Fully automated, level set-based segmentation for knee MRIs using an adaptive force function and template: data from the osteoarthritis initiative
Fully automated, level set-based segmentation for knee MRIs using an adaptive force function and template: data from the osteoarthritis initiative
复制标题
DOI：
10.1186/s12938-016-0225-7
复制
发表时间：
2016-08-24
影响因子：
3.9
通讯作者：
Park, Hyunjin
中科院分区：
文献类型：
--
作者：
Ahn, Chunsoo;Bui, Toan Duc;Park, Hyunjin
背景：这项研究的重点是骨关节炎，它影响数以百万计的成年人，发生在膝关节软骨。骨性关节炎的诊断需要准确的软骨结构分割。现有的膝关节图像软骨分割方法要么缺乏全自动算法，要么分割精度低于标准杆，要么没有综合考虑三种软骨组织。方法：提出了一种基于水平集分割方法和新颖模板数据的膝关节软骨分割算法。我们从骨性关节炎初始数据库中选取了20名正常受试者来构建新的模板数据。采用空间模糊C均值聚类的方法对轮廓进行自动初始化。结果：该算法对10个受试者的股骨、膝盖骨和胫骨软骨的骰子相似系数分别为87.1、84.8和81.7%。DSC结果显示，与现有入路相比，股骨、髌骨和胫骨软骨的改善分别为8.8、4.3和3.5%。我们的算法可以应用于所有三种软骨结构，而不是现有的只考虑两种软骨组织的方法。结论：我们的研究提出了一种新的适用于三种类型膝关节软骨组织的全自动分割算法。我们利用最先进的水平集方法和新构建的膝盖模板。实验结果表明，该方法比现有方法平均提高了5%的性能。
Background: This 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.Methods: We 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.Results: The 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.Conclusions: Our 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.