Construction of a knee osteoarthritis diagnostic system based on X-ray image processing

Li, Yongping; Xu, Ning; Liu, Qiang

doi:10.1007/s10586-018-2677-y

Cited by 8 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4. The detailed methodology of LCM segmentation technique has already been implemented and published [23,24]. An automatic cropping algorithm is then applied to isolate the knee joint space from the segmented image using colour scale maping technique, highlighting knee joint space (Fig.…”

Section: Segmentation Using Local Center Of Mass Algorithm and Extraction Of Region Of Interestmentioning

confidence: 99%

Automatic Detection and Classification of Human Knee Osteoarthritis Using Convolutional Neural Networks

Sikkandar¹,

Begum²,

Alkathiry³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Knee Osteoarthritis (KOA) is a degenerative knee joint disease caused by 'wear and tear' of ligaments between the femur and tibial bones. Clinically, KOA is classified into four grades ranging from 1 to 4 based on the degradation of the ligament in between these two bones and causes suffering from impaired movement. Identifying this space between bones through the anterior view of a knee X-ray image is solely subjective and challenging. Automatic classification of this process helps in the selection of suitable treatment processes and customized knee implants. In this research, a new automatic classification of KOA images based on unsupervised local center of mass (LCM) segmentation method and deep Siamese Convolutional Neural Network (CNN) is presented. First-order statistics and the GLCM matrix are used to extract KOA anatomical Features from segmented images. The network is trained on our clinical data with 75 iterations with automatic weight updates to improve its validation accuracy. The assessment performed on the LCM segmented KOA images shows that our network can efficiently detect knee osteoarthritis, achieving about 93.2% accuracy along with multi-class classification accuracy of 72.01% and quadratic weighted Kappa of 0.86.

show abstract

Section: Segmentation Using Local Center Of Mass Algorithm and Extraction Of Region Of Interestmentioning

confidence: 99%

Automatic Detection and Classification of Human Knee Osteoarthritis Using Convolutional Neural Networks

Sikkandar¹,

Begum²,

Alkathiry³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…-Bone defects: In severe cases of knee joint disorders, bone defects may develop [20]. These morphological changes can be detected on X-ray examination, MRI (magnetic resonance imaging), or other imaging methods, as well as during surgical intervention for the knee joint disorder [21].…”

Section: Introduction / вступmentioning

confidence: 99%

The Knee Joint Is the Achilles' Heel of a Child's Body

Protsaylo,

Dzhyvak,

Synytska

et al. 2023

EUMJ

View full text Add to dashboard Cite

The study objective was to draw practicing physicians’ attention to the risk of knee joint disorders in children during intensive growth to ensure timely detection and treatment. Materials and Methods. We analyzed the results of studies on the diseases of the knee joint carried out by modern scientists over the past ten years. We also took into account the clinical observations of children receiving inpatient treatment at the regional children's hospital. The examination methods were radiography, computer tomography, magnetic resonance imaging, and ultrasound. Results and Discussion. During growth, a child's knee joint is subjected to enormous loads and is sensitive to external and internal factors. The knee joint plays a dominant role in the limb’s longitudinal growth; the growth zones grow so intensively that they can be compared to the work of a "bone nuclear reactor." The bones of the skeleton grow unevenly and intermittently. The peak height velocity is observed at 10–14 years in girls and at 13–18 years in boys; then, height velocity slows down, and after 19 years, height growth almost stops. During the period of intensive growth, bones are very sensitive to internal and external factors of shape formation (growth hormones, physiological loads, radiation, vibration, injuries, hypothermia, metabolic disorders, etc. Therefore, this part is most sensitive to various endogenous and exogenous factors, which is manifested by various dysplastic changes and diseases. Conclusions. During the intensive growth of the child, the knee joint is most vulnerable to various endogenous and exogenous negative factors, which is manifested by various diseases. Osteogenic sarcoma, fibrous cortical defect, and juvenile osteocartilaginous exostoses most often affect the weakest place of the knee joint – the metaphyses of the femur and tibia (Achilles’ heel).

show abstract

Resource allocation and aging priority-based scheduling of linear workflow applications with transient failures and selective imprecise computations

Karatza,

Stavrinides

2024

Cluster Comput

View full text Add to dashboard Cite

Construction of a knee osteoarthritis diagnostic system based on X-ray image processing

Cited by 8 publications

References 53 publications

Automatic Detection and Classification of Human Knee Osteoarthritis Using Convolutional Neural Networks

Automatic Detection and Classification of Human Knee Osteoarthritis Using Convolutional Neural Networks

The Knee Joint Is the Achilles' Heel of a Child's Body

Resource allocation and aging priority-based scheduling of linear workflow applications with transient failures and selective imprecise computations

Contact Info

Product

Resources

About