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

doi:10.1109/ISBI.2014.6867916

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 proceeding › Conference 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 language	English
Title of host publication	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Subtitle of host publication	Proceedings
Publisher	IEEE
Pages	493-496
Number of pages	4
ISBN (Print)	9781467319591
DOIs	https://doi.org/10.1109/ISBI.2014.6867916
Publication status	Published - 2014
Event	2014 IEEE International Symposium on Biomedical Imaging - Renaissance Beijing Capital Hotel, Beijing, China Duration: 29 Apr 2014 → 2 May 2014 http://biomedicalimaging.org/2014/

Conference

Conference	2014 IEEE International Symposium on Biomedical Imaging
Abbreviated title	ISBI 2014
Country/Territory	China
City	Beijing
Period	29/04/14 → 2/05/14
Internet address	http://biomedicalimaging.org/2014/

Keywords

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

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2014.6867916

http://www.proceedings.com/23135.html

Cite this

@inproceedings{92e784d20cfb4358bb38ce011f9cefe4,

title = "Multi-scale non-local means with shape prior for enhancement of cell membrane images",

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.",

keywords = "Cell membrane, Image enhancement, Multi-scale representation, Non-local means, Shape prior",

author = "Cheng-Jin Du and Richard Tyson and Emil Rozbicki and Weijer, {Cornelis J.} and Till Bretschneider",

year = "2014",

doi = "10.1109/ISBI.2014.6867916",

language = "English",

isbn = "9781467319591",

pages = "493--496",

booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",

publisher = "IEEE",

note = "2014 IEEE International Symposium on Biomedical Imaging, ISBI 2014 ; Conference date: 29-04-2014 Through 02-05-2014",

url = "http://biomedicalimaging.org/2014/",

}

Du, C-J, Tyson, R, Rozbicki, E, Weijer, CJ & Bretschneider, T 2014, Multi-scale non-local means with shape prior for enhancement of cell membrane images. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014: Proceedings. IEEE, pp. 493-496, 2014 IEEE International Symposium on Biomedical Imaging, Beijing, China, 29/04/14. https://doi.org/10.1109/ISBI.2014.6867916

TY - GEN

T1 - Multi-scale non-local means with shape prior for enhancement of cell membrane images

AU - Du, Cheng-Jin

AU - Tyson, Richard

AU - Rozbicki, Emil

AU - Weijer, Cornelis J.

AU - Bretschneider, Till

PY - 2014

Y1 - 2014

N2 - 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.

AB - 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.

KW - Cell membrane

KW - Image enhancement

KW - Multi-scale representation

KW - Non-local means

KW - Shape prior

UR - http://www.scopus.com/inward/record.url?scp=84927950259&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2014.6867916

DO - 10.1109/ISBI.2014.6867916

M3 - Conference contribution

AN - SCOPUS:84927950259

SN - 9781467319591

SP - 493

EP - 496

BT - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

PB - IEEE

T2 - 2014 IEEE International Symposium on Biomedical Imaging

Y2 - 29 April 2014 through 2 May 2014

ER -

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

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this