Journal Metrics
Impact Factor: 1.211
ISSN Print: 1609-0985
ISSN Online: 2199-4757
Imprint: Springer
Journal Content Search
latest updated: 2015 / 07 / 30
Graph-Cut-Based Segmentation of Proximal Femur from Computed Tomography Images with Shape Prior
Junbin Huang, 
James F. Griffith, 
Defeng Wang, 
Lin Shi
Abstract
Femur segmentation from computed tomography (CT) images is a fundamental problem in femur-related computer-assisted diagnosis and surgical planning/navigation. In this study, an automatic approach for the segmentation of proximal femur from CT images that incorporates the statistical shape prior into the graph-cut framework (SP-GC) is proposed. The proposed segmentation framework includes two major processes, namely training and segmentation. In the training stage, a training set of three-dimensional CT images from a group of normal subjects were segmented semi-automatically. The shape prior was generated by active shape modeling that included mean shape and shape variance information. In the segmentation stage, two shape terms originated from the training stage were included in the GC energy function. The minimization of the energy function was achieved using a max-flow/min-cut algorithm. The performance of the proposed segmentation method was evaluated by testing on 60 CT datasets from bilateral femurs of 30 normal subjects. Qualitative and quantitative analyses of the segmentation results of the proposed method were performed and the results were compared with two widely used methods, namely the active shape model (ASM) and traditional GC, with results from manual delineation used as the ground truth. The mean dice similarity coefficient of the proposed SP-GC was 0.9600, which is higher than those of ASM and GC (0.8769 and 0.9358, respectively). The mean normalized error rate of the SP-GC results was 10 and 6 % lower than those of ASM and GC, respectively. In terms of the average surface distance measurement, the value for SP-GC was 0.885 mm, compared with 2.148 and 1.154 mm for ASM and GC, respectively. In comparison with ASM, SP-GC has superior performance given a small training set (e.g., n = 12). With increasing number of training samples, the segmentation accuracy of ASM saturated, but that of SP-GC slightly increased.
Home | Editorial Board | Archives | Special Issue | News | Contact | About JMBE | 08170748
National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Taipei 10617, Taiwan (R.O.C.)
phone: (+886)-2-3366-1868     fax: (+886)-2-33551687     E-mail:jmbeoffice@gmail.com
Copyright ◎ 2015 Journal All rights reserved