Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

No-Reference image quality metrics for structural MRI

No-Reference image quality metrics for structural MRI Neuroimagery must be visually checked for unacceptable levels of distortion prior to processing. However, inspection is time-consuming, unreliable for detecting subtle distortions and often subjective. With the increasing volume of neuroimagery, objective measures of quality are needed in order to automate screening. To address this need, we have assessed the effectiveness of no-reference image quality measures, which quantify quality inherent to a single image. A data set of 1001 magnetic resonance images (MRIs) recorded from 143 subjects was used for this evaluation. The MRI images were artificially distorted with two levels of either additive Gaussian noise or intensity nouniformity created from a linear model. A total of 239 different quality measures were defined from seven overall families and used to discriminate images for the type and level of distortion. Analysis of Variance identified two families of quality measure that were most effective: one based on Natural Scene Statistics and one originally developed to measure distortion caused by image compression. Measures from both families reliably discriminated among undistorted images, noisy images, and images distorted by intensity nonuniformity. The best quality measures were sensitive only to the distortion category and were not significantly affected by other factors. The results are encouraging enough that several quality measures are being incorporated in a real world MRI test bed. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neuroinformatics Springer Journals

No-Reference image quality metrics for structural MRI

Woodard, Jeffrey; Carley-Spencer, Monica
Neuroinformatics , Volume 4 (3) – Apr 11, 2007
Download PDF
20 pages

Loading next page...
 
/lp/springer-journals/no-reference-image-quality-metrics-for-structural-mri-rHa1kdgmbS
Publisher
Springer Journals
Copyright
Copyright © 2006 by Humana Press Inc.
Subject
Chemistry; Biotechnology; Engineering, general; Neurology
ISSN
1539-2791
eISSN
1559-0089
DOI
10.1385/NI:4:3:243
pmid
16943630
Publisher site
See Article on Publisher Site

Abstract

Neuroimagery must be visually checked for unacceptable levels of distortion prior to processing. However, inspection is time-consuming, unreliable for detecting subtle distortions and often subjective. With the increasing volume of neuroimagery, objective measures of quality are needed in order to automate screening. To address this need, we have assessed the effectiveness of no-reference image quality measures, which quantify quality inherent to a single image. A data set of 1001 magnetic resonance images (MRIs) recorded from 143 subjects was used for this evaluation. The MRI images were artificially distorted with two levels of either additive Gaussian noise or intensity nouniformity created from a linear model. A total of 239 different quality measures were defined from seven overall families and used to discriminate images for the type and level of distortion. Analysis of Variance identified two families of quality measure that were most effective: one based on Natural Scene Statistics and one originally developed to measure distortion caused by image compression. Measures from both families reliably discriminated among undistorted images, noisy images, and images distorted by intensity nonuniformity. The best quality measures were sensitive only to the distortion category and were not significantly affected by other factors. The results are encouraging enough that several quality measures are being incorporated in a real world MRI test bed.

Journal

Neuroinformatics – Springer Journals

Published: Apr 11, 2007

References

  • Statistical evaluation of image quality measures
    Avcibas, A.; Sankur, B.; Seafood, K.
  • Time-frequency distributions—A Review
    Cohen, L.
  • Automatic 3D intersubject registration of MR volumetric data in standardized Talairach space
    Collins, D.; Neelin, P.; Peters, T.; Evans, A.
  • Design and construction of a realistic digital brain phantom
    Collins, D.; Zijdenbos, A.; Kollokian, V.
  • Resolution in time-frequency
    Debrunner, V.; Ozaydm, M.; Prezebinda, T.
  • Image quality measures and their performance
    Eskicioglu, A.; Fisher, P.; Chen, S.
  • Multiresolution histograms and theiruse for recognition
    Hadjidemetriou, E.; Grossberg, M.; Nayar, S.
  • Digital Coding of Waveforms
    Jayant, N.; Noll, P.
  • MRI simulation-based evaluation of image-processing and classification methods
    Kwan, R.; Evans, A.; Pike, G.
  • Fast and accurate image registration using Tsallis entropy and simultaneous perturbation stochastic approximation
    Martin, G.; Morison, W.; Durrani, T.
  • Systems and Transforms with Applications in Optics
    Papoulis, A.
  • The steerable pyramid: A flexible architecture for multi-scale derivative computation
    Simoncelli, E.; Freeman, W.
  • Standing-wave and RF penetration artifacts caused by elliptical geometry: an electrodynamic analysis of MRI
    Sled, J.; Pike, G.
  • A non-parametric method for automatic correction of intensity non-uniformity in MRI data
    Sled, J.; Zijdenbos, A.; Evans, A.
  • On advances in statistical modeling of natural images
    Srivastava, A.; Lee, B.; Simoncelli, E.; Zhu, S.
  • Possible generalization of Boltzmann-Gibbs statistics
    Tsallis, C.
  • Special issue on image and video quality metrics
    Branden Lambrecht, C.
  • Why is image quality assessment so difficult?
    Wang, Z.; Bovik, A.; Lu, L.
  • Advances in Neural Information Processing Systems
    Wang, Z.; Simoncelli, E.
  • Uncertainty and inference in the visual system
    Wilson, R.; Knutsson, H.