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
|
|
|