthly household income of 3000 ~ 6000 yuan serve as protective factors against this asymmetry.

Deep learning to combat knee osteoarthritis and severity assessment by using CNN-based classification

BackgroundIn today’s digital age, various diseases drastically reduce people’s quality of life. Arthritis is one amongst the most common and debilitating maladies. Osteoarthritis affects several joints, including the hands, knees, spine, and hips. This study focuses on the medical disorder underlying Knee Osteoarthritis (KOA) which severely impairs people’s quality of life. KOA is characterised by restricted mobility, stiffness, and terrible pain and can be caused by a range of factors such as ageing, obesity, and traumas. This degenerative disorder leads to progressive wear and tear of the knee joint.MethodsTo combat arthritis in the kneecap, this study employs a 12-layer Convolutional Neural Network (CNN) to reach deep learning capabilities. A collection of data from the Osteoarthritis Initiative (OAI) is used to classify KOA. Through the use of medical image processing; the study ascertains whether an individual has this ailment. A sophisticated CNN architecture created especially for binary classification and KOA severity utilising deep learning algorithms is the main component of this work.ResultsThe cross-entropy loss function is an important component of the model’s laborious design that classifies data into two groups. The remaining section uses the Kellgren-Lawrence (KL) grade to classify the disease’s severity. In the binary classification, the proposed algorithm outperforms previous methods with an accuracy rate of 92.3%, and in the multiclassification, its accuracy rate is 78.4% which is superior to the previous findings.ConclusionLooking ahead, the research broadens the scope of this work by gathering information from various sources and using these methods on a wider range of datasets and situations. The potential for major advancements in the field of osteoarthritis detection and classification is highlighted by this forward-looking approach. Furthermore, this method reduces the intervention of medical practitioners and ultimately results in accurate diagnosis.Clinical trial numberNot applicable.

Articular cartilage debridement results in short-term significant improvements in patient-reported outcomes for large areas of cartilage loss of the femur in the setting of mild to moderate knee osteoarthritis

PurposeThis study aims to evaluate patient-reported outcomes (PROs) following chondroplasty in patients with larger chondral defects (≥2 cm2) of the femur in the setting of osteoarthritis. Materials and methodsRetrospective review of patients who underwent chondroplasty of the femur. All patients were radiographically assessed to have Kellgren-Lawrence (KL) grades of 2 or 3 and had a minimum of 1-year postoperative follow-up. Areas of chondral loss were estimated by arthroscopic measurements and by MRI. PROs included the International Knee Documentation Committee, Knee Injury and Osteoarthritis Outcome Score for Joint Replacement, and the Veterans Rand-12 Item. Statistical analysis was performed using paired t tests to compare baseline and follow-up data, as well as linear regressions to correlate lesion size with symptom improvement. ResultsA total of 39 patients were included. There were 20 KL grade 2 and 19 KL grade 3 knees. At both 1- and 2-year follow-ups, significant improvements were noted in International Knee Documentation Committee (34.9 ± 13.5 preoperative, 55.6 ± 18.8 at 2 years, P = .0025), Knee Injury and Osteoarthritis Outcome Score for Joint Replacement (56.3 ± 14.7 preoperative, 64.5 ± 17.0 at 2 years, P = .0243), and Veterans Rand-12 Item Physical Component Scores (38.0 ± 12.7 preoperative, 43.8 ± 8.6 at 2 years, P = .0044). All increases exceed previously reported Minimal Clinically Important Differences. Four (10.3%) conversions to arthroplasty were noted at most recent follow-up. ConclusionsArticular cartilage debridement for large areas of cartilage loss of the femur in the setting of mild to moderate knee osteoarthritis results in significant improvements in physical function and knee-specific PROs at 1- and 2-year follow-ups.

Influence of Knee Osteoarthritis Severity, Knee Pain, and Depression on Physical Function: A Cross-Sectional Study.

Decreased physical function with increasing life expectancy is a public health concern worldwide. Knee osteoarthritis (KOA) is considered one of the primary illnesses causing decreased physical function. Depression affects decreased physical function and is closely related to knee pain in KOA. However, the effect of these interacting factors on physical function is not clear. We conducted a cross-sectional analysis of the baseline data of 1106 subjects of the 2009 Locomotive Syndrome and Health Outcome in Aizu Cohort Study (LOHAS). We determined the association between their Timed Up and Go test (TUG) scores and radiographic KOA, knee pain, and depression in a multivariate analysis. Severe knee pain was significantly associated with decreased physical function (the odds ratio [OR] was 2.13, 95% confidence interval [CI]: 1.32-4.89), as was depression (OR 2.64, 95% CI 1.61-4.33). Only Kellgren-Lawrence (KL) grade 4 was significantly associated with decreased physical function in the radiographic KOA severity (OR 6.58, 95% CI 1.75-24.68). Severe knee pain and depression were significantly associated with decreased physical function, but not radiographic KOA severity except for KL grade 4. The limitations of using radiographic KOA severity alone as the indicator of assessment for physical function were suggested. When assessing decreased physical function, the clinical focus tends to be on radiographic KOA severity, but it is important to consider the patient's knee pain and psychological factors.

Deep Learning for Automatic Knee Osteoarthritis Severity Grading and Classification.

Knee osteoarthritis (OA) is a prevalent condition that significantly impacts the quality of life, often leading to the need for knee replacement surgery. Accurate and timely identification of knee degeneration is crucial for effective treatment and management. Traditional methods of diagnosing OA rely heavily on radiological assessments, which can be time-consuming and subjective. This study aims to address these challenges by developing a deep learning-based method to predict the likelihood of knee replacement and the Kellgren-Lawrence (KL) grade of knee OA from X-ray images. We employed the Osteoarthritis Initiative (OAI) dataset and utilized a transfer learning approach with the Inception V3 architecture to enhance the accuracy of OA detection. Our approach involved training 14 different models-Xception, VGG16, VGG19, ResNet50, ResNet101, ResNet152, ResNet50V2, ResNet101V2, ResNet152V2, Inception V3, Inception, ResNetV2, DenseNet121, DenseNet169, DenseNet201-and comparing their performance. The study incorporated pixel ratio computation and picture pre-processing, alongside a decision tree model for prediction. Our experiments revealed that the Inception V3 model achieved the highest training accuracy of 91% and testing accuracy of 67%, with notable performance in both training and validation phases. This model effectively identified the presence and severity of OA, correlating with the Kellgren-Lawrence scale and facilitating the assessment of knee replacement needs. By integrating advanced deep learning techniques with radiological diagnostics, our methodology supports radiologists in making more accurate and prompt decisions regarding knee degeneration. The Inception V3 model stands out as the optimal choice for knee X-ray analysis, contributing to more efficient and timely healthcare delivery for patients with knee osteoarthritis.

Factors affecting the therapeutic effects of multiple intra-articular injections of platelet-rich-plasma for knee osteoarthritis

BackgroundPlatelet-rich-plasma (PRP) is rapidly spreading as a conservative treatment option for knee osteoarthritis (KOA), however, its therapeutic efficacy is controversial. This study aimed to investigate the factors affecting the therapeutic effect of intra-articular PRP therapy for KOA in patients who received multiple PRP injections (PRP-I). MethodsThis is a historical cohort study included 1057 knees of 701 patients who received PRP-I during KOA treatment from 2018 to 2020. The difference in visual analog scale (VAS) scores before and after PRP-I was defined as the amount of change in VAS (ΔVAS). A linear mixed-effects model was employed with ΔVAS as a random effect and age, sex, BMI, KL classification, pre-treatment VAS, treatment duration, and the number of PRP injections as fixed effects. Evaluations using the Kellgren-Lawrence (KL) classification were added. ResultsAge, KL grade, and VAS score before treatment and after three, four, and five PRP-I were significantly associated with ΔVAS score. According to KL grade, age was significantly associated with ΔVAS score in the KL grade 4 group. VAS score before treatment was significantly associated with ΔVAS score, regardless of KL grade. Three-time PRP-I were significantly associated with ΔVAS in the KL-grade 1 and 2 groups. For KL grade 4, two or more PRP-I were significantly associated with the high efficacy. ConclusionsAge, pain before treatment, KL grade and number of injections were associated with pain reduction after intra-articular PRP-I for KOA treatment. Pain reduction can be expected after PRP-I when patients are younger or experience severe pain before treatment. Three-time PRP-I are recommended to reduce pain in early-stage KOA and more than three times in advanced-stage KOA. Trial registrationRetrospectively registration.

Application of remote sensing navigation system in total knee arthroplasty

To explore clinical accuracy of remote sensing navigation alignment (RSNA) system in total knee arthroplasty (TKA) and its influence on postoperative clinical efficacy. From May 2021 to May 2022, 60 knee osteoarthritis (KOA) patients with Kellgren-Lawrence (K-L) grade Ⅲ to Ⅳ treated by unilateral primary TKA were selected and divided into RSNA group and traditional operation group according to treatment methods, and 30 patients in each group. There were 6 males and 24 females in RSNA group, aged from 55 to 86 years old with an average of (68.06±8.23) years old;body mass index (BMI) ranged from 22.15 to 34.58 kg·m-2 with an average of (28.20±3.01) kg·m-2;the courses of disease ranged from 2 to 60 months with an average of (18.80±14.80) months;13 patients with grade Ⅲ and 17 patients with grade Ⅳ according to K-L grading. In traditional operation group, there were 8 males and 22 females, aged from 57 to 85 years old with an average of (67.26±6.32) years old;BMI ranged from 23.94 to 34.55 kg·m-2 with an average of (27.49±2.32) kg·m-2;the courses of disease ranged from 3 to 60 months with an average of (21.30±16.44) months;14 patients with grade Ⅲ and 16 patients with grade Ⅳ according to K-L grading. Western Ontario and McMaster Universities (WOMAC) osteoarthritis index and Knee Society score(KSS) were used to evaluate functional recovery of patients. Hip-knee-ankle angle (HKAA), distal femoral valgus angle (FVA) and distal fermoral flexion angle (DFFA) were measured before operation. HKAA and HKAA deviation angle were measured at 1 week after operation, and defective rate of lower limb force line, femur prosthesis valgus angle (FPVA) and femoral prosthesis flexion angle (FPFA), respectively, were calculated. There were no serious complications such as vascular and nerve injury during operation, and wound healed at stage Ⅰ. Both groups were followed up for 6 months. There were no significant difference in WOMAC index, KSS, HKAA, FVA and DFFA between two groups before operation (P>0.05). The force line defect rate, HKAA, HKAA deviation angle, FPVA deviation angle and FPFA of RSNA group were 6.7%, (178.74±1.56) °, (1.25±1.56) °, (1.84±0.16) ° and (4.85±2.46) °, respectively;while in traditional operation group were 20%, (176.73±3.46) °, (3.27±3.46) °, (2.44±0.26) °, (6.60±1.86) °;the difference between two groups were statistically significant (P<0.05). There were no significant difference in WOMAC index and KSS between two groups at 3 and 6 months after operation (P>0.05). RSNA system could reduce defective rate of lower limb force line, FPVA deviation angle and FPFA after TKA, which is more accurate and easy to operate than traditional intramedullary localization surgery while ensuring postoperative efficacy.

Early gait analysis after total knee arthroplasty based on artificial intelligence dynamic image recognition

To explore early postoperative gait characteristics and clinical outcomes after total knee arthroplasty (TKA). From February 2023 to July 2023, 26 patients with unilateral knee osteoarthritis (KOA) were treated with TKA, including 4 males and 22 females, aged from 57 to 85 years old with an average of (67.58±6.49) years old;body mass index (BMI) ranged from 18.83 to 38.28 kg·m-2 with an average of (26.43±4.15) kg·m-2;14 patients on the left side, 12 patients on the right side;according to Kellgren-Lawrence(K-L) classification, 6 patients with grade Ⅲ and 20 patients with grade IV;the courses of disease ranged from 1 to 14 years with an average of (5.54±3.29) years. Images and videos of standing up and walking, walking side shot, squatting and supine kneeling were taken with smart phones before operation and 6 weeks after operation. The human posture estimation framework OpenPose were used to analyze stride frequency, step length, step length, step speed, active knee knee bending angle, stride length, double support phase time, as well as maximum hip flexion angle and maximum knee bending angle on squatting position. Western Ontario and McMaster Universities (WOMAC) arthritis index and Knee Society Score (KSS) were used to evaluate clinical efficacy of knee joint. All patients were followed up for 5 to 7 weeks with an average of (6.00±0.57) weeks. The total score of WOMAC decreased from (64.85±11.54) before operation to (45.81±7.91) at 6 weeks after operation (P<0.001). The total KSS was increased from (101.19±9.58) before operation to (125.50±10.32) at 6 weeks after operation (P<0.001). The gait speed, stride frequency and stride length of the affected side before operation were (0.32±0.10) m·s-1, (96.35±24.18) steps·min-1, (0.72±0.14) m, respectively;and increased to (0.48±0.11) m·s-1, (104.20±22.53) steps·min-1, (0.79±0.10) m at 6 weeks after operation (P<0.05). The lower limb support time and active knee bending angle decreased from (0.31±0.38) s and (125.21±11.64) ° before operation to (0.11±0.04) s and (120.01±13.35) ° at 6 weeks after operation (P<0.05). Eleven patients could able to complete squat before operation, 13 patients could able to complete at 6 weeks after operation, and 9 patients could able to complete both before operation and 6 weeks after operation. In 9 patients, the maximum bending angle of crouching position was increased from 76.29° to 124.11° before operation to 91.35° to 134.12° at 6 weeks after operation, and the maximum bending angle of hip was increased from 103.70° to 147.25° before operation to 118.61° to 149.48° at 6 weeks after operation. Gait analysis technology based on artificial intelligence image recognition is a safe and effective method to quantitatively identify the changes of patients' gait. Knee pain of KOA was relieved and the function was improved, the supporting ability of the affected limb was improved after TKA, and the patient's stride frequency, stride length and stride speed were improved, and the overall movement rhythm of both lower limbs are more coordinated.

A retrospective study on two different surgical robots to assist total knee arthroplasty

To compare early clinical and imaging results of domestic HURWA and imported Brainlab Knee3 surgical robot-assisted knee replacement. A retrospective analysis was performed on 93 patients with knee osteoarthritis (KOA) who underwent robot-assisted descending total knee arthroplasty(TKA) from January 2021 to July 2023, and they were divided into BRATKA group and HRATKA group according to use of robotic system. There were 40 patients in BRATKA group, including 16 males and 24 females, aged from 55 to 90 years old with an average of (64.3±7.0) years old;27 patients with grade Ⅲ and 13 patients with grade Ⅳ according to Kellgren-Lawrence(K-L);18 patients on the right side and 22 patients on the left side;the courses of disease ranged from 1 to 30 years with an average of (15.3±7.6) years;imported Brainlab Knee3 surgical robot assisted system was adopted. There were 53 patients in HRATKA group, including 18 males and 35 females, aged from 52 to 81 years old with an average of (64.4±8.5) years old;30 patients with grade Ⅲ and 23 patients with grade Ⅳ;21 patients on the right side and 32 patients on the left side;the courses of disease ranged from 1 to 32 years with an average of (16.4±7.9) years;HURWA surgical robot assisted system was adopted. Operation time, perioperative total blood loss, incision length and postoperative complications were compared between two groups. Deviation angle of hip-knee-ankle angle(HKAA) before operation and on the first day after operation was compared between two groups. Later tibal component (LTC), frontal femoral component (FFC), later femoral component (LFC) and frontal tibal component(FTC) at 1 day after on the first day after operation was compared between two groups. Knee Society score(KSS), visual analogue scale (VAS) and range of motion (ROM) of knee joint were compared between two groups before operation and on the 3rd and 90th day after operation. Both groups were followed up for 11 to 18 months with an average of (14.4±2.1) months, and the wounds of all patients healed well. Operation time and incision length of BRATKA group were (132.1±34.6) min and (12.9±1.9) cm, while (94.1±10.8) min and (14.8±2.1) cm in HRATKA group, respectively, and the differences between two groups were statistically significant(P<0.05). There were no significant difference in perioperative total blood loss and preoperative deviation angle of HKAA between two groups(P>0.05). Deviation angle of HKAA, FFC angle and LFC angle in BRATKA group were (1.90±0.91) °, (87.90±1.51) ° and(9.00±3.2) °, respectively;while (0.93±1.04) °, (89.03±0.96) ° and (7.63±0.59) ° in HRATKA group, respectively, and the differences between two groups were statistically significant (P<0.05). There were no significant differences in FTC and LTC between two groups(P>0.05). There were no significant differences in VAS of knee rest and exercise, KSS score and ROM of knee joint between two groups before operation and 3 days and 90 days after operation(P>0.05). There was no significant difference in complications between two groups (P>0.05). Postoperative imaging of two robot systems showed good lower limb force line. The domestic HRATKA group had better LFC, FFC angle and HKA deviation angle than the imported BRATKA group, but there were no significant difference in postoperative knee function and pain relief.

Generative AI in orthopedics: an explainable deep few-shot image augmentation pipeline for plain knee radiographs and Kellgren-Lawrence grading.

Recently, deep learning medical image analysis in orthopedics has become highly active. However, progress has been restricted by the absence of large-scale and standardized ground-truth images. To the best of our knowledge, this study is the first to propose an innovative solution, namely a deep few-shot image augmentation pipeline, that addresses this challenge by synthetically generating knee radiographs for training downstream tasks, with a specific focus on knee osteoarthritis Kellgren-Lawrence (KL) grading. This study leverages a deep few-shot image augmentation pipeline to generate synthetic knee radiographs. Despite the limited availability of training samples, we demonstrate the capability of our proposed computational strategy to produce high-fidelity plain knee radiographs and use them to successfully train a KL grade classifier. Our experimental results showcase the effectiveness of the proposed computational pipeline. The generated synthetic radiographs exhibit remarkable fidelity, evidenced by the achieved average Frechet Inception Distance (FID) score of 26.33 for KL grading and 22.538 for bilateral knee radiographs. For KL grading classification, the classifier achieved a test Cohen's Kappa and accuracy of 0.451 and 0.727, respectively. Our computational strategy also resulted in a publicly and freely available imaging dataset of 86000 synthetic knee radiographs. Our approach demonstrates the capability to produce top-notch synthetic knee radiographs and use them for KL grading classification, even when working with a constrained training dataset. The results obtained emphasize the effectiveness of the pipeline in augmenting datasets for knee osteoarthritis research, opening doors for broader applications in orthopedics, medical image analysis, and AI-powered diagnosis.

Study of adiponectin gene (rs1501299) polymorphism and serum adiponectin level in patients with primary knee osteoarthritis

BackgroundWe aimed to study, for the first time in the Egyptian population, the relationship between the serum adiponectin level in knee osteoarthritis (KOA) patients and its correlation with clinical, radiological, and ultrasonographic characteristics. Additionally, investigate the relationship between the adiponectin (ADIPOQ) gene rs1501299 (+ 276G/T) polymorphism and KOA susceptibility and severity.MethodsThis case-control study enrolled 40 patients with primary KOA and 40 matched controls. All patients underwent physical examination of the knee, pain assessment using the visual analogue scale (VAS), and functional evaluation by Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). Severity of KOA was assessed by Kellgren Lawrence (KL) grading scale and ultrasonography grading systems. Serum adiponectin levels and adiponectin (ADIPOQ) gene single nucleotide polymorphism (SNP) (rs1501299) genotyping were done for all patients and controls.ResultsThe study included 40 patients with primary symptomatic KOA and 40 controls with comparable age, sex, and body mass index. The genotype of the rs1501299 (+ 276G/T) polymorphism of the ADIPOQ gene was determined using TaqMan allelic discrimination. An enzyme-linked immunosorbent test was used to measure the level of serum adiponectin. The Western Ontario and McMaster Universities Osteoarthritis (WOMAC) score was used to assess functional capability, while the visual analogue scale was utilised to assess knee pain. Using the Kellgren-Lawrence (KL) grading method and global femoral cartilage (GFC) ultrasound grading, the severity of KOA was assessed. No significant differences between patients and controls as regards the genotype distributions and allele frequencies (p = 0.400, p = 0.507, respectively) of ADIPOQ gene rs1501299 (+ 276G/T) polymorphism. Furthermore, serum adiponectin level was significantly higher in the patients compared to healthy subjects (p < 0.001). Additionally, adiponectin level had a significant negative correlation with disease severity as evaluated by KL and GFC grading (r=-0.351, p = 0.027 and r=-0.397, p = 0.011, respectively).ConclusionsThe ADIPOQ gene rs1501299 (+ 276G/T) polymorphism was not associated with KOA severity or vulnerability. The level of adiponectin considerably reduced as the severity of KOA rose, indicating that adiponectin may have a preventive effect in KOA.

Similar two‐year improvement in patient‐reported outcomes in patients 40 years and older with outerbridge grade III and IV lesions following ACL reconstruction

AbstractPurposeThis study aims to evaluate clinical and patient‐reported outcome measures (PROMs) of patients 40 years and older that underwent anterior cruciate ligament reconstruction (ACLR) and determine the influence of preexisting arthritis and chondral wear on ACLR outcomes. We hypothesized that patients aged 40+ with ACLR would have excellent clinical outcomes and PROMs regardless of preexisting arthritic changes.MethodsA total of 118 patients were included. Patients aged 40 years and older who underwent ACLR in a single healthcare system between 2009 and 2016 were eligible. Outcomes assessed include Knee Injury and Osteoarthritis Outcome Scores (KOOS), Single Assessment Numeric Evaluation (SANE) scores, intraoperative Outerbridge grading, preoperative Kellgren–Lawrence (KL) grading and postoperative complication rates over a 2‐year period.ResultsAverage increase in KOOS and SANE scores were 21.2 19.9 and 23.5 31.3, respectively. Patients with Outerbridge grade III and IV lesions in weight‐bearing compartments had lower baseline SANE and KOOS scores than those without (47.1 ± 22.0 vs. 64.5 ± 23.6 baseline SANE and 43.1 ± 18.1 vs. 63.5 ± 15.9 baseline KOOS; p = 0.002 and p &lt; 0.001, respectively) with no significant difference in the amount of change in SANE or KOOS scores (p = 0.111 and p = 0.165 respectively). Patients with KL‐grade 2+ osteoarthritis experienced similar changes in KOOS and SANE over the 2‐year period to their counterparts (p = 0.598 and p = 0.643, respectively).ConclusionThere is no correlation between preexisting osteoarthritic changes or chondral defects and PROs. KOOS and SANE scores both increased postoperatively. When treating older patients with an ACL tear, surgeons should consider the activity level and desires of the patient as they determine appropriate treatment. Preexisting osteoarthritis does not correlate with patient‐reported outcomes for ACLR.Level of EvidenceLevel IV

Medial open wedge high tibial osteotomy is a viable option in young patients with advanced arthritis in a long-term follow-up.

This study aimed to evaluate the long-term outcomes of medial open wedge high tibial osteotomy (MOWHTO) as a treatment option for advanced medial compartment knee osteoarthritis (OA) Kellgren-Lawrence (K-L) III and IV. Patients with severe medial compartment arthritis, who underwent MOWHTO with locking plate between 2003 and 2015, were retrospectively reviewed. A locking plate for the osteotomy was utilized. Preoperative and postoperative patients' evaluation was performed using the International Knee Documentation Committee Score (IKDC), the Oxford Knee Score (OKS), the Knee Injury Osteoarthritis Outcome Score (KOOS) and the Short Form-12 Score (SF-12). Standardized standing whole-limb X-rays were taken to evaluate the mechanical tibiofemoral angle (mTFA) and proximal medial tibial angle (PMTA), and the severity of OA. A total of 32 patients, 35 knees (27 males, five females) of which 21 were classified as K-L Grade III and 14 as K-L Grade IV, and mean age 47.1 ± 9.17 years old, who were followed for 13.6 years (range 7-20 years), were included in the study. During the follow-up period, three knees required conversion to total knee replacement (91.5% survival rate). All clinical outcome scores (KOOS, OKS, IKDC and SF-12) showed a significant improvement compared to preoperative status (p < 0.05). Preoperative mTFA and PMTA were significantly corrected immediately after surgery and retained this improvement at the last follow-up. MOWHTO with a locking plate is an effective method to treat severe medial compartments. Clinical and radiological results are satisfactory and the survival rate is 91.5%, at a mean follow-up of 13.6 years after the procedure. Level IV.