Knee Cartilage Estimation Based on Knee Bone Geometry Using Posterior Shape Model

Hao Chen, Tao Tan, Yan Kang, Yue Sun, Hui Xie, Xinye Wang, Nico Verdonschot

研究成果: Article同行評審

摘要

Osteoarthritis (OA) is a degenerative joint disease characterized by cartilage degradation and changes in bone morphology, typically assessed through magnetic resonance imaging (MRI). This study introduces a method using a posterior shape model (PSM) to estimate cartilage thickness based solely on bone geometry. Utilizing the SKI10 public MRI dataset, we developed bone shape and combined bone-cartilage shape models through a leave-one-out (LOO) experiment involving 99 folds. Cartilage estimation in the tibiofemoral contact and surgical areas relied solely on bone geometry, using a PSM. This novel method, compared against current state-of-the-art techniques, demonstrated a predictable correlation in cartilage thickness in regions where bone relationship information is available. The validation of the model was conducted using a cross-validation technique on the dataset, comparing the predicted cartilage thickness with actual measurements obtained through manual segmentation. Employing bone gap data at the tibiofemoral contact point, our cartilage thickness prediction achieved a root mean square error (RMSE) compared to the manual segmentation of 0.64 mm for the femur and 0.58 mm. Preliminary results indicate that the proposed method can successfully estimate cartilage information in scenarios where direct cartilage imaging is unavailable. This approach holds promise for enhancing diagnostic capabilities in knee joint conditions where cartilage assessment is critical.

原文English
頁(從 - 到)30600-30607
頁數8
期刊IEEE Sensors Journal
24
發行號19
DOIs
出版狀態Published - 2024

指紋

深入研究「Knee Cartilage Estimation Based on Knee Bone Geometry Using Posterior Shape Model」主題。共同形成了獨特的指紋。

引用此