Most edges in Markov random fields for white matter hyperintensity segmentation are worthless.

Christopher G. Schwarz, Evan Fletcher, Baljeet Singh, Amy Liu, Noel Smith, Charles DeCarli, Owen Carmichael

Research output: Contribution to journalArticle

Abstract

The time and space complexities of Markov random field (MRF) algorithms for image segmentation increase with the number of edges that represent statistical dependencies between adjacent pixels. This has made MRFs too computationally complex for cutting-edge applications such as joint segmentation of longitudinal sequences of many high-resolution magnetic resonance images (MRIs). Here, we show that simply removing edges from full MRFs can reduce the computational complexity of MRF parameter estimation and inference with no notable decrease in segmentation performance. In particular, we show that for segmentation of white matter hyperintensities in 88 brain MRI scans of elderly individuals, as many as 66% of MRF edges can be removed without substantially degrading segmentation accuracy. We then show that removing edges from MRFs makes MRF parameter estimation and inference computationally tractable enough to enable modeling statistical dependencies within and across a larger number of brain MRI scans in a longitudinal series; this improves segmentation performance compared to separate segmentations of each individual scan in the series.

Fingerprint

Magnetic resonance
Magnetic Resonance Spectroscopy
Parameter estimation
Brain
Image segmentation
Computational complexity
Joints
Pixels
White Matter

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

@article{cbf44b2cd96d43f99a3db31c3679bfb3,
title = "Most edges in Markov random fields for white matter hyperintensity segmentation are worthless.",
abstract = "The time and space complexities of Markov random field (MRF) algorithms for image segmentation increase with the number of edges that represent statistical dependencies between adjacent pixels. This has made MRFs too computationally complex for cutting-edge applications such as joint segmentation of longitudinal sequences of many high-resolution magnetic resonance images (MRIs). Here, we show that simply removing edges from full MRFs can reduce the computational complexity of MRF parameter estimation and inference with no notable decrease in segmentation performance. In particular, we show that for segmentation of white matter hyperintensities in 88 brain MRI scans of elderly individuals, as many as 66{\%} of MRF edges can be removed without substantially degrading segmentation accuracy. We then show that removing edges from MRFs makes MRF parameter estimation and inference computationally tractable enough to enable modeling statistical dependencies within and across a larger number of brain MRI scans in a longitudinal series; this improves segmentation performance compared to separate segmentations of each individual scan in the series.",
author = "Schwarz, {Christopher G.} and Evan Fletcher and Baljeet Singh and Amy Liu and Noel Smith and Charles DeCarli and Owen Carmichael",
year = "2012",
language = "English (US)",
volume = "2012",
pages = "2684--2687",
journal = "Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference",
issn = "1557-170X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Most edges in Markov random fields for white matter hyperintensity segmentation are worthless.

AU - Schwarz, Christopher G.

AU - Fletcher, Evan

AU - Singh, Baljeet

AU - Liu, Amy

AU - Smith, Noel

AU - DeCarli, Charles

AU - Carmichael, Owen

PY - 2012

Y1 - 2012

N2 - The time and space complexities of Markov random field (MRF) algorithms for image segmentation increase with the number of edges that represent statistical dependencies between adjacent pixels. This has made MRFs too computationally complex for cutting-edge applications such as joint segmentation of longitudinal sequences of many high-resolution magnetic resonance images (MRIs). Here, we show that simply removing edges from full MRFs can reduce the computational complexity of MRF parameter estimation and inference with no notable decrease in segmentation performance. In particular, we show that for segmentation of white matter hyperintensities in 88 brain MRI scans of elderly individuals, as many as 66% of MRF edges can be removed without substantially degrading segmentation accuracy. We then show that removing edges from MRFs makes MRF parameter estimation and inference computationally tractable enough to enable modeling statistical dependencies within and across a larger number of brain MRI scans in a longitudinal series; this improves segmentation performance compared to separate segmentations of each individual scan in the series.

AB - The time and space complexities of Markov random field (MRF) algorithms for image segmentation increase with the number of edges that represent statistical dependencies between adjacent pixels. This has made MRFs too computationally complex for cutting-edge applications such as joint segmentation of longitudinal sequences of many high-resolution magnetic resonance images (MRIs). Here, we show that simply removing edges from full MRFs can reduce the computational complexity of MRF parameter estimation and inference with no notable decrease in segmentation performance. In particular, we show that for segmentation of white matter hyperintensities in 88 brain MRI scans of elderly individuals, as many as 66% of MRF edges can be removed without substantially degrading segmentation accuracy. We then show that removing edges from MRFs makes MRF parameter estimation and inference computationally tractable enough to enable modeling statistical dependencies within and across a larger number of brain MRI scans in a longitudinal series; this improves segmentation performance compared to separate segmentations of each individual scan in the series.

UR - http://www.scopus.com/inward/record.url?scp=84883007920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883007920&partnerID=8YFLogxK

M3 - Article

C2 - 23366478

AN - SCOPUS:84883007920

VL - 2012

SP - 2684

EP - 2687

JO - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

JF - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

SN - 1557-170X

ER -