Automatic liver segmentation from CT scans using multi-layer segmentation and principal component analysis

Authors:
Hossein Badakhshannoory;Parvaneh Saeedi
Affiliations:
School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada;School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada
Venue:
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part II
Year:
2010

Citing 5
Cited 0

Active shape models—their training and application

Computer Vision and Image Understanding
Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Eigenfaces for recognition

Journal of Cognitive Neuroscience
A Generic Probabilistic Active Shape Model for Organ Segmentation

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Efficient liver segmentation based on the spine

ADVIS'04 Proceedings of the Third international conference on Advances in Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes an automatic liver segmentation algorithm for extracting liver masks from CT scan volumes. The proposed method consists of two stages. In the first stage, a multi-layer segmentation scheme is utilized to generate 3D liver mask candidate hypotheses. In the second stage, a 3D liver model, based on the Principal Component Analysis, is created to verify and select the candidate hypothesis that best conforms to the overall 3D liver shape model. The proposed algorithm is tested for MICCAI 2007 grand challenge workshop dataset. The proposed method of this paper at this time stands among the top four proposed automatic methods that have been tested on this dataset.