Advertisement

Comparison of Calcification Cluster Detection by CAD and Human Observers at Different Image Quality Levels

  • Padraig T. Looney
  • Lucy M. Warren
  • Susan M. Astley
  • Kenneth C. Young
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8539)

Abstract

Previous studies have compared the performance of human observers to the performance of human observers using CAD. Here we compare the performance of human observers to Hologic’s ImageChecker CAD system using a set of 162 images with simulated calcification clusters. The quality of the images was reduced to create four other image sets at different image qualities. These were analysed by the CAD system and the relevant information from the resulting DICOM structured reports was parsed. At the highest image quality level the figure of merit for the CAD was 0.82 and 0.84 for the humans. At the lowest image quality level the figure of merit for the CAD and humans were 0.62 and 0.55 respectively. At each image quality level there was no significant difference (p>0.05). The effect of changes in image quality on calcification detection was similar for human observers and the CAD system.

Keywords

CAD JAFROC Image Perception Python 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fenton, J.J., Abraham, L., Taplin, S.H., Geller, B.M., Carney, P.A., D’Orsi, C., Elmore, J.G., Barlow, W.E.: Effectiveness of computer-aided detection in community mammography practice. Journal of the National Cancer Institute 103(15), 1152–1161 (2011)CrossRefGoogle Scholar
  2. 2.
    Warren, L.M., Mackenzie, A., Cooke, J., Given-Wilson, R.M., Wallis, M.G., Chakraborty, D.P., Dance, D.R., Bosmans, H., Young, K.C.: Effect of image quality on calcification detection in digital mammography. Med. Phys. 39, 3202–3213 (2012)CrossRefGoogle Scholar
  3. 3.
    Warren, L.M., Green, F.H., Shrestha, L., Mackenzie, A., Dance, D.R., Young, K.C.: Validation of simulation of calcifications for observer studies in digital mammography. Phys. Med. Biol. 58, N217–N228 (2013)Google Scholar
  4. 4.
    Mason, D.: SU-E-T-33: Pydicom: An Open Source DICOM Library. Medical Physics 38, 3493–3493 (2011)CrossRefGoogle Scholar
  5. 5.
    Hunter, J.D.: Matplotlib: A 2D graphics environment. Computing in Science & Engineering 9, 90–95 (2007)CrossRefGoogle Scholar
  6. 6.
    Chakraborty, D.P.: Analysis of location specific observer performance data: Validated extensions of the jackknife free-response (JAFROC) method. Academic Radiology 13, 1187–1193 (2006)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Padraig T. Looney
    • 1
  • Lucy M. Warren
    • 1
    • 2
  • Susan M. Astley
    • 3
  • Kenneth C. Young
    • 1
    • 2
  1. 1.National Coordinating Centre for the Physics of MammographyRoyal Surrey County Hospital NHS Foundation TrustGuildfordUK
  2. 2.Department of PhysicsUniversity of SurreyGuildfordUK
  3. 3.Centre for Imaging Sciences, Institute of Population Health, Faculty of Medical and Human SciencesManchester Academic Health Science Centre, University of ManchesterManchesterUK

Personalised recommendations