Book chapter
Fully Automatic Segmentation of Hip CT Images via Random Forest Regression-Based Atlas Selection and Optimal Graph Search-Based Surface Detection
Computer Vision -- ACCV 2014, pp.640-654
Lecture Notes in Computer Science, 9005, Springer International Publishing
04/16/2015
DOI: 10.1007/978-3-319-16811-1_42
Abstract
Automatic extraction of surface models of both pelvis and proximal femur of a hip joint from 3D CT images is an important and challenging task for computer assisted diagnosis and planning of periacetabular osteotomy (PAO). Due to the narrowness of hip joint space, the adjacent surfaces of the acetabulum and the femoral head are hardly distinguishable from each other in the target CT images. This paper presents a fully automatic method for segmenting hip CT images using random forest (RF) regression-based atlas selection and optimal graph search-based surface detection. The two fundamental contributions of our method are: (1) An efficient RF regression framework is developed for a fast and accurate landmark detection from the hip CT images. The detected landmarks allow for not only a robust and accurate initialization of the atlases within the target image space but also an effective selection of a subset of atlases for a fast atlas-based segmentation; and (2) 3-D graph theory-based optimal surface detection is used to refine the extraction of the surfaces of the acetabulum and the femoral head with the ultimate goal to preserve hip joint structure and to avoid penetration between the two extracted surfaces. Validation on 30 hip CT images shows that our method achieves high performance in segmenting pelvis, left proximal femur, and right proximal femur with an average accuracy of 0.56 mm, 0.61 mm, and 0.57 mm, respectively.
Details
- Title: Subtitle
- Fully Automatic Segmentation of Hip CT Images via Random Forest Regression-Based Atlas Selection and Optimal Graph Search-Based Surface Detection
- Creators
- Chengwen Chu - University of Pittsburgh Medical CenterJunjie Bai - Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, USALi Liu - Institute for Surgical Technology and Biomechanics, University of Bern, Bern, SwitzerlandXiaodong Wu - University of Iowa, Electrical and Computer EngineeringGuoyan Zheng - University of Bern
- Resource Type
- Book chapter
- Publication Details
- Computer Vision -- ACCV 2014, pp.640-654
- Publisher
- Springer International Publishing; Cham
- Series
- Lecture Notes in Computer Science; 9005
- DOI
- 10.1007/978-3-319-16811-1_42
- eISSN
- 1611-3349
- ISSN
- 0302-9743
- Language
- English
- Date published
- 04/16/2015
- Academic Unit
- The Iowa Institute for Biomedical Imaging; Electrical and Computer Engineering; Radiation Oncology
- Record Identifier
- 9984197068102771
Metrics
65 Record Views