Chapter title |
A New Stochastic Framework for Accurate Lung Segmentation
|
---|---|
Chapter number | 39 |
Book title |
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2008
|
Published in |
Lecture notes in computer science, January 2008
|
DOI | 10.1007/978-3-540-85988-8_39 |
Pubmed ID | |
Book ISBNs |
978-3-54-085987-1, 978-3-54-085988-8
|
Authors |
El-Ba, Ayman, Gimel'farb, Georgy, Falk, Robert, Holland, Trevor, Shaffer, Teresa, Gimel’farb, Georgy |
Abstract |
New techniques for more accurate unsupervised segmentation of lung tissues from Low Dose Computed Tomography (LDCT) are proposed. In this paper we describe LDCT images and desired maps of regions (lung and the other chest tissues) by a joint Markov-Gibbs random field model (MGRF) of independent image signals and interdependent region labels but focus on most accurate model identification. To better specify region borders, each empirical distribution of signals is precisely approximated by a Linear Combination of Discrete Gaussians (LCDG) with positive and negative components. We modify a conventional Expectation-Maximization (EM) algorithm to deal with the LCDG and develop a sequential EM-based technique to get an initial LCDG-approximation for the modified EM algorithm. The initial segmentation based on the LCDG-models is then iteratively refined using a MGRF model with analytically estimated potentials. Experiments on real data sets confirm high accuracy of the proposed approach. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Iran, Islamic Republic of | 1 | 3% |
India | 1 | 3% |
Unknown | 35 | 95% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 11 | 30% |
Researcher | 5 | 14% |
Student > Doctoral Student | 3 | 8% |
Student > Master | 3 | 8% |
Student > Bachelor | 2 | 5% |
Other | 4 | 11% |
Unknown | 9 | 24% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 9 | 24% |
Computer Science | 7 | 19% |
Agricultural and Biological Sciences | 3 | 8% |
Medicine and Dentistry | 3 | 8% |
Immunology and Microbiology | 1 | 3% |
Other | 2 | 5% |
Unknown | 12 | 32% |