Difference between revisions of "ITK Analysis of Large Histology Datasets"

From NAMIC Wiki
Jump to: navigation, search
 
(10 intermediate revisions by the same user not shown)
Line 1: Line 1:
 +
__NOTOC__
 +
 +
[[File:  pipe.JPG]]
 +
[[File: reg.JPG]]
 +
[[File: seg.JPG]]
 +
==Key Investigators==
 +
* OSU: Liya Ding, Kun Huang, Raghu Machiraju
 +
* Harvard Medical School: Sean Megason
 +
 
==Project==
 
==Project==
  
 
<div style="margin: 20px;">
 
<div style="margin: 20px;">
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
  
 
<h3>Objective</h3>
 
<h3>Objective</h3>
 
</div>
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
 
 
3D histology stacks are being increasingly used to understand gross anatomical changes and to provide
 
3D histology stacks are being increasingly used to understand gross anatomical changes and to provide
 
valuable educational contexts. Most existing toolkits allow a 2D approach and do not meet the challenges
 
valuable educational contexts. Most existing toolkits allow a 2D approach and do not meet the challenges
Line 15: Line 19:
 
sensible registration, segmentation and reconstruction of digital slides depicting various organs and tissue
 
sensible registration, segmentation and reconstruction of digital slides depicting various organs and tissue
 
systems. Modules will be included that will allow for pre-processing (color correction, artifact removal,
 
systems. Modules will be included that will allow for pre-processing (color correction, artifact removal,
etc.), rigid and non-rigid registration, material-based segmentation, and visualization. Additionally, we will
+
etc.), rigid and non-rigid registration, material-based segmentation, and visualization.
provide access to multi resolution data that describes ensembles of nephrons in a human kidney.
 
 
 
<h3>Approach, Plan</h3>
 
  
 
</div>
 
</div>
<div style="width: 40%; float: left;">
+
<div style="width: 27%; float: left; padding-right: 3%;">
  
 +
<h3>Approach, Plan</h3>
 
we have developed a series of algorithms and
 
we have developed a series of algorithms and
 
computational pipelines for processing large microscopy images using heterogeneous
 
computational pipelines for processing large microscopy images using heterogeneous
Line 29: Line 31:
 
microscopy images to enable both 2D and 3D digital histology.
 
microscopy images to enable both 2D and 3D digital histology.
  
 +
</div>
 +
<div style="width: 40%; float: left;">
  
 
<h3>Progress</h3>
 
<h3>Progress</h3>
 +
We are creating three different workflows to achieve our goals. These
 +
workflows accomplish (i) pre-preprocessing the data, (ii) registration/3D reconstruction
 +
and segmentation/classification of tissue regions from multi-channel data, (iii) and the
 +
visualization of the microstructure.
 +
 +
During this project week, we learn about ITK modules for registration, ITK filters and 3D Slicer.
 +
We will convert our algorithms into ITK modules and also into a pipeline in 3D slicer in the future.
  
 
</div>
 
</div>
Line 36: Line 47:
  
 
<div style="width: 97%; float: left;">
 
<div style="width: 97%; float: left;">
 
We are creating three different workflows to achieve our goals. These
 
workflows accomplish (i) pre-preprocessing the data, (ii) registration/3D reconstruction
 
and segmentation/classification of tissue regions from multi-channel data, (iii) and the
 
visualization of the microstructure. We have previously developed this workflow for a
 
large scale 3D reconstruction from histological
 
images study for mouse placenta as shown in
 
Figure 1 [1, 3] which is almost universal for similar
 
applications.
 

Latest revision as of 14:28, 25 June 2010

Home < ITK Analysis of Large Histology Datasets


Pipe.JPG Reg.JPG Seg.JPG

Key Investigators

  • OSU: Liya Ding, Kun Huang, Raghu Machiraju
  • Harvard Medical School: Sean Megason

Project

Objective

3D histology stacks are being increasingly used to understand gross anatomical changes and to provide valuable educational contexts. Most existing toolkits allow a 2D approach and do not meet the challenges posed by 3D histology. ITKv4 can facilitate the realization application level toolkits that will allow for a sensible registration, segmentation and reconstruction of digital slides depicting various organs and tissue systems. Modules will be included that will allow for pre-processing (color correction, artifact removal, etc.), rigid and non-rigid registration, material-based segmentation, and visualization.

Approach, Plan

we have developed a series of algorithms and computational pipelines for processing large microscopy images using heterogeneous computing platforms including GPU and CPU/GPU clusters. We will extend ITKv4 by incorporating algorithm families that will allow for comprehensive processing of light microscopy images to enable both 2D and 3D digital histology.

Progress

We are creating three different workflows to achieve our goals. These workflows accomplish (i) pre-preprocessing the data, (ii) registration/3D reconstruction and segmentation/classification of tissue regions from multi-channel data, (iii) and the visualization of the microstructure.

During this project week, we learn about ITK modules for registration, ITK filters and 3D Slicer. We will convert our algorithms into ITK modules and also into a pipeline in 3D slicer in the future.