Published February 26, 2020 | Version v1.0.0
Software Open

Objective and repeatable image quality assessment with Gaussian mixture models

Creators

  • 1. University of Southampton

Description

Quantifying image quality enables objective optimisation of imaging protocols. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) measure visibility of features in relation to the image noise. Conventional SNR and CNR measurement is performed by user selection of regions in the image representing each material, which is not repeatable and impractical for large numbers of 3D datasets. Here, a semi-automated, objective and repeatable method of calculating SNR and CNR is presented which does not require user definition of regions-of-interest. This method utilises Gaussian mixture models to separate materials in the specimen based on the grey value distribution of the image. This tool is available as a graphical user interface for Fiji/ImageJ users, and as importable libraries for Python users under the GNU General Public License v3.0.

Notes

This study was supported by the Engineering and Physical Sciences Research Council (EPSRC), UK and the Institute for Life Sciences, University of Southampton, UK.

Files

elainehoml/GMM_Image_Quality-v1.0.0.zip

Files (138.8 MB)

Name Size Download all
md5:8871848d3a8a90c5c290a7a42250ed9c
138.8 MB Preview Download

Additional details

Related works

Is supplement to
https://github.com/elainehoml/GMM_Image_Quality/tree/v1.0.0 (URL)

References

  • M. Reiter et al., 'Evaluation of a histogram-based image quality measure for X-ray computed tomography', presented at the Proc. 5th conference on industrial computed tomography (iCT), Wels, Austria, 2014.
  • F. Timischl, 'The contrast-to-noise ratio for image quality evaluation in scanning electron microscopy', Scanning, vol. 37, no. 1, pp. 54–62, 2015, doi: 10.1002/sca.21179.
  • J. D. Hunter, 'Matplotlib: A 2D Graphics Environment', Computing in Science Engineering, vol. 9, no. 3, pp. 90–95, May 2007, doi: 10.1109/MCSE.2007.55.
  • S. van der Walt et al., 'scikit-image: image processing in Python', PeerJ, vol. 2, p. e453, Jun. 2014, doi: 10.7717/peerj.453.
  • Michael Waskom et al., mwaskom/seaborn: v0.9.0 (July 2018). Zenodo, 2018.
  • P. Virtanen et al., 'SciPy 1.0: fundamental algorithms for scientific computing in Python', Nature Methods, pp. 1–12, Feb. 2020, doi: 10.1038/s41592-019-0686-2.
  • F. Pedregosa et al., 'Scikit-learn: Machine Learning in Python', Journal of Machine Learning Research, vol. 12, p. 2825−2830, Oct. 2011.
  • J. Schindelin et al., 'Fiji: an open-source platform for biological-image analysis', Nature Methods, vol. 9, no. 7, pp. 676–682, Jul. 2012, doi: 10.1038/nmeth.2019.