COMP9517: Computer Vision
代写Computer Vision | 计算机视觉 | CV代写 – 这个题目属于一个Cv的代写任务, 涵盖了Computer Vision等程序代做方面
Motion and Tracking Applications
in Biomedical Imaging
Topics
Examples of change detection
- Patient motion correction in angiography
Examples of template matching
- Cell motion correction in microscopy
- Monomodal brain image registration
- Multimodal medical image registration
Examples of optical flow
- Heart tissue motion estimation
Examples of object tracking
- Particle tracking in molecular biology
- Bayesian multitarget tracking method
- Heart motion tracking and analysis
- Tracking for neuron reconstruction
- Object tracking in cell biology
Example of Change Detection
Digital Subtraction Angiography
0
X-ray at time t
Mask Image
X-ray at time
0
tt +
Live Image
Digital Subtraction Angiography
Live Mask Contrast Stretched Meijering et al., Radiology , 2001
Digital Subtraction Angiography
Contrast Stretched Motion Corrected
Automatic motion correction here is a form of template matching
Examples of Template Matching
Cell Motion Correction
Cell fixation by image post-
processing allows analysis of
the internal changes over time
Brain Image Registration
To understand how the human brain develops from childhood to adulthood and to study developmental disorders we can use magnetic resonance imaging (MRI) at different ages and match the images to a template using automatic image registration techniques
Joint Visualization
Multimodal Image Registration
Computed Tomography (CT)
Magnetic Resonance (MR)
Registration (alignment) of
images from multiple imaging
modalities (devices) allows
joint visualisation which may
provide additional information
to the physician
Example of Optical Flow
Heart Tissue Motion Estimation
- Heart tissue cultured 6 days
- Mono-layer cardiomyocytes
- Phase-contrast microscopy
- Real-time imaging 24 fps Since the images contain rich information it is easy to estimate local gradients with high accuracy so this is a perfect case for the optical flow method t
= fv f
Heart Tissue Motion
Motion vectors visualised by direction (color) and magnitude (intensity)
Examples of Object Tracking
Particle Tracking Problem
time
????
Bayesian Tracking
- Correction: Posterior Observation Model Prior 1
(|) (| )(| )
tt t t tt
PX Y LY X PX Y
1 1 11 1
(| ) (| )( | )
tt t t t t t
PX Y DX X PX Y dX
=
Prior Transition Model
- Prediction: Posterior
Computing the degree of belief in the object state by taking into
account all available evidence up to the current time point
(,, , , , )
t tt t t t
State: X rv a sI =
Position, velocity, acceleration, shape, intensity, …
()
t
expressed as probability density PX
Evidence: a set of images or extracted features { }
0
,,
tt
Yy y =
Bayesian Multitarget Tracking
X rv a sI 1; t =(, , , , ,)1; 1; tt t t t 1; 1; 1;
Extend the state space to include the states of all targets
1; 2; ;
( , ,, )
t t t Nt
X XX = X
X rv a sINt ; ; ; ; ;;=( , , , , ,) Nt Nt Nt Nt Nt
Computational cost grows exponentially with the number of targets
Requires heuristics to keep track of number of targets and identities
Use a mixture model of single-target probability densities
;
1
( |) ( |)
N
tt ntn tt
n
PXY wPXY
=
=
- Smal & Meijering
Tracking Heart Motion in MRI
Tracking Heart Motion in MRI
Tracks Strain
Smal& Meijering, Medical Image Analysis , 2012
Neuron Reconstruction
Neuron Reconstruction
T
xx xy xz
yx yy yz
zx zy zz
III
III
III
= =
HVV
Seed points:
3 21<<
1
v
3
2 v
v
Neuron Reconstruction
1; ( 1; ,,,,,1; 1; 1; 1; 1; )
xyz
x k = x yzvvvk kkkkk
Target states
2; ( 2; ,,,,,2; 2; 2; 2; 2; )
xyz
x k = x yzvvvk kkkkk
3; ( 3; ,,,,,3; 3; 3; 3; 3; )
xyz
x k = x yzvvvk kkkkk
; ; ;;;;;( ,,,,,)
xyz
x Nk = x yzvvvNk Nk Nk Nk Nk Nk
Tracking for Neuron Reconstruction
Radojevic & Meijering, Neuroinformatics , 2019
Neuron Reconstruction Results
Cell Tracking
Popular segmentation methods
- Intensity thresholding
- Watershed segmentation
- Active contour fitting
- Level-set segmentation () n ( ) n Cr = Br n
Model: P
Fitting: C =argmin ( ) EC
level-set function
zero-level set
Cell Tracking
Linking by contour model evolution
Dzyubachyk & Meijering, IEEE Transactions on Medical Imaging , 2010
Cell Tracking
Coloured contours indicate the results of cell segmentation and indentification
Cell Lineage Reconstruction
Drosophila embryogenesis Keller et al. 2014
Cell Lineage Reconstruction
Tracking each cell during Drosophila embryonic development
Keller et al., Nature Methods , 2014
References and Acknowledgements Further information on the presented applications can be found in the following papers:
- Image Registration for Digital Subtraction Angiography
- Advanced Level-Set Based Cell Tracking in Time-Lapse Fluorescence Microscopy
- Multimodal Volume Registration by Maximization of Mutual Information
- Optical-Flow Based Non-Invasive Analysis of Cardiomyocyte Contractility
- Multiple Object Tracking in Molecular Bioimaging by RBM Particle Filtering
- Objective Comparison of Particle Tracking Methods
- Reversible Jump MCMC Methods for Fully Automatic Motion Analysis in Tagged MRI
- Automated Neuron Tracing Using Probability Hypothesis Density Filtering
- An Objective Comparison of Cell-Tracking Algorithms
- Methods for Cell and Particle Tracking
- Reconstruction of Cell Lineages From Large-Scale Fluorescence Microscopy Data
- A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking