Display options
Cite
Widmer C, Heinrich S, Drewe P, et al. Graph-regularized 3D shape reconstruction from highly anisotropic and noisy images. Signal Image Video Process. 2014;8(1):41-48doi: 10.1007/s11760-014-0694-8.
Widmer, C., Heinrich, S., Drewe, P., Lou, X., Umrania, S., & Rätsch, G. (2014). Graph-regularized 3D shape reconstruction from highly anisotropic and noisy images. Signal, image and video processing, 8(1), 41-48. https://doi.org/10.1007/s11760-014-0694-8
Widmer, Christian, et al. "Graph-regularized 3D shape reconstruction from highly anisotropic and noisy images." Signal, image and video processing vol. 8,1 (2014): 41-48. doi: https://doi.org/10.1007/s11760-014-0694-8
Widmer C, Heinrich S, Drewe P, Lou X, Umrania S, Rätsch G. Graph-regularized 3D shape reconstruction from highly anisotropic and noisy images. Signal Image Video Process. 2014 Dec 01;8(1):41-48. doi: 10.1007/s11760-014-0694-8. PMID: 25866587; PMCID: PMC4389647.
Copy Download .nbib Format: NLM
Share it on

Signal Image Video Process. 2014 Dec 01;8(1):41-48. doi: 10.1007/s11760-014-0694-8.

Graph-regularized 3D shape reconstruction from highly anisotropic and noisy images.

Signal, image and video processing

Christian Widmer, Stephanie Heinrich, Philipp Drewe, Xinghua Lou, Shefali Umrania, Gunnar Rätsch

Affiliations

  1. Sloan Kettering Institute, 1275 York avenue, New York, NY, USA.
  2. Institute for Biochemistry, ETH Zurich, Otto-Stern-Weg 3, Zurich, Switzerland.

PMID: 25866587 PMCID: PMC4389647 DOI: 10.1007/s11760-014-0694-8

Abstract

Analysis of microscopy images can provide insight into many biological processes. One particularly challenging problem is cellular nuclear segmentation in highly anisotropic and noisy 3D image data. Manually localizing and segmenting each and every cellular nucleus is very time-consuming, which remains a bottleneck in large-scale biological experiments. In this work, we present a tool for automated segmentation of cellular nuclei from 3D fluorescent microscopic data. Our tool is based on state-of-the-art image processing and machine learning techniques and provides a user-friendly graphical user interface. We show that our tool is as accurate as manual annotation and greatly reduces the time for the registration.

Keywords: 3D fluorescent microscopic data; Cell nuclei detection; Nuclear segmentation; Shape reconstruction

References

  1. IEEE Trans Med Imaging. 2010 Dec;29(12):1959-78 - PubMed
  2. IEEE Trans Biomed Eng. 2010 Apr;57(4):841-52 - PubMed
  3. Proc IEEE Int Symp Biomed Imaging. 2009;5193098:518-521 - PubMed
  4. PLoS One. 2014 Feb 27;9(2):e90036 - PubMed
  5. Cytometry A. 2009 Jun;75(6):494-509 - PubMed
  6. BMC Cell Biol. 2007 Sep 04;8:40 - PubMed
  7. Nat Cell Biol. 2013 Nov;15(11):1328-39 - PubMed
  8. Sci Rep. 2012;2:503 - PubMed
  9. IEEE Trans Image Process. 2005 Sep;14(9):1396-410 - PubMed
  10. BMC Bioinformatics. 2010 Nov 29;11:580 - PubMed
  11. Stem Cell Reports. 2014 Mar 11;2(3):382-97 - PubMed
  12. Proc Natl Acad Sci U S A. 1984 Aug;81(16):5126-9 - PubMed
  13. IEEE Trans Image Process. 2009 Aug;18(8):1817-29 - PubMed

Publication Types

Grant support