Microscopy image enhancement for cost-effective cervical cancer screening
2015 (English)In: Image Analysis, Springer, 2015, 440-451 p.Conference paper (Refereed)
We propose a simple and fast method for microscopy imageenhancement and quantitatively evaluate its performance on a databasecontaining cell images obtained from microscope setups of several levelsof quality. The method utilizes an efficiently and accurately estimated rel-ative modulation transfer function to generate images of higher quality,starting from those of lower quality, by filtering in the Fourier domain.We evaluate the method visually and based on correlation coefficientand normalized mutual information. We conclude that enhanced imagesexhibit high similarity, both visually and in terms of information con-tent, with acquired high quality images. This is an important result forthe development of a cost-effective screening system for cervical cancer.
Place, publisher, year, edition, pages
Springer, 2015. 440-451 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 9127
Medical Image Processing
Research subject Computerized Image Processing
IdentifiersURN: urn:nbn:se:uu:diva-267293DOI: 10.1007/978-3-319-19665-7_37ISBN: 978-3-319-19664-0OAI: oai:DiVA.org:uu-267293DiVA: diva2:872646
SCIA 2015, June 15–17, Copenhagen, Denmark
FunderSwedish Research CouncilVINNOVA