Automatic liver segmentation is a crucial step for aiding in liver surgery and in diagnosing liver pathologies. Its goal is to find the following anatomical structures: the liver vessels and segments, and the present lesions and tumors. Herein, we describe a liver segmentation algorithm based on the gray-level histogram of volumetric and dynamic contrast enhanced computer tomography images. We give a comparison of two optimization methods used to fit a Gaussian mixture model to the histogram: the trust-region and the expectation-maximization algorithm. We show that the trust-region algorithm behaves more robustly and gives promising segmentation results. The expectation-maximization algorithm requires very good model estimation and elimination of the histogram data outside the 3 range of the outermost Gaussians. Moreover, in some cases the expectation-maximization algorithm converges to a smoother, but less accurate solution.
Markova, A, Deklerck, R, Nyssen, E & De Mey, J 2006, Comparison of the trust-region and the expectation-maximization algorithm for the application of automatic liver segmentation. in Belgian Day on Biomedical Engineering, IEEE/EMBS Benelux Symposium. pp. 195-198, Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet, Stockholm, Sweden, 21/09/09.
Markova, A., Deklerck, R., Nyssen, E., & De Mey, J. (2006). Comparison of the trust-region and the expectation-maximization algorithm for the application of automatic liver segmentation. In Belgian Day on Biomedical Engineering, IEEE/EMBS Benelux Symposium (pp. 195-198)
@inproceedings{bb7a006287ea41339ab82241cd78ff37,
title = "Comparison of the trust-region and the expectation-maximization algorithm for the application of automatic liver segmentation",
abstract = "Automatic liver segmentation is a crucial step for aiding in liver surgery and in diagnosing liver pathologies. Its goal is to find the following anatomical structures: the liver vessels and segments, and the present lesions and tumors. Herein, we describe a liver segmentation algorithm based on the gray-level histogram of volumetric and dynamic contrast enhanced computer tomography images. We give a comparison of two optimization methods used to fit a Gaussian mixture model to the histogram: the trust-region and the expectation-maximization algorithm. We show that the trust-region algorithm behaves more robustly and gives promising segmentation results. The expectation-maximization algorithm requires very good model estimation and elimination of the histogram data outside the 3 range of the outermost Gaussians. Moreover, in some cases the expectation-maximization algorithm converges to a smoother, but less accurate solution.",
keywords = "liver segmentation, gaussian mixture model, trust-region method, expectation-maximization algorithm",
author = "Aneta Markova and Rudi Deklerck and Edgard Nyssen and {De Mey}, Johan",
year = "2006",
month = dec,
day = "7",
language = "English",
pages = "195--198",
booktitle = "Belgian Day on Biomedical Engineering, IEEE/EMBS Benelux Symposium",
note = "Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet ; Conference date: 21-09-2009 Through 25-09-2009",
}