ITK Analysis of Large Histology Datasets
Project
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. Additionally, we will provide access to multi resolution data that describes ensembles of nephrons in a human kidney.
Objective
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.
Approach, Plan
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.
