Abstract
BackgroundThis study focuses on osteoarthritis (OA), which affects millions of adults and occurs in knee cartilage. Diagnosis of OA requires accurate segmentation of cartilage structures. Existing approaches to cartilage segmentation of knee imaging suffer from either lack of fully automatic algorithm, sub-par segmentation accuracy, or failure to consider all three cartilage tissues.MethodsWe propose a novel segmentation algorithm for knee cartilages with level set-based segmentation method and novel template data. We used 20 normal subjects from osteoarthritis initiative database to construct new template data. We adopt spatial fuzzy C-mean clustering for automatic initialization of contours. Force function of our algorithm is modified to improve segmentation performance.ResultsThe proposed algorithm resulted in dice similarity coefficients (DSCs) of 87.1, 84.8 and 81.7 % for the femoral, patellar, and tibial cartilage, respectively from 10 subjects. The DSC results showed improvements of 8.8, 4.3 and 3.5 % for the femoral, patellar, and tibial cartilage respectively compared to existing approaches. Our algorithm could be applied to all three cartilage structures unlike existing approaches that considered only two cartilage tissues.ConclusionsOur study proposes a novel fully automated segmentation algorithm adapted for three types of knee cartilage tissues. We leverage state-of-the-art level set approach with newly constructed knee template. The experimental results show that the proposed method improves the performance by an average of 5 % over existing methods.
Highlights
This study focuses on osteoarthritis (OA), which affects millions of adults and occurs in knee cartilage
We focused on the level set segmentation algorithm and on parametric deformable models, because the level set segmentation algorithm can accommodate the variability of biological structures over time and across individuals
Parameters and performance metric We demonstrated the performance of the proposed method on cartilage segmentation in knee magnetic resonance (MR) images with a size of 384 × 384 × 160 pixels
Summary
This study focuses on osteoarthritis (OA), which affects millions of adults and occurs in knee cartilage. This study is focused on osteoarthritis (OA), a prevalent but poorly understood disease that affects millions of adults and occurs in the bone-like cartilage of the femur or tibia [2]. Previous works attempted to segment for knee magnetic resonance imaging (MRI) from various techniques; atlas-based segmentation [3,4,5,6,7] and others [8,9,10,11]. The cartilage segmentation is difficult, because cartilage intensity varies, it is thin, and fat and muscle tissues encircle the cartilage boundary. Fat and muscle tissue in a knee MRI create abstract noise, which leads to holes or over-segmentation
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have