Skip to content
Open access

Computer Aided Diagnostic Model for Knee Osteoarthritis: A Multi-modal Feature Regression Approach

2023 · Research Square · 0 citations · 25 references

Abstract

Abstract Background: Knee osteoarthritis (KOA) is a prevalent and debilitating form of arthritis, posing a substantial burden on patients' quality of life. Timely and precise diagnosis is pivotal in impeding disease progression and averting the necessity for invasive interventions such as joint replacement surgery. Given the widespread availability of X-ray imaging, there exists a critical need for an effective diagnostic methodology for KOA. Methods: In response to this need, this study introduces a novel computer-aided diagnostic model for KOA, based on multi-modal feature regression with X-ray image. Specifically, two different modals of diagnostic features are extracted. Firstly, by analyzing the diagnostic indicators of KOA with X-ray image, this study explores the diagnostic basis of osteoarthritis from the perspective of X-ray image content, and then designed several image content-based features for measuring bone gap, bone skin thickness and bone mass. Meanwhile, medical information-based features such age, gender and surgical history are also integrated as diagnostic features. Then, the mapping relationship between diagnostic features and the prevalence of osteoarthritis (denoted by K-L classification) is established by support vector regression as knee osteoarthritis diagnostic model Results: To validate the efficacy of our diagnostic model, we curated the NDKY-N2H knee X-ray image database, encompassing 300 knee joint X-ray images, each paired with its corresponding K-L classification. Experimental indicators, such as diagnostic accuracy can be better than 90%, which affirm the judicious design and competence of the proposed diagnostic model. It demonstrates noteworthy performance in knee osteoarthritis diagnosis. Conclusion: In summary, our research underscores the paramount importance of precise KOA diagnosis in ameliorating patient well-being and obviating the need for surgical interventions. The innovative multi-modal feature regression-based approach, amalgamating image content-based and medical information-based features, exhibits great potential for delivering dependable and effective KOA diagnoses via X-ray imaging. These findings not only contribute substantially to the arena of arthritis diagnosis but also lay a robust foundation for practical tools empowering healthcare professionals to enhance patient outcomes in cases of knee osteoarthritis.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.