scholarly journals Emergence of Deep Learning in Knee Osteoarthritis Diagnosis

2021 ◽  
Vol 2021 ◽  
pp. 1-20
Author(s):  
Pauline Shan Qing Yeoh ◽  
Khin Wee Lai ◽  
Siew Li Goh ◽  
Khairunnisa Hasikin ◽  
Yan Chai Hum ◽  
...  
Keyword(s):  
Deep Learning ◽  
Knee Osteoarthritis ◽  
Research Field ◽  
Knee Joints ◽  
Learning Approaches ◽  
Clinical Practices ◽  
Clinical Workflow ◽  
3 Dimensional ◽  
Knee Oa ◽  
3D Cnn

Osteoarthritis (OA), especially knee OA, is the most common form of arthritis, causing significant disability in patients worldwide. Manual diagnosis, segmentation, and annotations of knee joints remain as the popular method to diagnose OA in clinical practices, although they are tedious and greatly subject to user variation. Therefore, to overcome the limitations of the commonly used method as above, numerous deep learning approaches, especially the convolutional neural network (CNN), have been developed to improve the clinical workflow efficiency. Medical imaging processes, especially those that produce 3-dimensional (3D) images such as MRI, possess ability to reveal hidden structures in a volumetric view. Acknowledging that changes in a knee joint is a 3D complexity, 3D CNN has been employed to analyse the joint problem for a more accurate diagnosis in the recent years. In this review, we provide a broad overview on the current 2D and 3D CNN approaches in the OA research field. We reviewed 74 studies related to classification and segmentation of knee osteoarthritis from the Web of Science database and discussed the various state-of-the-art deep learning approaches proposed. We highlighted the potential and possibility of 3D CNN in the knee osteoarthritis field. We concluded by discussing the possible challenges faced as well as the potential advancements in adopting 3D CNNs in this field.

scholarly journals Speech Enhancement Using Deep Learning Methods: A Review

2021 ◽  
Vol 21 (1) ◽  
pp. 19
Author(s):  
Asri Rizki Yuliani ◽  
M. Faizal Amri ◽  
Endang Suryawati ◽  
Ade Ramdan ◽  
Hilman Ferdinandus Pardede
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Speech Enhancement ◽  
Speech Signal ◽  
Research Field ◽  
Learning Technologies ◽  
Learning Approaches ◽  
Speech Signal Processing ◽  
Generative Adversarial Network ◽  
Advantages And Disadvantages

Speech enhancement, which aims to recover the clean speech of the corrupted signal, plays an important role in the digital speech signal processing. According to the type of degradation and noise in the speech signal, approaches to speech enhancement vary. Thus, the research topic remains challenging in practice, specifically when dealing with highly non-stationary noise and reverberation. Recent advance of deep learning technologies has provided great support for the progress in speech enhancement research field. Deep learning has been known to outperform the statistical model used in the conventional speech enhancement. Hence, it deserves a dedicated survey. In this review, we described the advantages and disadvantages of recent deep learning approaches. We also discussed challenges and trends of this field. From the reviewed works, we concluded that the trend of the deep learning architecture has shifted from the standard deep neural network (DNN) to convolutional neural network (CNN), which can efficiently learn temporal information of speech signal, and generative adversarial network (GAN), that utilize two networks training.

scholarly journals A Systematic Review of Deep Learning Approaches to Educational Data Mining

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-22 ◽  
Author(s):  
Antonio Hernández-Blanco ◽  
Boris Herrera-Flores ◽  
David Tomás ◽  
Borja Navarro-Colorado
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Deep Learning ◽  
Language Processing ◽  
Educational Data Mining ◽  
Research Field ◽  
Machine Learning Techniques ◽  
Mining Machine ◽  
Learning Approaches ◽  
Learning Techniques

Educational Data Mining (EDM) is a research field that focuses on the application of data mining, machine learning, and statistical methods to detect patterns in large collections of educational data. Different machine learning techniques have been applied in this field over the years, but it has been recently that Deep Learning has gained increasing attention in the educational domain. Deep Learning is a machine learning method based on neural network architectures with multiple layers of processing units, which has been successfully applied to a broad set of problems in the areas of image recognition and natural language processing. This paper surveys the research carried out in Deep Learning techniques applied to EDM, from its origins to the present day. The main goals of this study are to identify the EDM tasks that have benefited from Deep Learning and those that are pending to be explored, to describe the main datasets used, to provide an overview of the key concepts, main architectures, and configurations of Deep Learning and its applications to EDM, and to discuss current state-of-the-art and future directions on this area of research.

scholarly journals Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Simon Olsson ◽  
Ehsan Akbarian ◽  
Anna Lind ◽  
Ali Sharif Razavian ◽  
Max Gordon
Keyword(s):  
Deep Learning ◽  
Knee Osteoarthritis ◽  
Adult Population ◽  
Weight Bearing ◽  
Correct Diagnosis ◽  
University Hospital ◽  
Knee Oa ◽  
Orthopedic Surgeons ◽  
Visual Disturbances

Abstract Background Prevalence for knee osteoarthritis is rising in both Sweden and globally due to increased age and obesity in the population. This has subsequently led to an increasing demand for knee arthroplasties. Correct diagnosis and classification of a knee osteoarthritis (OA) are therefore of a great interest in following-up and planning for either conservative or operative management. Most orthopedic surgeons rely on standard weight bearing radiographs of the knee. Improving the reliability and reproducibility of these interpretations could thus be hugely beneficial. Recently, deep learning which is a form of artificial intelligence (AI), has been showing promising results in interpreting radiographic images. In this study, we aim to evaluate how well an AI can classify the severity of knee OA, using entire image series and not excluding common visual disturbances such as an implant, cast and non-degenerative pathologies. Methods We selected 6103 radiographic exams of the knee taken at Danderyd University Hospital between the years 2002-2016 and manually categorized them according to the Kellgren & Lawrence grading scale (KL). We then trained a convolutional neural network (CNN) of ResNet architecture using PyTorch. We evaluated the results against a test set of 300 exams that had been reviewed independently by two senior orthopedic surgeons who settled eventual interobserver disagreements through consensus sessions. Results The CNN yielded an overall AUC of more than 0.87 for all KL grades except KL grade 2, which yielded an AUC of 0.8 and a mean AUC of 0.92. When merging adjacent KL grades, all but one group showed near perfect results with AUC > 0.95 indicating excellent performance. Conclusion We have found that we could teach a CNN to correctly diagnose and classify the severity of knee OA using the KL grading system without cleaning the input data from major visual disturbances such as implants and other pathologies.

scholarly journals Knee Osteoarthritis Classification Using 3D CNN and MRI

2021 ◽  
Vol 11 (11) ◽  
pp. 5196
Author(s):  
Carmine Guida ◽  
Ming Zhang ◽  
Juan Shan
Keyword(s):  
Mr Images ◽  
X Ray ◽  
3 Dimensional ◽  
Knee Oa ◽  
Grade Classification ◽  
Kellgren And Lawrence ◽  
Diagnosis Accuracy ◽  
Validation Set ◽  
3D Cnn ◽  
Ray Methods

Osteoarthritis (OA) is the most common form of arthritis and can often occur in the knee. While convolutional neural networks (CNNs) have been widely used to study medical images, the application of a 3-dimensional (3D) CNN in knee OA diagnosis is limited. This study utilizes a 3D CNN model to analyze sequences of knee magnetic resonance (MR) images to perform knee OA classification. An advantage of using 3D CNNs is the ability to analyze the whole sequence of 3D MR images as a single unit as opposed to a traditional 2D CNN, which examines one image at a time. Therefore, 3D features could be extracted from adjacent slices, which may not be detectable from a single 2D image. The input data for each knee were a sequence of double-echo steady-state (DESS) MR images, and each knee was labeled by the Kellgren and Lawrence (KL) grade of severity at levels 0–4. In addition to the 5-category KL grade classification, we further examined a 2-category classification that distinguishes non-OA (KL ≤ 1) from OA (KL ≥ 2) knees. Clinically, diagnosing a patient with knee OA is the ultimate goal of assigning a KL grade. On a dataset with 1100 knees, the 3D CNN model that classifies knees with and without OA achieved an accuracy of 86.5% on the validation set and 83.0% on the testing set. We further conducted a comparative study between MRI and X-ray. Compared with a CNN model using X-ray images trained from the same group of patients, the proposed 3D model with MR images achieved higher accuracy in both the 5-category classification (54.0% vs. 50.0%) and the 2-category classification (83.0% vs. 77.0%). The result indicates that MRI, with the application of a 3D CNN model, has greater potential to improve diagnosis accuracy for knee OA clinically than the currently used X-ray methods.

scholarly journals FRI0390 IMPACT OF ULTRASONOGRAPHY‑DETECTED QUADRICEPS CALCIFIC TENDONITIS ON PAIN AND FUNCTION IN PATIENTS WITH PRIMARY KNEE OSTEOARTHRITIS

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 793.3-793
Author(s):  
M. A. Mortada ◽  
Y. A. Amer
Keyword(s):  
Knee Osteoarthritis ◽  
Vastus Lateralis ◽  
Health Assessment ◽  
Quadriceps Tendon ◽  
Knee Joints ◽  
Knee Oa ◽  
Vastus Intermedius ◽  
Calcific Tendonitis ◽  
Advanced Stages ◽  
And Function

Background:Calcific tendonitis is most commonly seen around shoulder joint. Few cases of quadriceps calcific tendonitis (QCT) of were reported. Routine use of ultrasonography in diagnosis of knee osteoarthritis has resulted in detection of many cases of QCT.Up to the best of our knowledge, this is the first study to detect impact of QCT in knee osteoarthritis by ultrasonography.Objectives:To compare pain, function, and clinical and radiological findings among primary KOA patients with or without ultrasonography-detected QCT.Methods:A prospective, observational study study was conducted on 214 patients with knee OA in the period between february 2019 to july 2019. Ultrasonography of knee joints was done according to EULAR guidelines. Quadriceps calcific tendonitis is defined as hyperechoic mass within the quadriceps tendon with posterior shadowing. The patients were categorized into two groups according to the presence or absence of QCT.Radiological grades of Kellgren–Lawrence were recorded. Pain and functional status was assessed by visual analog scale (VAS), Health Assessment Questionnaire-II (HAQ-II), and Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC)Results:QCT were detected in 25 (11.6%) patients. Most cases of QCT were detected in vastus lateralis 18 (72%), then in vastus intermedius 5 (20%) and only 2 cases were detected in vastus medialis.QCT were detected mainly in advanced stages of knee OA; 22 cases of QCT were found in patients with grade 4 KOA.The presence of QCT was statistically significant related (P< 0.05*) with age, VAS, HAQ-II, WOMAC subscales, synovitis and effusion.Conclusion:Quadriceps calcific tendonitis is not rare. Ultrasonography can detect QCT in many cases with advanced knee OA. QCT is associated with increased pain and dysfunction in knee OAReferences:NoneDisclosure of Interests:None declared

scholarly journals A Physics-Informed, Machine Learning Emulator of a 2D Surface Water Model: What Temporal Networks and Simulation-Based Inference Can Help Us Learn about Hydrologic Processes

Water ◽  
2021 ◽  
Vol 13 (24) ◽  
pp. 3633
Author(s):  
Reed M. Maxwell ◽  
Laura E. Condon ◽  
Peter Melchior
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Water Depth ◽  
Current Model ◽  
Time Dependent ◽  
Water Model ◽  
Learning Approaches ◽  
Simulation Based ◽  
3D Cnn ◽  
Learning Architectures

While machine learning approaches are rapidly being applied to hydrologic problems, physics-informed approaches are still relatively rare. Many successful deep-learning applications have focused on point estimates of streamflow trained on stream gauge observations over time. While these approaches show promise for some applications, there is a need for distributed approaches that can produce accurate two-dimensional results of model states, such as ponded water depth. Here, we demonstrate a 2D emulator of the Tilted V catchment benchmark problem with solutions provided by the integrated hydrology model ParFlow. This emulator model can use 2D Convolution Neural Network (CNN), 3D CNN, and U-Net machine learning architectures and produces time-dependent spatial maps of ponded water depth from which hydrographs and other hydrologic quantities of interest may be derived. A comparison of different deep learning architectures and hyperparameters is presented with particular focus on approaches such as 3D CNN (that have a time-dependent learning component) and 2D CNN and U-Net approaches (that use only the current model state to predict the next state in time). In addition to testing model performance, we also use a simplified simulation based inference approach to evaluate the ability to calibrate the emulator to randomly selected simulations and the match between ML calibrated input parameters and underlying physics-based simulation.

scholarly journals Oral Administration of Polymer Hyaluronic Acid Alleviates Symptoms of Knee Osteoarthritis: A Double-Blind, Placebo-Controlled Study over a 12-Month Period

2012 ◽  
Vol 2012 ◽  
pp. 1-8 ◽  
Author(s):  
Toshiyuki Tashiro ◽  
Satoshi Seino ◽  
Toshihide Sato ◽  
Ryosuke Matsuoka ◽  
Yasunobu Masuda ◽  
...  
Keyword(s):  
Hyaluronic Acid ◽  
Placebo Group ◽  
Oral Administration ◽  
Knee Osteoarthritis ◽  
Knee Joints ◽  
Controlled Study ◽  
Double Blind ◽  
Knee Oa ◽  
Strengthening Exercise ◽  
The One

This study was conducted to investigate the efficacy of oral hyaluronic acid (HA) administration for osteoarthritis (OA) in knee joints. Sixty osteoarthritic subjects (Kellgren-Lawrence grade 2 or 3) were randomly assigned to the HA or placebo group. The subjects in the HA group were given 200 mg of HA once a day everyday for 12 months, while the subjects in the placebo group were given placebo. The subjects in both groups were requested to conduct quadriceps strengthening exercise everyday as part of the treatment. The subjects’ symptoms were evaluated by the Japanese Knee Osteoarthritis Measure (JKOM) score. The symptoms of the subjects as determined by the JKOM score improved with time in both the HA and placebo groups. This improvement tended to be more obvious with the HA group, and this trend was more obvious with the subjects aged 70 years or less. For these relatively younger subjects, the JKOM score was significantly better than the one for the placebo group at the 2nd and 4th months after the initiation of administration. Oral administration of HA may improve the symptoms of knee OA in patients aged 70 years or younger when combined with the quadriceps strengthening exercise.

scholarly journals Multicentre Study Using Machine Learning Methods in Clinical Diagnosis of Knee Osteoarthritis

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Ke Zeng ◽  
Yingqi Hua ◽  
Jing Xu ◽  
Tao Zhang ◽  
Zhuoying Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Knee Osteoarthritis ◽  
Knee Joints ◽  
Imaging Data ◽  
Learning Methods ◽  
Remote Areas ◽  
Knee Oa ◽  
Machine Learning Methods ◽  
X Ray Imaging ◽  
Automatic Methods

Knee osteoarthritis (OA) is one of the most common musculoskeletal disorders. OA diagnosis is currently conducted by assessing symptoms and evaluating plain radiographs, but this process suffers from the subjectivity of doctors. In this study, we retrospectively compared five commonly used machine learning methods, especially the CNN network, to predict the real-world X-ray imaging data of knee joints from two different hospitals using Kellgren-Lawrence (K-L) grade of knee OA to help doctors choose proper auxiliary tools. Furthermore, we present attention maps of CNN to highlight the radiological features affecting the network decision. Such information makes the decision process transparent for practitioners, which builds better trust towards such automatic methods and, moreover, reduces the workload of clinicians, especially for remote areas without enough medical staff.

scholarly journals Impact of ultrasonography detected quadriceps calcific tendinopathy on pain and function in patients with primary knee osteoarthritis

Reumatismo ◽  
2021 ◽  
Vol 73 (2) ◽  
pp. 111-116
Author(s):  
M.A. Mortada ◽  
L.I. Kotb ◽  
Y.A. Amer
Keyword(s):  
Knee Osteoarthritis ◽  
Vastus Lateralis ◽  
Health Assessment ◽  
Cross Sectional Study ◽  
Knee Joints ◽  
Cross Sectional ◽  
Calcific Tendinopathy ◽  
Knee Oa ◽  
Grade 3 ◽  
And Function

Calcific tendinopathy is most commonly seen around the shoulder joint. Only a few cases of quadriceps calcific tendinopathy (QCT) were reported. This study compares pain, function, clinical examination results, and ultrasonographic findings among primary knee osteoarthritis (KOA) patients with or without ultrasonography-detected QCT. A cross-sectional study was conducted on 214 patients with knee OA. Ultrasonography (US) of knee joints was performed according to the EULAR guidelines. Kellgren-Lawrence radiographic grading was used to score OA. Pain and functional status were assessed using the visual analog scale (VAS), the Health Assessment Questionnaire-II (HAQ-II), and the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). QCT was detected in 50 out of 428 knees (11.6%), i.e. in 46 out of 214 patients (21.49%). Most cases of QCT were detected in the following sites: 36 in the vastus lateralis (72%), 10 in the vastus intermedius (20%), and only 4 in the vastus medialis (8%). QCT was found mainly in advanced KOA stages: 44 cases of QCT were found in patients with grade 4 KOA and 6 cases in grade 3 KOA. The presence of QCT showed a statistically significant association (p<0.05) with VAS, HAQ-II, WOMAC subscales, synovitis, and effusion detected by US. In knees with ultrasound-detected QCT, ultrasonographic features of CPPD were found in 31 knees (62%). QCT was found in cases with advanced KOA and mainly with ultrasonographic findings of CPPD disease. QCT could be considered an independent poor prognostic finding regarding pain, functional activity, and response to NSAIDs.

scholarly journals Correlation between protein YKL-40 and ultrasonographic findings in active knee osteoarthritis

2018 ◽  
Vol 1 (1) ◽  
pp. 57 ◽  
Author(s):  
Rositsa Karalilova ◽  
Maria Kazakova ◽  
Anastas Batalov ◽  
Victoria Sarafian
Keyword(s):  
Synovial Fluid ◽  
Serum Concentration ◽  
Knee Osteoarthritis ◽  
Power Doppler ◽  
Strong Relationship ◽  
Serum Levels ◽  
Knee Joints ◽  
Knee Oa ◽  
American College Of Rheumatology ◽  
A Prospective Study

The aim of our study was to analyze the level of the glycoprotein YKL-40 in patients with active knee osteoarthritis (OA) and to search possible correlations with local inflammation and ultrasound (US) findings.Material and methods: A prospective study with fifty consecutive patients with active knee OA (diagnosed based on the American College of Rheumatology criteria for OA with radiographic confirmation) was performed. Concentrations of YKL-40 in serum and synovial fluid were measured by ELISA. US examinations – Gray scale (GS) US and Power Doppler (PD) US – of the knee was performed according to international guidelines. The suprapatellar, medial and lateral parapatellar recesses were scanned in each knee to evaluate synovial hypertrophy and vascularization.Results: Forty women (mean age 61.50±11.33 years old) and 10 men (aged 68.50±6.60 years old) were enrolled. We found that the synovial level of the glycoprotein (237.80±104.08 ng/ml) was significantly higher compared to the serum concentration (112.83±60.61 ng/ml, p<0.001). The serum concentration in OA patients was higher comparing with age-matched healthy controls (84.19±11.39 ng/ml) (p<0.05). A statistically significant association between YKL- 40 in synovial fluid and serum levels was shown. We determined a moderately positive linear relationship between the synovial level of the glycoprotein and the serum concentration. No association between the levels of inflammatory markers – erythrocyte sedimentation rate and C-reactive protein – and YKL-40 concentrations was detected. Our study revealed a strong relationship between YKL-40 in synovial fluid and GS US and feeble with PD US. YKL-40 correlated with inflammatory activity in knee joints and neovascularization detected by US.Conclusions: YKL-40 is involved in the pathogenesis of OA synovitis. Evaluation of YKL-40 levels in parallel with US might provide more sensitive and reliable information for the diagnosis and understanding of OA.

Sign in / Sign up

Export Citation Format

Share Document