Difference between revisions of "Integration of Neural Network Algorithms"

From NAMIC Wiki
Jump to: navigation, search
 
(6 intermediate revisions by the same user not shown)
Line 19: Line 19:
  
 
* Iowa: Nicole DeVries, Nicole Grosland, Vincent Magnotta
 
* Iowa: Nicole DeVries, Nicole Grosland, Vincent Magnotta
 +
 +
 +
'''Results'''
 +
{| class="wikitable" border="1" cellpadding="2"
 +
|+ANN Relative Overlap with Manual Rater
 +
|-
 +
! Subject !! Proximal Phalanx !! Middle Phalanx !! Distal Phalanx
 +
|-
 +
| 1 || 0.91 || 0.79 || 0.79
 +
|-
 +
| 2 || 0.91 || 0.88 || 0.84
 +
|-
 +
| 3 || 0.85 || 0.83 || 0.78
 +
|-
 +
| 4 || 0.86 || 0.81 || 0.68
 +
|-
 +
| 5 || 0.84 || 0.78 || 0.72
 +
|-
 +
! Average ||0.87 || 0.82 || 0.76
 +
|}
 +
 +
<br>
 +
<br>
 +
 +
{| class="wikitable" border="1" cellpadding="2"
 +
|+Average Distance Between ANN Derived Surface and Physical Laser Scanned Surface
 +
|-
 +
! Subject !! Proximal Phalanx (mm) !! Middle Phalanx (mm) !! Distal Phalanx (mm)
 +
|-
 +
| 1 || 0.23||0.12||0.17
 +
|-
 +
| 2 || 0.18||0.16||0.16
 +
|-
 +
| 3 || 0.35||0.27||0.97
 +
|-
 +
| 4 || 0.26||0.17||0.20
 +
|-
 +
! Bone Average ||0.26||0.18||0.38
 +
|}
 +
  
 
'''Links:'''
 
'''Links:'''
 
*[http://www.springerlink.com/content/b15376vwx00v5088/ Automated Bony Region Identification Using Artificial Neural Networks: Reliability and Validation Measurements. Esther E. Gassman, Stephanie M. Powell, Nicole A. Kallemeyn, Kiran H. Shivanna, Vincent A. Magnotta, Brian D. Adams, Nicole M. Grosland. Skeletal Radiology]
 
*[http://www.springerlink.com/content/b15376vwx00v5088/ Automated Bony Region Identification Using Artificial Neural Networks: Reliability and Validation Measurements. Esther E. Gassman, Stephanie M. Powell, Nicole A. Kallemeyn, Kiran H. Shivanna, Vincent A. Magnotta, Brian D. Adams, Nicole M. Grosland. Skeletal Radiology]
 +
*[http://www.ccad.uiowa.edu/mimx Musculoskeletal Imaging, Modeling and Experimentation (MIMX)]
 +
 +
'''Figures:'''
 +
[[Image:ANN-Segmentation-Phalanx.jpg |left|thumb|300px|Comparison of the manual and ANN segmentations of the phalanx bones. Manual segmentations are shown in red and automated in blue.]]

Latest revision as of 00:40, 7 January 2008

Home < Integration of Neural Network Algorithms

Objective:

  • Integrate artificial neural network segmentation into the NA-MIC kit for segmentation of upper extremity regions of interest.

Progress:

  • Base algorithm has been developed using the annie neural network library
  • Segmentation algorithm has been applied to segmentation of the phalanx bones on the index finger
    • Paper has been published on this initial work


To Do:

  • Initial evaluation of this technique has been performed for phalanx bones.
  • Need to rework ITK neural network libraries to allow the size of the network to be dynamic configured at run time instead of compile time
    • There are several issues that neeed to be resolved regarding the Neural network I/O in ITK
    • Consider the inclusion of the old ANN code that existed in the BRAINS software

Key Investigators:

  • Iowa: Nicole DeVries, Nicole Grosland, Vincent Magnotta


Results

ANN Relative Overlap with Manual Rater
Subject Proximal Phalanx Middle Phalanx Distal Phalanx
1 0.91 0.79 0.79
2 0.91 0.88 0.84
3 0.85 0.83 0.78
4 0.86 0.81 0.68
5 0.84 0.78 0.72
Average 0.87 0.82 0.76



Average Distance Between ANN Derived Surface and Physical Laser Scanned Surface
Subject Proximal Phalanx (mm) Middle Phalanx (mm) Distal Phalanx (mm)
1 0.23 0.12 0.17
2 0.18 0.16 0.16
3 0.35 0.27 0.97
4 0.26 0.17 0.20
Bone Average 0.26 0.18 0.38


Links:

Figures:

Comparison of the manual and ANN segmentations of the phalanx bones. Manual segmentations are shown in red and automated in blue.