Oct 2026· Engineering, Technology & Applied Science Research· 0 citations· 12 references
TL;DR
An ROI-aware ordinal and uncertainty-aware multi-task framework for automated KOA severity assessment that integrates ROI-guided feature learning, ordinal KL-grade classification, and severity regression to better model progressive disease characteristics is proposed.
Abstract
Knee Osteoarthritis (KOA) severity assessment from X-ray images remains challenging due to subtle radiographic differences between adjacent Kellgren–Lawrence (KL) grades, particularly in early-stage cases. This paper proposes an ROI-aware ordinal and uncertainty-aware multi-task framework for automated KOA severity assessment. The proposed framework integrates ROI-guided feature learning, ordinal KL-grade classification, and severity regression to better model progressive disease characteristics. ConvNeXt and Swin Transformer are utilized for hierarchical feature extraction and contextual representation learning, while uncertainty estimation is incorporated to identify ambiguous predictions between neighboring KL grades. Experiments were conducted on approximately 18,000 knee X-ray images collected from multiple public and clinical datasets labeled according to the Kellgren–Lawrence (KL) grading system. The proposed framework achieved 90.7% classification accuracy, a Macro F1-score of 0.89, and a Quadratic Weighted Kappa (QWK) score of 0.93, demonstrating improved reliability and interpretability for AI-assisted KOA severity assessment.
Objectives: To develop a model for the classification of knee OsteoArthritis (OA) on radiographs, which is computationally efficient and severity ordered. Method: This study focuses on class imbalance, adjacent-grade confusion and high computational cost of multi-model hybrid systems. The proposed SOBR-KneeNet (Severit...
S. Bruntha, M. Chidambaram· Indian Journal of Science an...· 0 citations
Radiographic assessment of knee osteoarthritis remains challenging when adjacent grades on the Kellgren–Lawrence (KL) scale differ only slightly and model predictions are uncertain. We evaluated a “coarse-from-fine” approach based on EfficientNetB3 in a retrospective internal validation study. The hybrid model learned...
Kevin Alejandro Yepez, Emmily Villacreses, D. Almeida-Galárraga et al.· Bioengineering· 0 citations
A multi‐modal, artificial intelligence (AI)‐driven framework for automated grading of knee osteoarthritis severity from radiographs, integrating advanced detection, deep learning, radiomics, and clinical data is developed and validated.
Qi-Chang Yue, Qian Wang, Chang-Shuang Bai et al.· International journal of ima...· 0 citations
Automated osteoporosis assessment from knee radiographs remains a challenging computer-aided diagnosis task due to subtle structural differences among normal, osteopenic, and osteoporotic bone patterns, together with the limited availability of transparent and reproducible evaluation frameworks based on publicly access...
Sara Medhat, Wessam S. ElAraby, M. Saad et al.· Scientific Reports· 0 citations
Assessment of periodontal bone resorption severity from panoramic radiographs can be time-consuming and subject to inter-observer variability. This study evaluates a multimodal deep learning framework for automated Bone Resorption Age Ratio (BRAR)-based severity classification by integrating panoramic radiographi...
Adnan Salman, I. Bishtawi· BMC Medical Imaging· 0 citations
Knee osteoarthritis (KOA) is a leading cause of physical disability and currently has no curative clinical treatment. Early diagnosis and accurate prognosis are therefore vital for managing its progression. Existing methods mainly predict future severity grades and provide limited visual explanation of structural chang...
Shao-Tian Li, Chenhui Wang, Wen-Hua Wu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.