This study aims to develop and validate an artificial intelligence (AI)-assisted platform for musculoskeletal knee ultrasonography and to establish an interpretable prediction model for clinical outcomes following ultrasound-guided injection therapies in patients with degenerative knee disorders. The project seeks to improve the standardization, reproducibility, and clinical utility of knee ultrasound by reducing operator dependency and providing quantitative image analysis and outcome prediction.
The study will be conducted in three phases. First, an AI foundation model for knee ultrasonography will be developed using standardized image acquisition protocols to enable automated localization, segmentation, and quantitative assessment of major anatomical structures, including tendons, ligaments, cartilage, fat pads, and peripheral nerves. Second, supervised machine learning models will be trained to classify normal and pathological ultrasound findings, including common degenerative and inflammatory abnormalities affecting the knee. Third, retrospective and prospective clinical data from approximately 150 patients receiving ultrasound-guided injection therapies will be integrated to develop and validate a predictive model for treatment outcomes using imaging biomarkers and clinical variables. Treatment response will be evaluated using validated patient-reported outcome measures, and explainable AI methods will be applied to improve model interpretability.
The anticipated outcome of this study is the development of a comprehensive AI-assisted knee ultrasound platform that supports standardized image interpretation, quantitative assessment of musculoskeletal pathology, and personalized prediction of treatment response to ultrasound-guided injection therapies in degenerative knee disorders.
Clinical diagnosis of healthy adult without major systemic disease
Age ≥18 years
Able to understand and follow study instructions
Ambulatory without walking aids
Previous knee surgery
Rupture of one or more cruciate ligaments
Knee injection within the preceding 6 months
Major trauma involving the knee or periarticular region
The study will be conducted in three phases. First, an AI foundation model for knee ultrasonography will be developed using standardized image acquisition protocols to enable automated localization, segmentation, and quantitative assessment of major anatomical structures. Second, supervised machine learning models will be trained to classify normal and pathological ultrasound findings, including common degenerative and inflammatory abnormalities affecting the knee. Third, retrospective and prospective clinical data from approximately 150 patients receiving ultrasound-guided injection therapies will be integrated to develop and validate a predictive model for treatment outcomes using imaging biomarkers and clinical variables. Treatment response will be evaluated using validated patient-reported outcome measures, and explainable AI methods will be applied to improve model interpretability.
Cohort
Prospective
artificial intelligence-assisted advanced analysis
Diagnostic testThe study will be conducted in three phases. First, an AI foundation model for knee ultrasonography will be developed using standardized image acquisition protocols to enable automated localization, segmentation, and quantitative assessment of major anatomical structures. Second, supervised machine learning models will be trained to classify normal and pathological ultrasound findings, including common degenerative and inflammatory abnormalities affecting the knee. Third, retrospective and prospective clinical data from approximately 150 patients receiving ultrasound-guided injection therapies will be integrated to develop and validate a predictive model for treatment outcomes using imaging biomarkers and clinical variables. Treatment response will be evaluated using validated patient-reported outcome measures, and explainable AI methods will be applied to improve model interpretability.
AI Segmentation Performance for Normal Knee Structures
Performance of the artificial intelligence model in automatically identifying and segmenting normal knee anatomical structures on ultrasound images. Model performance will be evaluated using the Dice Similarity Coefficient (DSC) and Intersection-over-Union (IoU) by comparing AI-generated segmentation with expert manual annotations. Target structures include tendons, ligaments, cartilage, menisci, fat pads, and peripheral nerves.
Diagnostic Accuracy of AI-Based Classification of Knee Pathologies
Diagnostic performance of the AI model in differentiating normal and pathological knee structures on ultrasound imaging. Performance will be evaluated using accuracy, sensitivity (recall), specificity, precision, F1-score, and area under the receiver operating characteristic curve (AUC), using expert ultrasound interpretation as the reference standard. Pathologies include tendinopathy, calcification, ligament sprain or tear, meniscal degeneration or tear, cartilage degeneration, synovitis, fat pad inflammation, and peripheral nerve enlargement.
Accuracy of AI Prediction for Treatment Success
Performance of the AI-assisted prediction model in identifying patients who achieve successful clinical outcomes after ultrasound-guided injection therapy. Treatment success will be defined according to achievement of the Minimal Clinically Important Difference (MCID) in KOOS and/or attainment of the Patient Acceptable Symptom State (PASS). Predictive performance will be assessed using AUC, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value.
Knee Pain Intensity
Pain intensity assessed using the Visual Analog Scale (VAS; 0-10), with higher scores indicating greater pain severity.
Knee Function
Functional status assessed using the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), including pain, stiffness, and physical function subscales. Higher scores indicate worse symptoms and functional limitation.
Knee Injury and Osteoarthritis Outcome Score (KOOS)
Clinical improvement following ultrasound-guided injection therapy assessed using the Knee Injury and Osteoarthritis Outcome Score (KOOS). Higher scores indicate better knee function and fewer symptoms.
Patient Acceptable Symptom State (PASS)
Proportion of participants achieving a patient-acceptable symptom state following treatment according to validated PASS criteria.
Click on the lead sponsor to view all of their trials.
National Taiwan University Hospital
Lead sponsor
National Taiwan University Hospital Beihu Branch
Collaborator
