Diagnosis Of Knee Osteoarthritis Research Articles

Transfer learning-assisted 3D deep learning models for knee osteoarthritis detection: Data from the osteoarthritis initiative.

Knee osteoarthritis is one of the most common musculoskeletal diseases and is usually diagnosed with medical imaging techniques. Conventionally, case identification using plain radiography is practiced. However, we acknowledge that knee osteoarthritis is a 3D complexity; hence, magnetic resonance imaging will be the ideal modality to reveal the hidden osteoarthritis features from a three-dimensional view. In this work, the feasibility of well-known convolutional neural network (CNN) structures (ResNet, DenseNet, VGG, and AlexNet) to distinguish knees with and without osteoarthritis (OA) is investigated. Using 3D convolutional layers, we demonstrated the potential of 3D convolutional neural networks of 13 different architectures in knee osteoarthritis diagnosis. We used transfer learning by transforming 2D pre-trained weights into 3D as initial weights for the training of the 3D models. The performance of the models was compared and evaluated based on the performance metrics [balanced accuracy, precision, F1 score, and area under receiver operating characteristic (AUC) curve]. This study suggested that transfer learning indeed enhanced the performance of the models, especially for ResNet and DenseNet models. Transfer learning-based models presented promising results, with ResNet34 achieving the best overall accuracy of 0.875 and an F1 score of 0.871. The results also showed that shallow networks yielded better performance than deeper neural networks, demonstrated by ResNet18, DenseNet121, and VGG11 with AUC values of 0.945, 0.914, and 0.928, respectively. This encourages the application of clinical diagnostic aid for knee osteoarthritis using 3DCNN even in limited hardware conditions.

Day-to-day fluctuations of fatigue severity in individuals with knee osteoarthritis: an ecological momentary assessment approach.

The variable course of fatigue adds to the disease burden of patients with OA yet it has been poorly understood. This study aimed to describe within-person fluctuations of fatigue severity and explore its associations with pain, positive affect, negative affect, sleep, and perceived exertion of physical activity. Individuals with chronic knee pain or a clinical diagnosis of knee OA ≥40 years of age completed daily assessments about fatigue, pain, positive affect, negative affect, sleep, perceived exertion of physical activity (numeric rating scale 0-10), and overwhelming fatigue (yes/no) on a smartphone over 14 days. Within-person fluctuations of fatigue severity were described by the probability of acute changes (PACs) and s.d.s. Associations with pain, positive affect, negative affect, sleep, and perceived exertion of physical activity were explored using multilevel models. Forty-nine individuals were included (mean age 63.4 years; 82% female). PACs and s.d.s of within-person daily fatigue fluctuations ranged from 0.00 to 0.80 and 0.35 to 2.95, respectively. Within-person associations of fatigue severity were moderate for positive affect [β = -0.57 (95% CI -0.67, -0.47)], weak for pain [β = 0.41 (95% CI 0.29, 0.53)] and negative affect [β = 0.40 (95% CI 0.21, 0.58)], and negligible for sleep [β = -0.13 (95% CI -0.18, -0.08)] and perceived exertion of physical activity [β = 0.18 (95% CI 0.09, 0.26)]. Some individuals showed almost stable day-to-day levels of fatigue severity, whereas others experienced a substantial number of clinically relevant fluctuations. To reduce the burden of daily fatigue fluctuations, our results suggest that pain, positive and negative affect rather than sleep and perceived exertion of physical activity should be considered as potential targets.

Knee Osteoarthritis Detection and Severity Classification Using Residual Neural Networks on Preprocessed X-ray Images.

One of the most common and challenging medical conditions to deal with in old-aged people is the occurrence of knee osteoarthritis (KOA). Manual diagnosis of this disease involves observing X-ray images of the knee area and classifying it under five grades using the Kellgren-Lawrence (KL) system. This requires the physician's expertise, suitable experience, and a lot of time, and even after that the diagnosis can be prone to errors. Therefore, researchers in the ML/DL domain have employed the capabilities of deep neural network (DNN) models to identify and classify KOA images in an automated, faster, and accurate manner. To this end, we propose the application of six pretrained DNN models, namely, VGG16, VGG19, ResNet101, MobileNetV2, InceptionResNetV2, and DenseNet121 for KOA diagnosis using images obtained from the Osteoarthritis Initiative (OAI) dataset. More specifically, we perform two types of classification, namely, a binary classification, which detects the presence or absence of KOA and secondly, classifying the severity of KOA in a three-class classification. For a comparative analysis, we experiment on three datasets (Dataset I, Dataset II, and Dataset III) with five, two, and three classes of KOA images, respectively. We achieved maximum classification accuracies of 69%, 83%, and 89%, respectively, with the ResNet101 DNN model. Our results show an improved performance from the existing work in the literature.

Leveraging Insurance Claims Data to Identify Risk Factors for Posttraumatic Osteoarthritis After Multiligament Knee Reconstruction

Background: The incidence of subsequent posttraumatic osteoarthritis (OA) diagnosis after surgery and the associated risk factors have been well reported after single-ligament anterior cruciate ligament (ACL) reconstruction; however, to date, the incidence of posttraumatic OA for those who have experienced multiligament knee injury (MLKI) has been reported only in relatively small, single-center studies. Purpose: To compare the incidence of OA diagnoses between patients with ACL injury versus patients with MLKI and to identify risk factors for OA diagnosis after MLKI. Study Design: Cohort study; Level of evidence, 3. Methods: This study used the PearlDiver Mariner database, which contains insurance claims information on >151 million orthopaedic patients. We identified 2 cohorts for this study by using Current Procedural Terminology codes. The cohorts included patients between the ages of 16 and 60 who underwent either isolated ACL reconstruction (n = 114,282) or MLKI reconstruction (n = 3325) between July 1, 2010, and August 30, 2016. MLKI reconstruction was operationally defined as ACL reconstruction plus concurrent surgical treatment of ≥1 additional ligaments. Demographic factors, concomitant meniscal and cartilage procedures, and subsequent reoperation to restore motion were recorded, as was the incidence of knee OA diagnosis within 5 years of the index surgical procedure. OA incidence and demographic and surgical factors were compared (1) between ACL and MLKI groups and (2) between patients with MLKI either with or without OA diagnosis. Results: A significantly greater proportion of patients with MLKI were diagnosed with knee OA within 5 years of surgery (MLKI = 299/3325 [9.0%] vs ACL = 6955/114,282 [6.1%]; P < .0001) (odds ratio [OR], 1.52; 95% CI, 1.35-1.72; P < .001). Factors associated with increased odds of OA diagnosis after MLKI included age ≥30 years (OR, 5.90), reoperation to restore motion (OR, 2.54), obesity (OR, 1.96), mood disorder diagnoses (OR, 1.85), partial meniscectomy (OR, 1.85), and tobacco use (OR, 1.72). Concomitant meniscal repair was protective against OA diagnosis (OR, 0.06). Conclusion: OA incidence was greater after MLKI reconstruction than after isolated ACL reconstruction. Potentially modifiable risk factors for OA after MLKI were identified and include obesity, tobacco use, depression, and the need for motion-restoring surgery.

A fully automatic fine tuned deep learning model for knee osteoarthritis detection and progression analysis

Knee osteoarthritis (KOA) sufferers have one of the highest disability-adjusted life years. The entire knee joint is affected by KOA. KOA is a condition that makes it hard for the knee to move normally. In KOA, the damage to the joints is irreversible, and the only treatment is a total knee replacement (TKR), which is expensive and only lasts a short time, especially for obese people. The individual's social isolation and low quality of life are significant outcomes of KOA. Despite being time-consuming and highly subject to user variation, segmentation, manual diagnosis, and annotation of knee joints are still the most common procedure used in clinical practices to diagnose osteoarthritis. To overcome the above limitations of the previously mentioned widely used procedure and reduce diagnostic errors made by doctors, we proposed a fine-tuning KOA diagnosis model using the DenseNet169 deep learning (DL) technique to improve the efficiency of KOA diagnosis. Our model will reduce the cost of diagnosis, speed up diagnosis, and delay disease progression, enhancing the procedure from the patient's perspective. The proposed model will determine the degree of KOA diseases by making multi-classification and binary classifications of the KOA severity. It will successfully localize the opacities' peripheral, diffuse distribution, and vascular thickening. Therefore, the proposed model would enable clinicians to understand the primary causes of KOA through this localization. We evaluated the proposed model over the OAI dataset. The OAI dataset was pre-processed by artifact removal, resizing, contrast handling, and a normalization technique. The proposed model was evaluated and compared with recent classifiers. In multi-classification, the DenseNet169 model achieved 95.93%, 88.77%, 95.41%, 85.8%, and 87.08% for accuracy, sensitivity, specificity, precision, and F1-score, respectively. In binary classification, the accuracy, sensitivity, specificity, precision, and the F1-score of the DenseNet169 model were 93.78%, 91.29%, 91.29%, 87.57%, and 89.27%, respectively. Therefore, the proposed model is an unrivaled perceptive outcome with tuning as opposed to other ongoing existing frameworks.

Investigate the situation of knee osteoarthristic and evaluate the results of treatment in Ha Dong general hospital in 2021

Objective: To investigate the situation of knee osteoarthritis and evaluate the results of treatment of primary knee osteoarthritis at Ha Dong General Hospital in 2021.Subjects and methods: A retrospective descriptive study on 93 medical records with a diagnosis of knee osteoarthritis according to the standards of the American College of Rheumatology ACR 1991, VAS scale &lt; 6 points, and Damp-Cold combined with Liver and Kidney deficiency according to TCM at Ha Dong General Hospital in 2021. Experimental group: Moxibustion-infrared lamp + Doc hoat ky sinh thang decoction + Electro- acupuncture for 20 days. Control group: Doc hoat ky sinh thang decoction + Electro-acupuncture for 20 days.Results: Physical workers and BMI ≥ 23 increase the risk of knee osteoarthritis. X-ray characteristics of the knee joint: mainly degeneration with 92.47% and inflammation with 60.81%. Features of knee joint ultrasound: Knee effusion accounted for 37.84%, Baker cyst accounted for 11.86%; 83.87% had osteophyte, 51.61% had endplate sclerosis and 39.78% had joint space narrowing. According to modern medicine: the number of patients with knee osteoarthritis and inflamed knee osteoarthritis has a similar incidence. According to traditional medicine: 81.72% were diagnosed with Damp-Cold combined with Liver and Kidney deficiency; 18.28% were Damp-Heat combined with Liver and Kidney deficiency, 9.68% were Damp-Cold standalone. The pain reduction efficiency according to VAS of the experimental group was 5.96 ± 1.09 points, higher than that of the control group which was 4.56 ± 0.77 points with statistical significance (p&lt;0.05). In the experimental group, 30% of patients had no pain, 70% of patients had mild pain. In the control group, 10% of patients had moderate pain, 86.7% had mild pain and only 3.3% of patients had no pain. The difference between the two groups was statistically significant (p&lt;0.05). The improvement effect of the experimental group was better than the control group, the difference was statistically significant (p &lt; 0.05). During 20 days of treatment, there were no unwanted clinical effects.

An auxiliary diagnostic technology and clinical efficacy evaluation in knee osteoarthritis based on serum surface-enhanced Raman spectroscopy

Knee osteoarthritis (KOA), a progressive joint disease, is a leading source of chronic pain and disability, and its diagnosis mainly depends on medical imaging findings and clinical symptoms. This study aimed to explore an auxiliary diagnostic technology and clinical efficacy evaluation in KOA based on surface-enhanced Raman scattering (SERS). Three sequential experiments were performed: 1) preliminary observation of the therapeutic effects of icariin (ICA); 2) using serum SERS spectra obtained from rat models belonging to sham group, KOA group and icariin treatment group, respectively, to analyze the KOA-related expression profiles; 3) employing partial least squares (PLS) and support vector machines (SVM) algorithms to establish KOA diagnosis model. Pathological changes verified the efficacy of icariin in KOA. Raman peak assignment combined with spectral difference analysis reflected the biochemical changes associated with KOA, including amino acid, carbohydrates and collagen. ICA intervention significantly reversed these changes, although full recovery could not be achieved. Based on PLS-SVM approach, the sensitivity, specificity and accuracy of 100%, 98.33% and 98.89%, respectively, were obtained for screening KOA. This work proves that SERS has great potential to be used as an auxiliary diagnostic technology for KOA, and is also helpful for the exploration of novel KOA treatment agent.

Correlation between the Signal Intensity Alteration of Infrapatellar Fat Pad and Knee Osteoarthritis: A Retrospective, Cross-Sectional Study

Infrapatellar fat pad (IPFP) inflammation is a common pathological manifestation in knee osteoarthritis (OA). However, the significance of IPFP signal intensity alteration for clinical diagnosis and treatment of knee OA needs further research. We assessed IPFP signal intensity alteration (0-3), IPFP maximum cross-sectional area (CSA) and IPFP depth, meniscus injury, bone marrow edema, and cartilage injury from magnetic-resonance imaging (MRI) in 41 non-KOA patients (K-L grade 0 and grade I) and 68 KOA patients (K-L grade 2,3 and 4). We found that IPFP signaling was altered in all patients with KOA whose alteration was closely related to the K-L grading. We found that the IPFP signal intensity was increased in most OA patients, especially the ones in the late stage. There were significant differences in IPFP maximum CSA and IPFP depth between groups in KOA and non-KOA patients. Moreover, Spearman correlation analysis showed that IPFP signal intensity was moderately positively correlated with age, meniscal injury, cartilage injury, and bone marrow edema, and negatively correlated with height, while not correlated with visual analogue scale (VAS) scoring and body mass index (BMI). In addition, women have higher IPFP inflammation scores on MRI than men. In conclusion, IPFP signal intensity alteration is associated with joint damage in knee OA, which may have clinical significance for diagnosing and treating KOA.

Automated knee osteoarthritis severity classification using three‐stage preprocessing method andVGG16architecture

AbstractAs a nutshell, an early diagnosis of Knee Osteoarthritis (KOA) enhances the likelihood of an individual receiving treatment at its onset and prevents joint replacement surgery. Computer‐Aided‐Diagnosis (CAD) from the radiograph images have gained a wide‐spread attention in automated grading of KOA severity. But radiograph images have certain limitations, such as presence of too much noise and uneven contrast distribution across the image that impacts the accuracy and reliability of CAD systems. Therefore, a novel three‐stage pre‐processing method has been proposed using a combination of different techniques applied at sequential stages such as noise‐reduction using gaussian‐filter, normalization using pixel‐centering method, and balanced contrast enhancement technique. A transfer‐learning based VGG16 architecture has been used for severity classification. Our classification framework outperforms the existing state‐of‐the‐art methods achieving an excellent accuracy of 89.95\%. Therefore, our system can be used by the radiologists and physicians as a decision‐support tool in their daily diagnosis procedure.

Annals for Educators - February 2023.

Annals for Educators - February 2023.

The Association between Saliva and Serum Vitamin D with Knee Osteoarthritis

Background: The incidence of osteoarthritis (OA) is high in patients suffering from 25-hydroxyvitamin D3 (25(OH)D) deficiency. The goal of this study is to examine the association between saliva and serum 25(OH)D and knee OA. Methods: Serum and saliva 25(OH)D levels of 30 patients with knee OA and 30 matched healthy people in a control group were measured by ELISA. Knee pain was assessed by Western Ontario and McMaster Universities Arthritis Index (WOMAC). Data were analyzed through student’s t-test, Pearson correlation test and receiver operating characteristic (ROC). Results: The mean serum and saliva 25(OH)D levels were lower in knee OA group than the healthy group. WOMAC negatively correlated with serum (r = -0.37; P = 0.02) and with unstimulated (r = -0.30; P = 0.04) saliva 25(OH)D. The unstimulated saliva 25(OH)D cutoff value was 27.8 pg/m1 regarding the diagnosis of knee OA. Conclusion: Serum 25(OH)D levels were positively associated with saliva 25(OH)D, and 25(OH)D level in saliva, as in serum, was low in knee OA.

CORR Insights®: A Qualitative Study of Psychosocial Factors in Patients With Knee Osteoarthritis: Insights Learned From an Asian Population.

CORR Insights®: A Qualitative Study of Psychosocial Factors in Patients With Knee Osteoarthritis: Insights Learned From an Asian Population.

Artificial-Intelligence-Aided Radiographic Diagnostic of Knee Osteoarthritis Leads to a Higher Association of Clinical Findings with Diagnostic Ratings.

Radiographic knee osteoarthritis (OA) severity and clinical severity are often dissociated. Artificial intelligence (AI) aid was shown to increase inter-rater reliability in radiographic OA diagnosis. Thus, AI-aided radiographic diagnoses were compared against AI-unaided diagnoses with regard to their correlations with clinical severity. Seventy-one DICOMs (m/f = 27:42, mean age: 27.86 ± 6.5) (X-ray format) were used for AI analysis (KOALA software, IB Lab GmbH). Subjects were recruited from a physiotherapy trial (MLKOA). At baseline, each subject received (i) a knee X-ray and (ii) an assessment of five main scores (Tegner Scale (TAS); Knee Injury and Osteoarthritis Outcome Score (KOOS); International Physical Activity Questionnaire; Star Excursion Balance Test; Six-Minute Walk Test). Clinical assessments were repeated three times (weeks 6, 12 and 24). Three physicians analyzed the presented X-rays both with and without AI via KL grading. Analyses of the (i) inter-rater reliability (IRR) and (ii) Spearman's Correlation Test for the overall KL score for each individual rater with clinical score were performed. We found that AI-aided diagnostic ratings had a higher association with the overall KL score and the KOOS. The amount of improvement due to AI depended on the individual rater. AI-guided systems can improve the ratings of knee radiographs and show a stronger association with clinical severity. These results were shown to be influenced by individual readers. Thus, AI training amongst physicians might need to be increased. KL might be insufficient as a single tool for knee OA diagnosis.

Responsiveness and the Minimal Important Change of Knee Injury and Osteoarthritis Outcome Score Following Physiotherapy Intervention in Iraqi People with Knee Osteoarthritis

Background: The Knee Injury Osteoarthritis Outcome Score (KOOS) is a widely used patient-reported questionnaire to evaluate individuals with knee osteoarthritis or a history of knee injuries. Objectives: The aim of this study was to evaluate the responsiveness and establish the minimal important change (MIC) for the Arabic version of KOOS in Iraqi individuals with knee osteoarthritis following physiotherapy intervention. Methods: Fifty volunteers (13 male and 37 female, mean age: 59.3 ± 9.6 years old) with an orthopedic diagnosis of knee osteoarthritis participated in this study. The Arabic KOOS was completed by the participants once before the intervention and once after completing a 4-week physiotherapy treatment program. A seven-item global rating of change scale was used as an external anchor to assess the participants' opinion about the treatment and its possible changes. Responsiveness was evaluated by calculating the receiver operating characteristic (ROC) curve, and the MIC was established by identifying an optimal cut-off on the ROC curve. Results: All subscales of the Arabic KOOS showed an area under the curve &gt; 0.70. The MICs reflecting the values required by the participants to feel the improvement were 15.5, 14.5, 11, 11.5, and 12.5 for the pain, symptoms, activities of daily living, sports and recreation, and quality of life subscales, respectively. Conclusions: All subscales of the Arabic KOOS are responsive to physiotherapy treatment. Therapists and researchers can use the MIC values to evaluate whether their prescribed treatment was satisfactory and effective from their patients' point of view.

Non-destructive Diagnosis of Knee Osteoarthritis Based on Sparse Coding of MRI

Non-destructive Diagnosis of Knee Osteoarthritis Based on Sparse Coding of MRI

Non-destructive diagnosis of knee osteoarthritis based on sparse coding of MRI

Non-destructive diagnosis of knee osteoarthritis based on sparse coding of MRI

A Qualitative Study of Psychosocial Factors in Patients With Knee Osteoarthritis: Insights Learned From an Asian Population.

A patient's experience with knee osteoarthritis (OA) is influenced by many psychosocial contributors that can influence the impact of pain. Such factors are known to explain some of the discordance between objective clinical parameters and patient-reported levels of disability and treatment effectiveness. However, few data are available to help clinicians understand the psychosocial factors that apply to the world's many Asian populations. Insights gained from a qualitative study in such a population may support targeted interventions. In this qualitative study involving a group of Asian patients with knee OA in Singapore, we asked: (1) What psychologic factors contribute to patients' experiences, rehabilitation, and recovery? (2) What social factors contribute to patients' experiences, rehabilitation, and recovery? Semistructured interviews eliciting broad patient experiences of managing knee OA were conducted in an urban, referral-based tertiary hospital in central Singapore. Patients were recruited if they met either of the following criteria: Kellgren-Lawrence grade ≥ 3 (minimum of one knee); Knee Injury and Osteoarthritis Outcome Score ≤ 60; or the Pain average (P), interference with Enjoyment of life (E), and interference with General activity (G) (PEG) ≥ 5. All patients had a clinical diagnosis of knee OA, were ambulatory in the community with or without a walking aid, had not undergone partial arthroplasty or TKA, were prescribed nonsurgical treatment, and were conversant in either English or Mandarin. Forty-six patients (30 women and 16 men, mean age 64 years old) were recruited for this study. A thematic analysis with elements of grounded theory and framework analysis was performed using a deductive approach. Psychologic influences specific to patients' behavioral and emotional responses to pain, as well as social factors known to have an impact on the experience of managing knee OA, were identified in the interview transcripts and coded according to established factors from earlier research. An inductive thematic analysis was then applied to the remaining transcripts to identify new themes that emerged from the data. Thematic saturation was attained when study team members agreed data and thematic sufficiency were met in the 46 transcripts. The study team discussed and deemed the 46 transcripts to contain sufficient insights for a reasonably clear understanding of the codes and development of themes to answer the study's research questions. Six main themes related to psychosocial influences on pain emerged. Psychologic factors were "loss of face" because of knee OA, anticipation and avoidance of pain and suffering, and a vicious cycle of negative emotional experiences. The social factors we identified were social and family support, workplace environment and employment uncertainty, and built environment (patients' ability to navigate manmade structures and facilities). Psychosocial factors have an important impact on patients' physical, psychologic, and social functioning. Although several of our findings have been addressed previously, the phenomenon of loss of face and the wide spectrum of social and family support dynamics found in our Asian patients with knee OA were new findings. With loss of face, patients were concerned about how others would view the change in them, including movement changes because of knee OA. They appeared to associate the use of walking canes with major disability, loss of respect, and being discriminated against by others, motivating patients to "save face" by dissociating themselves from those stigmas, even at the cost of mobility and independence. An interplay of complex cultural processes (perceived social roles and contributions to family, desire to avoid burdening family, help-seeking behavior, and the preference for unsolicited social support) underpinned by the value of collectivism impacted the behaviors and choices patients exhibited. With knowledge about the impact of culturally relevant psychosocial factors on the experience and outcomes of patients with knee OA, clinicians will be able to screen and actively explore these factors more effectively. Especially important themes include pain perception (paying close attention to signs of pain catastrophizing and negative affect), presence of chronic illness shame associated with a diagnosis of knee OA (including the stigma associated with using a walking aid), and level of social support received and contributions of a patient's built environment to kinesiophobia. For patients who are still working, the presence of workplace stressors and management of these stressors should also be explored. Where possible, screening tools that measure psychosocial factors such as pain catastrophizing and emotional distress can also be used as an added layer of screening in busy clinical settings.

Occurrence of comorbidity following osteoarthritis diagnosis: a cohort study in the Netherlands

To determine the risk of comorbidity following diagnosis of knee or hip osteoarthritis (OA). A cohort study was conducted using the Integrated Primary Care Information database, containing electronic health records of 2.5 million patients from the Netherlands. Adults at risk for OA were included. Diagnosis of knee or hip OA (=exposure) and 58 long-term comorbidities (=outcome) were defined by diagnostic codes following the International Classification of Primary Care coding system. Time between the start of follow-up and incident diagnosis of OA was defined as unexposed, and between diagnosis of OA and the end of follow-up as exposed. Age and sex adjusted hazard ratios (HRs) comparing comorbidity rates in exposed and unexposed patient time were estimated with 99.9% confidence intervals (CI). The study population consisted of 1,890,712 patients. For 30 of the 58 studied comorbidities, exposure to knee OA showed a HR larger than 1. Largest positive associations (HR with (99.9% CIs)) were found for obesity 2.55 (2.29-2.84) and fibromyalgia 2.06 (1.53-2.77). For two conditions a HR<1 was found, other comorbidities showed no association with exposure to knee OA. For 26 comorbidities, exposure to hip OA showed a HR larger than 1. The largest were found for polymyalgia rheumatica 1.81 (1.41-2.32) and fibromyalgia 1.70 (1.10-2.63). All other comorbidities showed no associations with hip OA. This study showed that many comorbidities were diagnosed more often in patients with knee or hip OA. This suggests that the management of OA should consider the risk of other long-term-conditions.

A novel computer-assisted diagnosis method of knee osteoarthritis based on multivariate information and deep learning model

Knee Osteoarthritis (KOA) is a chronic joint disease characterized by degeneration of knee's articular cartilage. Comparing with the imaging diagnostic method, the vibroarthrographic (VAG) may be emerged as a new candidate for diagnosis of KOA in clinics. However, it is challenging for doctors to evaluate patients' condition by visually detecting VAGs due to the limited understanding about contained information. Besides, the basic physiological signals are also closely correlated with a greater risk of KOA. Based on this, we focus on studying computer-assisted diagnosis method of KOA (KOA-CAD) using multivariate information (i.e. VAGs and basic physiological signals) based on an improved deep learning model (DLM). Firstly, a new Laplace distribution-based strategy (LD-S) for classification in DLM is designed. Secondly, an aggregated multiscale dilated convolution network (AMD-CNN) is constructed to learn features from multivariate information of KOA patients. Then, a new KOA-CAD method is proposed by integrating the AMD-CNN with the LD-S to realize three CAD objectives, including the automatic KOA detection, the KOA early detection, and the KOA grading detection. Finally, the multivariate information collected clinically is applied to verify the proposed method, where the automatic detection accuracy, early detection accuracy and grading detection accuracy are 93.6%, 92.1%, and 84.2% respectively.

Nomogram model based on radiomics signatures and age to assist in the diagnosis of knee osteoarthritis

BackgroundKnee osteoarthritis (KOA) is a common disease in the elderly. An effective method for accurate diagnosis could affect the management and prognosis of patients. ObjectivesTo develop a nomogram model based on X-ray imaging data and age, and to evaluate its effectiveness in the diagnosis of KOA. MethodsA total of 4403 knee X-rays from 1174 patients (July 2017 to November 2018) were retrospectively analyzed. Radiomics features were extracted and selected from the X-ray image data to quantify the phenotypic characteristics of the lesion region. Feature selection was performed in three steps to enable the derivation of robust and effective radiomics signatures. Then, logistic regression (LR), support vector machine (SVM) AdaBoost, gradient boosting decision tree (GBDT), and multi-layer perceptron (MLP) was adopted to verify the performance of radiomics signatures. In addition, a nomogram model combining age with radiomics signatures was constructed. At last, receiver operating characteristic (ROC) curve, calibration and decision curves were used to evaluate the discriminative performance. ResultsThe LR model has the best classification performance among the four radiomics models in testing cohort (LR AUC vs. SVM AUC: 0.843 vs. 0.818, DeLong test P = 0.0024; LR AUC vs. GBDT AUC: 0.843 vs. 0.821, P = 0.0028; LR AUC vs. MLP AUC: 0.843 vs. 0.822, P = 0.0019). The nomogram model achieved better predictive efficacy than the radiomics model in testing cohort compared to radiomics models although the statistical difference was not significant (Nomogram AUC vs. Radiomics AUC: 0.847 vs. 0.843, P = 0.06). The decision curve analysis revealed that the constructed nomogram had clinical usefulness. ConclusionThe nomogram model combining radiomics signatures with age has good performance for the accurate diagnosis of KOA and may help to improve clinical decision-making.