The Third I nternational C onference on D igital I nformation P rocessing and C ommunications ( I C D I P C 2013) Medical Image Segmentation Using Hidden Markov Random Field A Distributed Approach Theme SAMY AIT-AOUDIA, RAMDANE MAHIOU, EL-HACHEMI GUERROUT
24
Embed
Medical Image Segmentation Using Hidden Markov Random Field A Distributed Approach
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
The Third International Conference on Digital Information Processing and Communications (ICDIPC 2013)
Medical Image Segmentation Using Hidden Markov Random Field A Distributed Approach
Theme
SAMY AIT-AOUDIA,
RAMDANE MAHIOU,
EL-HACHEMI GUERROUT
INTRODUCTION
SEGMENTATION BY USING HMRF
EXPERIMENTAL RESULTS
CONCLUSION AND PERSPECTIVES
P L A N
2
One exam by CT (Computed Tomography) scanner can produce hundred images.
All of these images represents a 3D
image
Processing and analysis of these images becomes a difficult and daunting task
The classical analysis of medical cuts
3
I N T R O D U C T I O N
Problem
3D automatic segmentation
The 3D image The segmented 3D image
4
I N T R O D U C T I O NSolution :
Tool to aid the physician to make the decisionbased on Automatic segmentation.
5
T H E A I MRelevance of the physician aid tool to
make the decision based on
OUR AIM
The time of computation The quality of segmentation
TIME + QUALITY
INTRODUCTION
SEGMENTATION BY USING HMRF
EXPERIMENTAL RESULTS
CONCLUSION AND PERSPECTIVES
P L A N
6
S E G M E N T A T I O N B Y U S I N G H M R F
7
1 23 4
Y: Observed Image
X: Hidden Image
2C,s
2s ),(2-(1)2ln(2
)²-(yy)(x,
ttsx
Ss x
x xxTs
s
s
y)(x,minarg Xx
x
S E G M E N T A T I O N B Y U S I N G H M R F
8
Optimizations techniques are used like ICM, …
Problem
Minimizing the function (x,y) is computationally intractable.
Solution
S E G M E N T A T I O N B Y U S I N G H M R FICM Algorithm:
1. Initialization: Start with an arbitrary labeling x0 and let n=0.
2. At step n:
Visit all the sites according to a visiting scheme and in every site :
,
3. Increment n. Goto 2, until a stopping criterion is satisfied.