vPSNR: a visualization-aware image fidelity metric tailored for diagnostic imaging
2013 (English)In: International Journal of Computer Assisted Radiology and Surgery, ISSN 1861-6410, Vol. 8, no 3, 437-450 p.Article in journal (Refereed) Published
Purpose Often, the large amounts of data generated in diagnosticimaging cause overload problems for IT systems andradiologists. This entails a need of effective use of data reductionbeyond lossless levels, which, in turn, underlines theneed to measure and control the image fidelity. Existingimage fidelity metrics, however, fail to fully support importantrequirements from a modern clinical context: supportfor high-dimensional data, visualization awareness, and independencefrom the original data.Methods We propose an image fidelity metric, called thevisual peak signal-to-noise ratio (vPSNR), fulfilling the threemain requirements. A series of image fidelity tests on CTdata sets is employed. The impact of visualization transform(grayscalewindow) on diagnostic quality of irreversiblycompressed data sets is evaluated through an observer-basedstudy. In addition, several tests were performed demonstratingthe benefits, limitations, and characteristics of vPSNR indifferent data reduction scenarios.Results The visualization transform has a significant impacton diagnostic quality, and the vPSNR is capable of representingthis effect. Moreover, the tests establish that the vPSNRis broadly applicable.Conclusions vPSNR fills a gap not served by existingimage fidelity metrics, relevant for the clinical context. WhilevPSNR alone cannot fulfill all image fidelity needs, it can bea useful complement in a wide range of scenarios.
Place, publisher, year, edition, pages
Springer, 2013. Vol. 8, no 3, 437-450 p.
Image fidelity, Image quality, Metric, Diagnostic imaging, vPSNR, Data reduction, Image compression, Visualization, Perception
Medical Image Processing
IdentifiersURN: urn:nbn:se:liu:diva-91460DOI: 10.1007/s11548-012-0792-4ISI: 000318867000010OAI: oai:DiVA.org:liu-91460DiVA: diva2:617997
FunderSwedish Foundation for Strategic Research , SM10-0022