Surface-based rigid registration using a global optimization algorithm for assessment of MRI knee cartilage thickness changes. (April 2015)

• Record Type: Journal Article
• Authors: Guo, Changyong; Cheng, Yuanzhi; Guo, Haoyan; Wang, Jinke; Wang, Yadong; Tamura, Shinichi
• Is Part Of: Biomedical signal processing and control. Volume 18(2015)
• Page Start: 303
• Page End: 316
• Publication Date: 2015-04
• Subjects: Cartilage segmentation -- Changes over time -- Femoral cartilage -- Global optimization -- Registration; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2015.02.007
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: An approach for globally solving the 3D rigid registration problem is proposed. The method was used for assessment for MRI knee cartilage thickness changes. The method was evaluated on MR images from porcine knees and human knees. Experimental results show the effectiveness of our approach. Abstract: Registration methods have become an important tool in many medical applications. Existing methods require a good initial estimation (transformation) in order to find a global solution, i.e., if the initial estimation is far from the actual solution, incorrect solution or mismatching is very likely. In contrast, this paper presents a novel approach for globally solving the three dimensional (3D) rigid registration problem. The registration is grounded on a mathematical theory—Lipschitz optimization. It achieves a guaranteed global optimality with a rough initial estimation (e.g., even a random guess). Moreover, Munkres assignment algorithm is used to find the point correspondences. It applies the distance matrix to find an optimal correspondence. Our method is evaluated and demonstrated on MR images from porcine knees and human knees. Compared with state-of-the-art methods, the proposed technique is more robust, more accurate to perform point to point comparisons of knee cartilage thickness values for follow-up studies on the same subject.