Difference between revisions of "2014 Summer Project Week:mipiX"
From NAMIC Wiki
| (5 intermediate revisions by the same user not shown) | |||
| Line 2: | Line 2: | ||
<gallery> | <gallery> | ||
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]] | Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]] | ||
| − | Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly : mipiX] | + | Image:mipiX.png|[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true mipiX] |
| + | Image:mipiX_2.png|[http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true mipiX] | ||
</gallery> | </gallery> | ||
| Line 12: | Line 13: | ||
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions. | This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions. | ||
| − | [http:// | + | [http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/lupus/lupus_$_$.jpg&nDims=2&xBins=5&yBins=56&debug=true Lupus Dataset Demo] |
| − | [http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1# | + | [http://mipix.fotozygous.com/demo/?path=http://mipix.fotozygous.com/exdata/adnisel/crop_ds_$.nii.gz&nDims=1&xBins=20&crossOrigin=1&debug=1# ADNI Demo] |
| + | [http://www.mit.edu/~adalca/tipiXnightly/?path=http://www.mit.edu/~adalca/tipiX/imageSets/leuk/reg$_$.png&nDims=2&xBins=13&yBins=2&debug=true Time series demo] | ||
<div style="width: 27%; float: left; padding-right: 3%;"> | <div style="width: 27%; float: left; padding-right: 3%;"> | ||
<h3>Objective</h3> | <h3>Objective</h3> | ||
| Line 26: | Line 28: | ||
<div style="width: 27%; float: left; padding-right: 3%;"> | <div style="width: 27%; float: left; padding-right: 3%;"> | ||
<h3>Progress</h3> | <h3>Progress</h3> | ||
| − | * | + | Discussions led to: |
| + | * need support for multiple-sized images | ||
| + | * need support for various input types | ||
| + | * need support for more high dimensions, or fast switching between dimensions. We are considering use of mouse wheel. | ||
| + | Features implemented | ||
| + | * Support for (individual) mask files has been implemented and tested, although not yet in the full framework | ||
| + | * blending between images implemented | ||
| + | * started work on a simple GUI. | ||
| + | * investigated CamanJS for image control. | ||
</div> | </div> | ||
</div> | </div> | ||
Latest revision as of 14:08, 27 June 2014
Home < 2014 Summer Project Week:mipiX
Key Investigators
- Adrian Dalca, Ramesh Sridharan, Erjona Topalli, Polina Golland, MIT
Project Description
This is a new approach for fast and effective visualization of large image collections in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Increasingly, medical image computing research involves exploring large image sets with high intrinsic dimensionality. This includes three dimensions for each medical volume, and many meta-dimensions such as subject index, modality type in multimodal studies, time in longitudinal studies, or parameter choice in parameter sweep experiments. Current visualization tools generally display one or few 2D slices or 3D renderings at a time, and do not provide a natural way to explore the meta-dimensions.
Objective
- We intend to incorporate several new features into the tool, including the display of appropriate information about the volume and support for individual masks for each volume.
Approach, Plan
- The development is done mostly in Javascript, maintained open-source at https://github.com/adalca/tipiX
Progress
Discussions led to:
- need support for multiple-sized images
- need support for various input types
- need support for more high dimensions, or fast switching between dimensions. We are considering use of mouse wheel.
Features implemented
- Support for (individual) mask files has been implemented and tested, although not yet in the full framework
- blending between images implemented
- started work on a simple GUI.
- investigated CamanJS for image control.
