Evolution Model Based on Prior Information for Narrow Joint Segmentation
- PDF / 2,136,967 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 19 Downloads / 198 Views
Evolution Model Based on Prior Information for Narrow Joint Segmentation Xin Wang1 · Shuai Xu1 · Zhen Ye2 · Chao-Zheng Zhou2 · Jing Qin3 Received: 8 May 2019 / Revised: 5 June 2019 / Accepted: 30 August 2019 © Operations Research Society of China, Periodicals Agency of Shanghai University, Science Press, and Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract Automated segmentation of hip joint computed tomography images is significantly important in the diagnosis and treatment of hip joint disease. In this paper, we propose an automatic hip joint segmentation method based on a variational model guided by prior information. In particular, we obtain prior features by automatic sample selection, get a discriminative function by training these selected samples and then integrate this prior information into our variational model. Numerical results demonstrate that the proposed method has high accuracy in segmenting narrow joint regions. Keywords Image segmentation · Hip joint · CT · Feature prior · Level set · Variational model Mathematics Subject Classification 65K10 · 94A08
This research was supported in part by the National Natural Science Foundation of China (Nos. 11771276, 11471208) and the capacity construction project of local universities in Shanghai (No. 18010500600). The research of Jing Qin was supported by the National Science Foundation of USA (No. DMS-1941197).
B
Jing Qin [email protected] Xin Wang [email protected] Shuai Xu [email protected] Zhen Ye [email protected] Chao-Zheng Zhou [email protected]
1
Department of Mathematics, Shanghai University, Shanghai 200444, China
2
Shanghai Electric Central Research Institute, Shanghai 200070, China
3
Department of Mathematics, University of Kentucky, Lexington, KY 40506-0027, USA
123
X. Wang et al.
1 Introduction Computed tomography (CT) is an important imaging modality and has tremendous applications in medical image processing and computer vision, such as analyzing and extracting anatomical structures [1–4]. As one of its applications, automated segmentation of CT images is of great significance in clinical imaging processing. It is essential to the subsequent process and to obtain clinical indices, and is widely used in hip joint disease diagnosis and treatment, such as hip joint osteoporosis, degeneration, fracture, dysplasia, preoperative planning and joint replacement. During the CT acquisition procedure, however, image degradation is inevitable and blurry, and noisy and inhomogeneous intensities may exist. Meanwhile, weak boundaries due to various factors, such as osteoporosis, osteoarthritic degeneration and osteonecrosis, make the automatic CT segmentation a difficult task. The difficulty also lies in complicated bone structures of the acetabular cup and caput femoris. In particular, the long sutural joint often appears between the acetabular cup and caput femoris. Overall, narrow joint segmentation is a challenging problem due to the weakness and narrowness of long boundaries. Various methods, in
Data Loading...
