Home | Research | Publications | Industrial Experience | Education | Links

Research Interests

Biomedical image processing and segmentation, computer vision, image registration technique

 

 

Current Research

1. Automated Segmentation of Microtubules and Their Plus-ends

 

Kinetochore microtubules (KMTs) and plus-ends have been investigated extensively in cell biology and molecular medicine. Though electron tomography is able to image their high-resolution structures, the interpretation of the acquired data remains an obstacle due to the low signal noise ratio and crowded cellular environment. To overcome the low efficiency of manual segmentation, we developed a model-based automated approach to extracting KMTs and the associated plus-ends with a coarse-to-fine scale scheme consisting of volume preprocessing, microtubule segmentation and plus-end tracing.  In volume preprocessing, we first apply an anisotropic invariant wavelet transform and a tube-enhancing filter to enhance the microtubules for coarse localization. This is followed with a surface-enhancing filter to accentuate the fine microtubule boundary features. The microtubule body is then segmented using a modified active shape model method. Starting from the segmented microtubule body, the plus-ends are extracted with a probabilistic tracing method.

See slides here for details of our method and video file for sample results.

A slice in the electron tomography volume, KMTs indicated by arrows.

Left: a localized small volume, right: a segmented microtubule and its plus-ends filaments.

 

2. Level Set Segmentation with Shape Prior

 

 

 

A. Implementation of existing methods

 

 

 

Shape modeling with front propagation

Active contour with edges

Level Set Based Shape Prior Segmentation

 

 

Home | Research | Publications | Industrial Experience | Education | Links