Detail publikace

3D LUNG SEGMENTATION SEGMENTATION USING MARKOV RANDOM FIELDS

Originální název

3D LUNG SEGMENTATION SEGMENTATION USING MARKOV RANDOM FIELDS

Anglický název

3D LUNG SEGMENTATION SEGMENTATION USING MARKOV RANDOM FIELDS

Jazyk

en

Originální abstrakt

In this paper, Bayesian classification with Markov random fields is used for 3D Computed Tomography (3D CT) lung image segmentation and modified metropolis dynamic is employed as optimization algorithm. Lung tissue is well separated from the other tissues like a bones, muscles, surrounding soft tissue and fat. Segmentation is necessary for subsequent lung analysis (size, shape, lung contour, etc.), and lung blood-vessels, airways (bronchi, bronchioles) segmentation and tumour studies.

Anglický abstrakt

In this paper, Bayesian classification with Markov random fields is used for 3D Computed Tomography (3D CT) lung image segmentation and modified metropolis dynamic is employed as optimization algorithm. Lung tissue is well separated from the other tissues like a bones, muscles, surrounding soft tissue and fat. Segmentation is necessary for subsequent lung analysis (size, shape, lung contour, etc.), and lung blood-vessels, airways (bronchi, bronchioles) segmentation and tumour studies.

BibTex


@inproceedings{BUT107618,
  author="Jiří {Chmelík} and Jiří {Jan}",
  title="3D LUNG SEGMENTATION SEGMENTATION USING MARKOV RANDOM FIELDS",
  annote="In this paper, Bayesian classification with Markov random fields is used for 3D Computed Tomography (3D CT) lung image segmentation and modified metropolis dynamic is employed as optimization algorithm. Lung tissue is well separated from the other tissues like a bones, muscles, surrounding soft tissue and fat. Segmentation is necessary for subsequent lung analysis (size, shape, lung contour, etc.), and lung blood-vessels, airways (bronchi, bronchioles) segmentation and tumour studies.",
  address="LITERA",
  booktitle="Proceedings of the 20th Conference STUDENT EEICT 2014 Volume 3",
  chapter="107618",
  howpublished="print",
  institution="LITERA",
  year="2014",
  month="april",
  pages="217--221",
  publisher="LITERA",
  type="conference paper"
}