skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Segmentation of subcellular compartments combining superpixel representation with Voronoi diagrams

; ;
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
Report Number(s):
DOE Contract Number:
Resource Type:
Resource Relation:
Conference: International Symposium on Biomedical Imaging, Apr 2014
Country of Publication:
United States
97 MATHEMATICS AND COMPUTING; cervical cell quantification; Voronoi; segmentation

Citation Formats

Ushizima, Daniela M., Bianchi, Andrea G. C., and Carneiro, Claudia M. Segmentation of subcellular compartments combining superpixel representation with Voronoi diagrams. United States: N. p., 2015. Web.
Ushizima, Daniela M., Bianchi, Andrea G. C., & Carneiro, Claudia M. Segmentation of subcellular compartments combining superpixel representation with Voronoi diagrams. United States.
Ushizima, Daniela M., Bianchi, Andrea G. C., and Carneiro, Claudia M. Mon . "Segmentation of subcellular compartments combining superpixel representation with Voronoi diagrams". United States. doi:.
title = {Segmentation of subcellular compartments combining superpixel representation with Voronoi diagrams},
author = {Ushizima, Daniela M. and Bianchi, Andrea G. C. and Carneiro, Claudia M.},
abstractNote = {},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Mon Jan 05 00:00:00 EST 2015},
month = {Mon Jan 05 00:00:00 EST 2015}

Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • This paper describes a method of detecting, tracking and identifying moving objects in video scenes. The method is based on an adaptive change detector which detects and tracks moving objects and extracts silhouettes of the objects from the background so they can be classified by shape. The adaptive change detector uses estimates of image noise and contrast to dynamically adjust decision thresholds. A principal feature of this method is the synergistic interaction between the tracker, the segmenter and the classifier to eliminate uninteresting objects, to improve estimates of the background and noise, to guide threshold selection, and to influence featuremore » selection classification. 9 refs., 4 figs.« less
  • Tattoo segmentation is challenging due to the complexity and large variance in tattoo structures. We have developed a segmentation algorithm for nding tattoos in an image. Our basic idea is split-merge: split each tattoo image into clusters through a bottom-up process, learn to merge the clusters containing skin and then distinguish tattoo from the other skin via top-down prior in the image itself. Tattoo segmentation with unknown number of clusters is transferred to a gure-ground segmentation. We have applied our segmentation algorithm on a tattoo dataset and the results have shown that our tattoo segmentation system is e cient andmore » suitable for further tattoo classi cation and retrieval purpose.« less
  • Presents results of experimental studies in image understanding. Two experiments are discussed, one on image correlation and another on target boundary estimation. The experiments are demonstrative of polar exponential grid (peg) representation, an approach to sensory data coding which the authors believe will facilitate problems in 3-d machine perception. The discussion of the image correlation experiment is largely an exposition of the peg-representation concept and approaches to its computer implementation. A robust stochastic, parallel computation segmentation algorithm, the peg parallel hierarchical ripple filter (peg-phrf), is presented. 18 references.
  • By producing compact representations of hyperspectral image cubes (hypercubes), image storage requirements and the amount of time it takes to extract essential elements of information can both be dramatically reduced. However, these compact representations must preserve the important spectral features within hypercube pixels and the spatial structure associated with background and objects or phenomena of interest. This paper describes a novel approach for automatically and efficiently generating a particular type of compact hypercube representation, referred to as a supercube. The hypercube is segmented into regions that contain pixels with similar spectral shapes that are spatially connected, and the pixel connectivitymore » constraint can be relaxed. Thresholds of similarity in spectral shape between pairs of pixels are derived directly from the hypercube data. One superpixel is generated for each region as some linear combination of pixels belonging to that region. The superpixels are optimal in the sense that the linear combination coefficients are computed so as to minimize the level of noise. Each hypercube pixel is represented in the supercube by applying a gain and bias to the superpixel assigned to the region containing that pixel. Examples are provided.« less
  • Freshly prepared ventricular myocytes from rat hearts, aliquots of which were tested for sarcolemmal integrity by La exposure, were labeled at high 45Ca specific activity. Isotope was subsequently washed out at a perfusion rate of 2.8 ml/s with washout solution sampled each 1 s. No initial unrecorded period of washout was imposed. Four compartments were distinguishable: (1) a rapid compartment (RC) containing 2.6 mmol Ca/kg dry wt of La-displaceable Ca, half time (t1/2) less than 1 s; (2) an intermediate compartment(s) (IC) containing 2.1 mmol, t1/2 = 3 and 19 s; (3) a slow compartment (SC) containing 1.6 mmol, t1/2more » = 3.6 min; (4) an inexchangeable compartment that demonstrated no 45Ca uptake after 60-min labeling containing 1.2 mmol. Introduction of 10 mM caffeine as a probe for sarcoplasmic reticulum (SR) content at various times during the washouts caused an increased release of 45Ca. The net increased 45Ca release plotted as a function of time at which caffeine was introduced produced a biexponential curve with t1/2s of 2 and 22 s, very similar to the t1/2s of the IC. Ryanodine (1 microM) significantly reduced the caffeine-induced 45Ca release, confirming the SR locus of the IC. Cells were perfused with 10 mM NaH2PO4 to specifically increase mitochondrial 45Ca labeling. Subsequent removal of PO4 at various times during washouts produced large increases in effluent 45Ca. A plot of the net peak release of 45Ca vs. time of PO4 removal was monoexponential with t1/2 = 3.3 min, very similar to the SC t1/2. The large La-accessible RC remains unlocalized, but the rapidity of its exchange places it in the sarcolemma and/or at sites in rapid equilibrium with the sarcolemma.« less