Book chapter
Multiple Surface Segmentation Using Truncated Convex Priors
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp.97-104
Lecture Notes in Computer Science, Springer International Publishing
11/18/2015
DOI: 10.1007/978-3-319-24574-4_12
Abstract
Multiple surface segmentation with mutual interaction between surface pairs is a challenging task in medical image analysis. In this paper we report a fast multiple surface segmentation approach with truncated convex priors for a segmentation problem, in which there exist abrupt surface distance changes between mutually interacting surface pairs. A 3-D graph theoretic framework based on local range search is employed. The use of truncated convex priors enables to capture the surface discontinuity and rapid changes of surface distances. The method is also capable to enforce a minimum distance between a surface pair. The solution for multiple surfaces is obtained by iteratively computing a maximum flow for a subset of the voxel domain at each iteration. The proposed method was evaluated on simultaneous intraretinal layer segmentation of optical coherence tomography images of normal eye and eyes affected by severe drusen due to age related macular degeneration. Our experiments demonstrated statistically significant improvement of segmentation accuracy by using our method compared to the optimal surface detection method using convex priors without truncation (OSDC). The mean unsigned surface positioning errors obtained by OSDC for normal eyes (4.47 ±1.10)μm was improved to (4.29 ±1.02)μm, and for eyes with drusen was improved from (7.98 ±4.02)μm to (5.12 ±1.39)μm using our method. The proposed approach with average computation time of 539 sec is much faster than 10014 sec taken by OSDC.
Details
- Title: Subtitle
- Multiple Surface Segmentation Using Truncated Convex Priors
- Creators
- Abhay Shah - University of IowaJunjie Bai - University of IowaZhihong Hu - Doheny Eye InstituteSrinivas Sadda - University of IowaXiaodong Wu - University of Iowa
- Resource Type
- Book chapter
- Publication Details
- Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp.97-104
- Publisher
- Springer International Publishing; Cham
- Series
- Lecture Notes in Computer Science
- DOI
- 10.1007/978-3-319-24574-4_12
- eISSN
- 1611-3349
- ISSN
- 0302-9743
- Language
- English
- Date published
- 11/18/2015
- Academic Unit
- Electrical and Computer Engineering; Radiation Oncology; The Iowa Institute for Biomedical Imaging
- Record Identifier
- 9984197450802771
Metrics
14 Record Views