Traumatic brain injury tbi detection
Download
1 / 19

Traumatic Brain Injury (TBI) Detection - PowerPoint PPT Presentation


  • 92 Views
  • Uploaded on

Traumatic Brain Injury (TBI) Detection. Final Presentation –Winter 2012 Date : 10.05.2012 Presenters: Malihi Naveh , Fidelman Peli Project Advisor: Aides Amit Project Initiator: Dr. Nakhmani Arie. Motivation. TBI caused by an acute event Severe damage to portions of the brain

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' Traumatic Brain Injury (TBI) Detection' - varuna


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Traumatic brain injury tbi detection

Traumatic Brain Injury (TBI) Detection

Final Presentation –Winter 2012

Date: 10.05.2012

Presenters: MalihiNaveh, FidelmanPeli

Project Advisor: Aides Amit

Project Initiator: Dr. NakhmaniArie


Motivation
Motivation

  • TBI caused by an acute event

  • Severe damage to portions of the brain

  • TBI may cause severe disabilities - cognitive deflects, communication, mental health.

  • 1.7 million new cases of TBI in the U.S. each year

  • 50,000 deaths caused by TBI each year in the U.S.

  • Need for automatic tools for TBI clinical practice and patient monitoring


Mri imaging
MRI Imaging

  • Magnetic Resonance Imaging (MRI)

  • A medical imaging technique used in radiology to visualize internal structures of the body

  • Good contrast between the different soft tissues of the body

  • MRI uses non-ionizing radiation (unlike CT)

  • Different types of MRI scans: MP_RAGE, FLAIR, T1-weighted etc.

  • Expansive


Literature survey
Literature survey

  • Main approaches for TBI detection:

    • Population based atlases

    • Symmetry based analysis

  • We chose the symmetry based approach

    • Doesn’t require statistical analysis of large data bases

    • More robust – age & population independent

  • Symmetry Axis detection:

    • Preprocessing – brain segmentation3

    • PCA – Principal Component Analysis1,5

    • PSD – Phase Based Symmetry detection1

    • Gravitational torque4


Literature survey1
Literature survey

  • Symmetry Analysis

    • Gabor8,10

    • Edge matching

    • Flow vector8

    • Energy medians comparison (boxing)11

  • Methods fusion

  • Active Contours12

[1] http://en.wikipedia.org/wiki/Magnetic_resonance_imaging#Other_specialized_MRI_techniques

[2] http://www.na-mic.org/Wiki/index.php/DBP3:UCLA#What_is_traumatic_brain_injury.3F

[3] L. Smith, A Tutorial on Principal Components Analysis, www.cs.otago.ac.nz/cosc453/student_tutorials/principal_components.pdf, 2002.

[4] Zhito Xiao and Hun Wu, “Analysis on Image Symmetry Detection Algorithms”, (FSKD 2007. V.4, pp 745-750.

[5] E Song ,et al, ” Symmetry analysis to detect pathological brain in MRI”, MIPPR 2007.Proc. of SPIEVol. 6789,.67891F, (2007).

[6]  StivenSchwanz Dias, “Improved 2D Gabor filter”, Matlab Central – File exchange,

http://www.mathworks.com/matlabcentral/fileexchange/13776-improved-2d-gabor-filter.

[7] H. Khotanlou, O. Colliot, I. Bloch, “Automatic brain tumor segmentation using symmetry analysis and deformable models”, in: Internat. Conf. on Advances in Pattern Recognition ICAPR, Kolkata, India, January 2007.

[8] Y. Sun, B. Bhanu, and S. Bhanu, “Automatic Symmetry-Integrated Brain Injury Detection in MRI Sequences”, Proc. IEEE CS Conf. Computer Vision and Pattern Recognition Workshop, 2009.

[9] ValentinaPedoia, ElisabettaBinaghi, Sergio Balbi, Alessandro De Benedictis, EmanueleMontiand Renzo Minotto, "Glial brain tumor detection by using symmetry analysis", Proc. SPIE 8314, Medical Imaging 2012: Image Processing, 831445 (February 23, 2012); doi:10.1117/12.910172; http://dx.doi.org/10.1117/12.910172.

[10] J. Movellan, “Tutorial on Gabor Filters”, technical report, MPLab Tutorials, Univ. of California, San Diego, 2005. 

[11] N. Ray, R. Greiner and A. Murtha, “Using Symmetry to Detect Abnormalities in Brain MRI”, Computer Society of India Communications, 31(19), pp 7-10, 2008.

[12] LiorDeutch & Marina Kokotov, “Sobolov Active Countours without edges”, a Student project in course “Introduction to Medicl Imaging”, Spring 2010.


Proposed solution
Proposed solution

PCA

Symmetry Axis

Gabor

Edge Matching

Symmetry affinity

Empiric Threshold

Thresholding

Morphological

Clustering

Active Contours

Contour

3D modeling

3D model


Proposed solution1
Proposed solution

PCA

Symmetry Axis

Gabor

Edge Matching

Symmetry affinity

Empiric Threshold

Thresholding

Morphological

Clustering

Active Contours

Contour

3D modeling

3D model


PCA

Symmetry Axis

Symmetry affinity

Thresholding

  • Without Brain segmentation

    • Offset

  • Improvement Needed

  • Continued with manual Axis

Clustering

Contour

3D modeling


Gabor
Gabor

Symmetry Axis

  • Used As a BandPass

  • Gaussian size -> resolution

  • Circle shaped filter

  • Direction Variant

  • DC compensation

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


Gabor1
Gabor

Symmetry Axis

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


Edge detection
Edge Detection

Symmetry Axis

  • Bilateral Symmetry

  • Manual Axis

  • Used: Canny Edges

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


Edge detection1
Edge Detection

Symmetry Axis

  • Edges Flipped on each other

  • Later used: bwdist

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


Masking and clustering
Masking and Clustering

Symmetry Axis

  • Skull removal

    • Elipse Shaped mask

  • Removal of small objects

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


Active contour
Active Contour

Symmetry Axis

  • Use initial detection edges as initial Snake.

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


Active contour1
Active Contour

  • Get final Contour using an active contour method.

    • Sobolev Snake

Symmetry Axis

Symmetry affinity

Thresholding

Click to

See Movie

Clustering

Contour

3D modeling


Active contour2
Active Contour

  • Get final Contour using an active contour method.

    • Sobolev Snake

Symmetry Axis

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


3d modeling
3D modeling

Symmetry Axis

  • Use Snakes from different frames as initial 3d data.

  • Apply continuity conditions.

  • Smoothing the data using 3d gaussian.

  • Determine blood pool surface in 3d space.

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


3d modeling1
3D modeling

Symmetry Axis

  • Plot Blood Pools Using Patch:

Symmetry affinity

Thresholding

Clustering

Contour

3D modeling


Conclusions
Conclusions

  • A working Algorithm to detect Brain Blood Pools was presented.

  • Novelties in this work:

    • Symmetry Affinity Based on Edge comparison

    • 3D continuity conditions


ad