Quantitative segmentation of fluorescence microscopy images of heterogeneous tissue: Approach for tuning algorithm parameters

Jenna L. Mueller, Zachary T. Harmany, Jeffrey K. Mito, Stephanie A. Kennedy, Yongbaek Kim, Leslie G. Dodd, Joseph Geradts, David G. Kirsch, Rebecca Willett, J. Quincy Brown, Nirmala RamanujamProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2013 · DOI

Abstract

The combination of fluorescent contrast agents with microscopy is a powerful technique to obtain real time images of tissue histology without the need for fixing, sectioning, and staining. The potential of this technology lies in the identification of robust methods for image segmentation and quantitation, particularly in heterogeneous tissues. Our solution is to apply sparse decomposition (SD) to monochrome images of fluorescently-stained microanatomy to segment and quantify distinct tissue types. The clinical utility of our approach is demonstrated by imaging excised margins in a cohort of mice after surgical resection of a sarcoma. Representative images of excised margins were used to optimize the formulation of SD and tune parameters associated with the algorithm. Our results demonstrate that SD is a robust solution that can advance vital fluorescence microscopy as a clinically significant technology.
BibTeX
@inproceedings{mueller2013quantitative,
  author = {Jenna L. Mueller and Zachary T. Harmany and Jeffrey K. Mito and Stephanie A. Kennedy and Yongbaek Kim and Leslie G. Dodd and Joseph Geradts and David G. Kirsch and Rebecca Willett and J. Quincy Brown and Nirmala Ramanujam},
  title = {{Quantitative segmentation of fluorescence microscopy images of heterogeneous tissue: Approach for tuning algorithm parameters}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2013},
  doi = {10.1117/12.2006429},
}

Loading related content...

Figure