Stochastic segmentation of severely degraded images using gibbs random fields

Kim, Dongwoo; Lee, Gee–Hyuk; Kim, SooYong

doi:10.1007/bf02931717

Cited by 3 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in (4) denote possible higher order terms. Many models exist for estimating the function V c ðxÞ, such as the Ising model, Potts model, and MLL model [29]. Many approaches have been proposed for finding the MAP estimate of label field X. Geman et al used a Gibbs sampler and simulated annealing (SA) to solve the problem [30].…”

Section: Markov Random Field Modelsmentioning

confidence: 99%

Automated Measurement Method of Common Carotid Artery Intima-Media Thickness in Ultrasound Image Based on Markov Random Field Models

Xiao

Bai

et al. 2015

J. Med. Biol. Eng.

View full text Add to dashboard Cite

Common carotid artery intima-media thickness (IMT) is regarded as one of the most significant indicators for the assessment of cardiovascular diseases. This paper proposes an automated method based on Markov random field models for IMT measurement. The label field is initialized from line segments generated using the Hough transform and the iterated conditional modes method is applied to detect the final boundaries of the lumen-intima interface as well as the media-adventitia interface. A total of 80 ultrasound images from 80 corresponding patients were tested with the proposed method. The ground truth (GT) of the IMT was manually measured a total of four times and then averaged, and the automatically segmented (AS) IMT was computed using the proposed method. The mean of the absolute error ± standard deviation between AS and GT IMT values was 0.0244 ± 0.0227 mm, and the correlation coefficient between the two was 0.9810. Furthermore, the computational time was 1.7 s per image for serial computation with MATLAB on a computer with an Intel Core i5-4200M CPU running 32-bit Windows 7. Experimental results show that the proposed method is both efficient and accurate. The proposed method can be applied for real-time IMT measurement by utilizing parallel computation, which is enable by the use of Markov random field models.

show abstract

Section: Markov Random Field Modelsmentioning

confidence: 99%

Automated Measurement Method of Common Carotid Artery Intima-Media Thickness in Ultrasound Image Based on Markov Random Field Models

Xiao

Bai

et al. 2015

J. Med. Biol. Eng.

View full text Add to dashboard Cite

show abstract

Unsupervised Image Segmentation Using Hierarchical Clustering

Ohkura

Nishizawa

Obi

et al. 2000

OPT REV

View full text Add to dashboard Cite

<title>Algorithm for spatio-temporal heart segmentation</title>

Majcenic

Lončarić

2000

SPIE Proceedings

View full text Add to dashboard Cite

Heart image analysis is a challenging and important process used for a range of purposes such as image based measurement, visualization, etc. The most important step in medical image analysis is segmentation. In this work we present an algorithm for CT heart image segmentation. The segmentation is based on two basic pieces of information, pixels brightness and motion. The motion information is gathered as the optical flow information. Such information is later used for definition of an energy function for image labeling. This energy function represents a Markov random field (MRF) posterior distribution function. The MAP estimation of the segmented image has been determined using the simulated annealing (SA) algorithm.

show abstract

Stochastic segmentation of severely degraded images using gibbs random fields

Cited by 3 publications

References 20 publications

Automated Measurement Method of Common Carotid Artery Intima-Media Thickness in Ultrasound Image Based on Markov Random Field Models

Automated Measurement Method of Common Carotid Artery Intima-Media Thickness in Ultrasound Image Based on Markov Random Field Models

Unsupervised Image Segmentation Using Hierarchical Clustering

<title>Algorithm for spatio-temporal heart segmentation</title>

Contact Info

Product

Resources

About