Shape Analysis for Microscopy - TCD

Shape Analysis for Microscopy - TCD

Shape Analysis for Microscopy Kangyu Pan in collaboration with: Jens Hillebrand, Mani Ramaswami Institute for Neuroscience Trinity College Dublin & Michael J. Higgins

Intelligent Polymer Research Institute University of Wollongong, Australia Memory Formation Jens Hillebrand, Mani Ramaswami Institute for Neuroscience Trinity College Dublin Neuron cells

Stimulated synapses Protein synthesis Roles of the specific proteins Shape of the synapses Roles of the specific proteins ? Co-localization of the different proteins

Gaussian Mixture Model KEY: fitting a GMM to the surface of an object Optimization Parameters of the Gaussian mixture components Number of the components Optimized by Split & Merge Expectation Maximization algorithm (SMEM)

Merge Split directions distance ? ?

Split Algorithm Firstly, similar to Zhangs split technique [1] relied on multiple random splits at each iteration [1] Z. Zhang, C. Chen, J. Sun, and K. L. Chan, EM algorithms for Gaussian mixtures with splitand-merge operation, Pattern Recognition, vol. 36, no. 9, pp. 19731983, 2003. Split operation Section(4.2.2) EM operation

Publication: K. Pan, A. Kokaram, J. Hillebrand, and M. Ramaswami, Gaussian mixtures for intensity modelling of spots in microscopy, IEEE International Symposium on Biomedical Imaging (ISBI), 2010. Lately, we developed an error-based SMEM (eSMEM) which is deterministic, repeatable, more efficient. Error distribution A collection of the error that belongs to each mixture component at each pixel site

Estimation error From the E-step of EM E ( x n ) | I EM ( x n ) I norm ( x n ) | Error distribution E m ( xn ) wm ( xn ) E ( xn ) New

Error-based Split algorithm Contour view i Split directions distance

j ? ? x min 2 x min 1 j

i x max X min Results I norm (x )

I EM (x ) Publication: K. Pan, J. Hillebrand, M. Ramaswami, and A. Kokaram, Gaussian mixture models for spots in microscopy using a new split/merge EM algorithm, IEEE International Conference on Image Processing (ICIP'10) , 3645-3648 (2010). GUI for the biologists Co-localization Analysis

Shape of synapses ? Publication: K. Pan, D. Corrigan, J. Hillebrand, M. Ramaswami, and A. Kokaram, A Wavelet-Based Bayesian Framework for 3D Object Segmentation in Microscopy, SPIE BiOS Symposium. Regeneration of muscle tissue Michael J. Higgins Intelligent Polymer Research Institute University of Wollongong, Australia

Research on a novel technique that uses electrical stimulation to control the growth of muscle cells through conductive polymer materials. To assess the performance of various processes, we must measure muscle cell density quantitatively. Which requires the classification of: Cell (with only one nucleus)

& Fibres (with multiple nuclei inside cell body) Skeletal muscle cells & fibres The number of nuclei in each cell/fibre Segmentation of the cell/fibre (especially the overlapped cells and fibres)

Cell body (segmentation of the overlapped cell bodies) Skeletal cells & fibres Nuclei (Using GMM and optimized with eSMEM) Cellsnake :

A NEW ACTIVE CONTOUR TECHNIQUE FOR CELL/FIBRE SEGMENTATION Publication: K. Pan, A. Kokaram , K. Gilmore , M. J. Higgins , R. Kapsa and G. G. Wallace, Cellsnake: A new active contour technique for cell/fibre segmentation, IEEE International Conference on Image Processing (ICIP'11) , 36453648 (2011). Future work Organize the algorithms as plug-in tools for the software that the biologists used (like IGOR Pro). Run more experiments to further examine the performance of the

techniques and submit the dissertation in April.

Recently Viewed Presentations

  • Presentación de PowerPoint

    Presentación de PowerPoint

    , acaso por el choque de un electrón libre que se acerca a ellos a gran velocidad. Entonces prepondera la . carga positiva. existente en el núcleo; el átomo se ha convertido en un . ión positivo. A la inversa,...
  • A RESOURCE FOR TEACHING G N I D

    A RESOURCE FOR TEACHING G N I D

    Understand how to use digraphs, long vowels, blends and silent letters to spell words, and use morphemes and syllabification to break up simple words and use visual memory to write irregular words . ACELA1471 Recognise common prefixes and suffixes and...
  • 6.6 Aldehydes and Ketones - ThinkChemistry

    6.6 Aldehydes and Ketones - ThinkChemistry

    From the results, compound X is an and compound Y is an . 6.6 Aldehydes and Ketones 6.6.1 Aldehyde Structures An alkanal (aldehyde) has a group at the end of the carbon chain. Alkanals have the the functional group: 6.6.2...
  • Key audience theories

    Key audience theories

    The active audience theory suggests that the audience interacts with media text to create meaning, which is in comparison with the passive theory. Two-step flow model. This model was first introduced by Paul Lazarsfeld, Bernard Berelson and Hazel Gaudet and...
  • NHS WEST KENT CCG - GP Patient

    NHS WEST KENT CCG - GP Patient

    Author: Sylvie.Hobden Created Date: 04/19/2012 04:10:37 Title: Slide 1 Keywords: PowerPoint potx Template Ipsos MORI Last modified by: svc_MRDD Company
  • Domain 3  Security Engineering  Objectives  Security Engineering  Architecture

    Domain 3 Security Engineering Objectives Security Engineering Architecture

    Zachman Framework. Section breaker slide with customer logo. Section heading - Arial Headings, 34, Bold. Sub head - Arial Headings, 18, normal. Used for a section heading. You may add a sub heading not exceeding one line also here. Section...
  • What is Bullying?

    What is Bullying?

    Bullying is a big issue and can be scary to deal with,but by making small, simple changes we can all make sure our school is a safe, happy place for everyone. Individual . activity: Think .
  • Oracle's Business Strategy: Maximizing Your Sales Leverage

    Oracle's Business Strategy: Maximizing Your Sales Leverage

    George Bourmas Sales Consulting Manager Database & Options Is there a G-Cloud? In G-Cloud we define a "Private Cloud" as an infrastructure dedicated to government most likely amalgam of several compute utilities targeted to improve citizen services.