01_Altinok_cvpr06

01_Altinok_cvpr06 - Activity Analysis in Microtubule Videos...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Activity Analysis in Microtubule Videos by Mixture of Hidden Markov Models Alphan Altınok 1 Motaz El-Saban 2 Austin J. Peck 3 Leslie Wilson 3 Stuart C. Feinstein 3 B. S. Manjunath 2 Kenneth Rose 2 Computer Science 1 , Electrical and Computer Engineering 2 , Molecular, Cellular, and Developmental Biology 3 University of California Santa Barbara, Santa Barbara, CA, 93106 [email protected] Abstract We present an automated method for the tracking and dy- namics modeling of microtubules -a major component of the cytoskeleton- which provides researchers with a previously unattainable level of data analysis and quantification capa- bilities. The proposed method improves upon the manual tracking and analysis techniques by i) increasing accuracy and quantified sample size in data collection, ii) eliminat- ing user bias and standardizing analysis, iii) making avail- able new features that are impractical to capture manually, iv) enabling statistical extraction of dynamics patterns from cellular processes, and v) greatly reducing required time for entire studies. An automated procedure is proposed to track each resolvable microtubule, whose aggregate activ- ity is then modeled by mixtures of Hidden Markov Models to uncover dynamics patterns of underlying cellular and experimental conditions. Our results support manually es- tablished findings on an actual microtubule dataset and il- lustrate how automated analysis of spatial and temporal patterns offers previously unattainable insights to cellular processes. 1. Introduction Advances in computer vision and pattern analysis find excellent applications in biological data, specifically in the analysis of patterns on massive image and video libraries. Over the years, researchers generated large amounts of im- age and video libraries that stimulated research efforts for pattern analysis applications. In this context, microtubule (MT) dynamics research is one of these fields where auto- mated and advanced analysis techniques are anticipated to make a significant and imminent contribution. MTs are filamentous subcellular structures involved in essential cellular functions. Research on MT dynamics seeks to understand and quantify underlying cellular mech- anisms relating to normal and abnormal functioning of the cell in response to changes in environmental conditions [ 8 ]. A striking example is as follows: MTs regulate cell divi- sion by attaching to chromosomes and segregating them in dividing cells, and common conjecture is that certain vital diseases such as Alzheimer’s and cancer are at least cor- related with the regulatory abnormalities in MT dynamics. A clear understanding of MT activity (behavior) and causal factors may advance the state of the art in medicine....
View Full Document

This note was uploaded on 12/28/2011 for the course BIO 100 taught by Professor Gomez during the Fall '11 term at UCSB.

Page1 / 8

01_Altinok_cvpr06 - Activity Analysis in Microtubule Videos...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online