scholarly journals A Novel Hybrid Approach Based on Deep CNN Features to Detect Knee Osteoarthritis

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6189
Author(s):  
Rabbia Mahum ◽  
Saeed Ur Rehman ◽  
Talha Meraj ◽  
Hafiz Tayyab Rauf ◽  
Aun Irtaza  ◽  
...  
Keyword(s):  
Knee Joint ◽  
Knee Osteoarthritis ◽  
Hybrid Approach ◽  
Joint Space Width ◽  
Local Binary Patterns ◽  
Bone Diseases ◽  
Support Vector ◽  
Joint Movement ◽  
X Ray

In the recent era, various diseases have severely affected the lifestyle of individuals, especially adults. Among these, bone diseases, including Knee Osteoarthritis (KOA), have a great impact on quality of life. KOA is a knee joint problem mainly produced due to decreased Articular Cartilage between femur and tibia bones, producing severe joint pain, effusion, joint movement constraints and gait anomalies. To address these issues, this study presents a novel KOA detection at early stages using deep learning-based feature extraction and classification. Firstly, the input X-ray images are preprocessed, and then the Region of Interest (ROI) is extracted through segmentation. Secondly, features are extracted from preprocessed X-ray images containing knee joint space width using hybrid feature descriptors such as Convolutional Neural Network (CNN) through Local Binary Patterns (LBP) and CNN using Histogram of oriented gradient (HOG). Low-level features are computed by HOG, while texture features are computed employing the LBP descriptor. Lastly, multi-class classifiers, that is, Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN), are used for the classification of KOA according to the Kellgren–Lawrence (KL) system. The Kellgren–Lawrence system consists of Grade I, Grade II, Grade III, and Grade IV. Experimental evaluation is performed on various combinations of the proposed framework. The experimental results show that the HOG features descriptor provides approximately 97% accuracy for the early detection and classification of KOA for all four grades of KL.

Convolutional Neural Network-Based Automatic Measurement of Joint Space Width to Predict Radiographic Severity and Progression of Knee Osteoarthritis

2021 ◽  
Author(s):  
James Chung Wai Cheung ◽  
Yiu Chow TAM ◽  
Lok Chun CHAN ◽  
Ping Keung CHAN ◽  
Chunyi WEN
Keyword(s):  
Neural Network ◽  
Knee Osteoarthritis ◽  
Convolutional Neural Network ◽  
Pearson Correlation ◽  
Joint Space Width ◽  
Joint Space ◽  
Receiver Operating Curve ◽  
Radiographic Severity ◽  
X Ray ◽  
Space Width

Abstract Objectives To develop a deep convolutional neural network (CNN) for the segmentation of femur and tibia on plain x-ray radiographs, hence enabling an automated measurement of joint space width (JSW) to predict the severity and progression of knee osteoarthritis (KOA). Methods A CNN with ResU-Net architecture was developed for knee X-ray imaging segmentation. The efficiency was evaluated by the Intersection over Union (IoU) score by comparing the outputs with the annotated contour of the distal femur and proximal tibia. By leveraging imaging segmentation, the minimal and multiple JSWs in the tibiofemoral joint were estimated and then validated by radiologists’ measurements in the Osteoarthritis Initiative (OAI) dataset using Pearson correlation and Bland–Altman plot. The estimated JSWs were deployed to predict the radiographic severity and progression of KOA defined by Kellgren-Lawrence (KL) grades using the XGBoost model. The classification performance was assessed using F1 and area under receiver operating curve (AUC). Results The network has attained a segmentation efficiency of 98.9% IoU. Meanwhile, the agreement between the CNN-based estimation and radiologist’s measurement of minimal JSW reached 0.7801 (p < 0.0001). Moreover, the 32-point multiple JSW obtained the highest AUC score of 0.656 to classify KL-grade of KOA. Whereas the 64-point multiple JSWs achieved the best performance in predicting KOA progression defined by KL grade change within 48 months, with AUC of 0.621. The multiple JSWs outperform the commonly used minimum JSW with 0.587 AUC in KL-grade classification and 0.554 AUC in disease progression prediction. Conclusion Fine-grained characterization of joint space width of KOA yields comparable performance to the radiologist in assessing disease severity and progression. We provide a fully automated and efficient radiographic assessment tool for KOA.

scholarly journals Changes in Knee Joint Space Width in Treatment with a New Hyaluronic-Based Hydrogel

2017 ◽  
Vol 63 (3) ◽  
pp. 125-128
Author(s):  
Octav Marius Russu ◽  
Andrei Marian Feier ◽  
Tudor Sorin Pop ◽  
Marcela Todoran ◽  
István Gergely
Keyword(s):  
Hyaluronic Acid ◽  
Knee Joint ◽  
Knee Osteoarthritis ◽  
Joint Space Narrowing ◽  
Joint Space Width ◽  
Joint Space ◽  
One Year ◽  
A Minor ◽  
Space Width

AbstractObjective: Our purpose was to assess the effect of a new hyaluronic acid-based (Hymovis®) injections on joint space width narrowing in patients diagnosed with knee osteoarthritis.Methods: A prospective clinical trial was conducted in the Department of Orthopedics and Traumatology II from the Clinical County Hospital, Tîrgu Mureș, Romania. Thirty-five patients diagnosed with idiopathic knee osteoarthritis received two intraarticular injections with hyaluronic acid-based hydrogel (24 mg of hyaluronic acid/3 ml) at one-week interval. Anteroposterior radiographs were obtained before the injections, at six and twelve months after. Minimum joint space width was measured by two senior orthopaedics surgeons at each follow up. Each radiograph was measured again by the same evaluators two weeks apart.Results: Thirty-one patients were present at the final follow-up. A minor reduction in mean weight was noticed (from 82.2 kg ± 16.2 kg to 80.9 kg ± 16.0, p > 0.398) without any correlation with joint space width narrowing. There were no major changes at the first follow up (6 months) regarding joint space narrowing. A reduction in joint space width was observed however at 12 months varying from 4.4 mm (SD ± 1.64, range 1.8-7.1) at the first assessment to 4.3 mm (SD ± 1.26, range 0.0-6.8) at the final follow-up but with no statistical difference (p=0.237).Conclusion: No significant modification in joint space width at the final follow-up secondarily proved that two injections of Hymovis® may slow down narrowing in the knee joint space over a one-year period.

scholarly journals RADIOLOGICAL ASSESSMENT OF KNEE JOINT WIDTH DIFFERENCES IN OLDER ADULTS WITH SYMPTOMATIC MEDIAL KNEE OSTEOARTHRITIS

2021 ◽  
Author(s):  
SAMWON YOON ◽  
YOUNGJOO CHA ◽  
HYUNSIK YOON ◽  
KYOUNGTAE KIM ◽  
ILBONG PARK ◽  
...  
Keyword(s):  
Older Adults ◽  
Knee Joint ◽  
Knee Osteoarthritis ◽  
Joint Space Width ◽  
Lower Limbs ◽  
Unaffected Side ◽  
Medial Knee ◽  
Knee Oa ◽  
Affected Side ◽  
Significant Difference

Knee osteoarthritis (OA) is a degenerative articular disease. The knee joint space width (JSW) is used for grading the severity of knee OA. However, there is a lack of research on differences in the widths of knee joints between both lower limbs in unilateral OA. The purpose of this research was to examine the radiological difference in the affected knee joint and contralateral knee joint by analyzing unilateral older adults with medial knee OA using both knees’ JSW differences. Twenty-five subjects with unilateral medial knee OA participated. X-ray radiographs were used to assess knee JSW, and the paired [Formula: see text]-test was performed to assess the knee joint gap width between the affected side and the unaffected side in the respective medial and lateral sides. The independent [Formula: see text]-test compared the differences between the lateral and medial knee JSWs on the affected side and unaffected side. The paired [Formula: see text]-test did not show a significant difference in the medial and lateral knee JSW on the affected side compared to the unaffected side ([Formula: see text]; 0.11). Meanwhile, the independent [Formula: see text]-test revealed a significant difference between the affected and unaffected sides ([Formula: see text]). This study showed no significant changes in affected knee JSWs compared to unaffected sides, but the difference between the lateral and medial JSWs was significant between the knees affected and unaffected by OA in the older adults with medial knee OA.

scholarly journals Influence of Pain on Knee Joint Movement and Moment during the Stance Phase in Patients with Severe Bilateral Knee Osteoarthritis: A Pilot Study

Medicina ◽  
2019 ◽  
Vol 55 (12) ◽  
pp. 756
Author(s):  
Takashi Fukaya ◽  
Hirotaka Mutsuzaki ◽  
Koichi Mori
Keyword(s):  
Knee Joint ◽  
Knee Osteoarthritis ◽  
Stance Phase ◽  
Three Dimensional ◽  
Knee Extensor ◽  
Three Dimensions ◽  
Knee Joints ◽  
Joint Movement ◽  
Bilateral Knee ◽  
Kinematics And Kinetics

Background and Objectives: The purpose of this study was to compare the side-to-side differences in knee joint movement and moment for the degree of pain in the walking stance phase in patients with bilateral knee osteoarthritis (KOA) of comparable severity. We hypothesized that knee joint movement and moment on the side with strong pain were lower compared with the side with weak pain. Materials and Methods: We included 11 patients diagnosed with bilateral severe KOA. In all patients’ left and right knees, the Kellgren–Lawrence radiographic scoring system grade was level 4, and the femorotibial angle and knee range of motion were equivalent. Following patients’ interviews with an orthopedic surgeon, we performed a comparative study with KOA with strong pain (KOAs) as the strong painful side and KOA with weak pain (KOAw) as the weak painful side. Data for changes in bilateral knee joint angles in three dimensions during the stance phase and bilateral knee sagittal and frontal moments exerted in the early and late stance phases were extracted from kinematics and kinetics analyses. Results: Three-dimensional joint movements in the knee joint were not significantly different in all phases between KOAs and KOAw. Knee extensor moment in the early stance phase in KOAs was significantly smaller than that in KOAw. Knee abductor moment in the early and late stance phase was not significantly different between KOAs and KOAw. Conclusions: Although we found no difference in joint motion in bilateral knee joints, knee extensor moment on the side with strong pain was decreased. In patients with bilateral severe KOA, it was suggested that the magnitude of knee pain contributed to the decrease in knee joint function.

Multi-Feature-Based Classification of Osteoarthritis in Knee Joint X-Ray Images

2019 ◽  
pp. 74-96
Author(s):  
Ravindra S. Hegadi ◽  
Dattatray N. Navale ◽  
Trupti D. Pawar ◽  
Darshan D. Ruikar
Keyword(s):  
Knee Joint ◽  
X Ray ◽  
Feature Based ◽  
Feature Based Classification

Hybrid impedance control of a knee joint orthosis

2019 ◽  
Vol 46 (2) ◽  
pp. 192-201
Author(s):  
Mohamed Amine Alouane ◽  
Hala Rifai ◽  
Kwangtaek Kim ◽  
Yacine Amirat ◽  
Samer Mohammed
Keyword(s):  
Knee Joint ◽  
Impedance Control ◽  
Hybrid Approach ◽  
Joint Torque ◽  
Joint Movement ◽  
Content Type ◽  
Control Approach ◽  
Flexion Extension ◽  
Proportional Derivative Controller ◽  
Linear Disturbance

Purpose This paper aims to deal with the design of new hybrid approach for the assistance of the flexion extension movement of the knee joint. Design/methodology/approach The control approach combines the use of a knee joint orthosis along with functional electrical stimulation (FES) within an assist-as-needed paradigm. An active impedance controller is used to assist the generation of muscular stimulation patterns during the extension sub-phase of the knee joint movement. The generated FES patterns are appropriately tailored to achieve flexion/extension movement of the knee joint, which allows providing the required assistance by the subject through muscular stimulation. The generated torque through stimulation is tracked by a non-linear disturbance observer and fed to the impedance controller to generate the desired trajectory that will be tracked using a standard proportional derivative controller. Findings The approach was tested in experiments with two healthy subjects. Results show satisfactory performances in terms of estimating the knee joint torque, as well as in terms of cooperation between the FES and the orthosis actuator during the execution of the knee joint flexion/extension movements. Originality/value The authors designed a new hybrid approach for the assistance of the flexion extension movement of the knee joint, which has not been studied yet. The control approach combines the use of a knee joint orthosis along with FES within an assist-as-needed paradigm.

Sign in / Sign up

Export Citation Format

Share Document