Multi-scale non-local means with shape prior for enhancement of cell membrane images

Cheng-Jin Du, Richard Tyson, Emil Rozbicki, Cornelis J. Weijer, Till Bretschneider

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Light sheet microscopy allows rapid optical sectioning of whole chicken embryos during early development, visualizing cells through transgenic expression of a fluorescent cell membrane label. Low signal-to-noise ratios and large variability in intensity make segmentation of these images difficult, often resulting in discontinuous cell edges. We propose a multi-scale non-local means with shape prior (MS-NLM-SP) method for image enhancement, which takes into account cell-specific characteristics, such as size, geometry, and periodicity. Investigating theoretical connections between our approach and anisotropic diffusion reveals that the first step, detail-enhanced multi-scale representation, corresponds to selective backward diffusion, while the second step of MS-NLM-SP resembles anisotropic forward diffusion. Experimental results show that incorporating cell-specific features into non-local image denoising methods improves subsequent segmentation.

    Original languageEnglish
    Title of host publication2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
    Subtitle of host publicationProceedings
    PublisherIEEE
    Pages493-496
    Number of pages4
    ISBN (Print)9781467319591
    DOIs
    Publication statusPublished - 2014
    Event2014 IEEE International Symposium on Biomedical Imaging - Renaissance Beijing Capital Hotel, Beijing, China
    Duration: 29 Apr 20142 May 2014
    http://biomedicalimaging.org/2014/

    Conference

    Conference2014 IEEE International Symposium on Biomedical Imaging
    Abbreviated titleISBI 2014
    CountryChina
    CityBeijing
    Period29/04/142/05/14
    Internet address

    Keywords

    • Cell membrane
    • Image enhancement
    • Multi-scale representation
    • Non-local means
    • Shape prior

    Fingerprint Dive into the research topics of 'Multi-scale non-local means with shape prior for enhancement of cell membrane images'. Together they form a unique fingerprint.

    Cite this