Knee Osteoarthritis
Knee osteoarthritis (OA) is a debilitating joint disease characterized by cartilage degeneration and bone changes, impacting millions globally. Current research focuses on developing accurate and efficient automated diagnostic tools using deep learning models, such as convolutional neural networks (CNNs), transformers, and generative adversarial networks (GANs), often incorporating multi-modal data (X-rays, MRI) and advanced techniques like self-supervised learning and domain adaptation to improve diagnostic accuracy and reduce reliance on large annotated datasets. These advancements aim to improve the objectivity and efficiency of OA diagnosis and severity grading, ultimately leading to better patient care and more effective clinical trial design.
Papers
Cascade learning in multi-task encoder-decoder networks for concurrent bone segmentation and glenohumeral joint assessment in shoulder CT scans
Luca Marsilio, Davide Marzorati, Matteo Rossi, Andrea Moglia, Luca Mainardi, Alfonso Manzotti, Pietro Cerveri
Personalized Prediction Models for Changes in Knee Pain among Patients with Osteoarthritis Participating in Supervised Exercise and Education
M. Rafiei, S. Das, M. Bakhtiari, E.M. Roos, S.T. Skou, D.T. Grønne, J. Baumbach, L. Baumbach
Exploring the Efficacy of Base Data Augmentation Methods in Deep Learning-Based Radiograph Classification of Knee Joint Osteoarthritis
Fabi Prezja, Leevi Annala, Sampsa Kiiskinen, Timo Ojala
Adaptive Variance Thresholding: A Novel Approach to Improve Existing Deep Transfer Vision Models and Advance Automatic Knee-Joint Osteoarthritis Classification
Fabi Prezja, Leevi Annala, Sampsa Kiiskinen, Suvi Lahtinen, Timo Ojala