Activity Analysis in Microtubule Videos by Mixture of Hidden Markov Models

Abstract

We

Extracting Dynamic Microtubule Features from Image Sequences

“…In this section, we discuss two tracking methods: [3] uses active contours for extracting the MT length as open ended curves, and [10] uses a hidden Markov model based approach for tracking the deformation of a curve after initially tracing it on the first frame. From the usage point of view, the two methods provide different user interaction stipulations.…”

Deformable trellis: open contour tracking in bio-image sequences

“…The potential impact of automated analysis has attracted much attention. For recent results see, e.g., [1,2,3,4,5,6]. Herein we present a novel general approach and its application to the problem of tracking live cell microtubules.…”

Variable Length Open Contour Tracking Using a Deformable Trellis

“…The performance of the HMM-based open-contour tracking methods are also compared with two earlier approaches based on tip point matching [3] and discrete dynamic contour model [33]. To the best of our knowledge, these are the closest approaches which address the variable length open-contour deformations.…”

“…The energy minimization is performed by gradient descent and the energy is defined based on the local ridge strength and contour smoothness for the open-contour adjustment [3], [31]. Low signal to noise ratio makes the algorithm prone to be trapped in local minima, which is the main drawback of the active contours.…”

“…In the active contour approaches [2], end points are assumed to be fixed, hence any length changes due to end point motion (or growth and shortening) are not captured. On the other hand, tip matching-based tracking schemes [3] are highly prone to clutter.…”