Knee bone segmentation from MRI: A classification and literature review

Segmentation of cartilage from Magnetic Resonance (MR) images has evolved as a tool for the diagnosis of knee joint pathologies. However, accuracy and reproducibility of automated methods of cartilage segmentation may require the prior extraction of bone surfaces from MR imaging sequences specifically designed to evidence the cartilage and not the bone. Thus a priori knowledge of knee joint structures and fully automated segmentation methods are adopted to provide reliable detection of bone surfaces. In this paper, we review knee bone segmentation methods from MR images. We classified the methods proposed in literature according to the level of a priori knowledge, the level of automation and the level of manual user interaction. Furthermore we discuss the segmentation results in literature in relation to the MR sequences used to image the bone. 2016 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. Published by Elsevier Sp. z o.o. All rights reserved.

从磁共振（MR）图像中对软骨进行分割已发展成为一种诊断膝关节病变的工具。然而，软骨自动分割方法的准确性和可重复性可能需要从专门用于显示软骨而非骨骼的MR成像序列中预先提取骨表面。因此，采用膝关节结构的先验知识和全自动分割方法来提供可靠的骨表面检测。在本文中，我们综述了从MR图像中对膝关节骨进行分割的方法。我们根据先验知识水平、自动化水平和手动用户交互水平对文献中提出的方法进行了分类。此外，我们还结合用于对骨骼成像的MR序列讨论了文献中的分割结果。2016年波兰科学院生物控制论与生物医学工程Nalecz研究所。由爱思唯尔有限责任公司出版。保留所有权利。