{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"# Introduction to the Insight Toolkit (ITK)"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Learning Objectives\n",
"\n",
"* Learn how to **run** cells in **a Jupyter Notebook**\n",
"* Run a segmentation example that demonstrates **ITK**'s ability to provide **insight into images**\n",
"* Understand the **purpose and capabilities** of the toolkit"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"## Jupyter Notebooks"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"These are [Jupyter Notebooks](https://jupyter.org/), an open-source web application that allows you to create and share documents that contain live code, equations, visualizations and narrative text.\n",
"\n",
"To run cells in the notebook, press *shift + enter*.\n",
"\n",
"For more information, see the [Notebook Help](https://nbviewer.jupyter.org/github/ipython/ipython/blob/3.x/examples/Notebook/Index.ipynb)"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"## Insight Into Images"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"outputs": [],
"source": [
"import itk\n",
"\n",
"from itkwidgets import view"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"slideshow": {
"slide_type": "fragment"
}
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4cdfc916fe954f998b62ecd4b18f637e",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Viewer(gradient_opacity=0.8, rendered_image=<itkImagePython.itkImageF3; proxy of <Swig Object of type 'itkImag…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"file_name = 'data/brainweb165a10f17.mha'\n",
"image = itk.imread(file_name, itk.ctype('float'))\n",
"view(image, slicing_planes=True, gradient_opacity=0.8, ui_collapsed=True)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e83c0d5f34a5421f8aef475ea7e928ae",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Viewer(gradient_opacity=0.8, rendered_image=<itkImagePython.itkImageF3; proxy of <Swig Object of type 'itkImag…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Smooth the image\n",
"smoothed = itk.curvature_flow_image_filter(image,\n",
" number_of_iterations=6,\n",
" time_step=0.005)\n",
"view(smoothed, slicing_planes=True, gradient_opacity=0.8, ui_collapsed=True)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"outputs": [],
"source": [
"# Segment the white matter with a 3D region-growing algorithm\n",
"confidence_connected = itk.ConfidenceConnectedImageFilter.New(smoothed)\n",
"confidence_connected.SetMultiplier(2.5)\n",
"confidence_connected.SetNumberOfIterations(5)\n",
"confidence_connected.SetInitialNeighborhoodRadius(2)\n",
"confidence_connected.SetReplaceValue(255)\n",
"\n",
"confidence_connected.AddSeed([118, 133, 92])\n",
"confidence_connected.AddSeed([63, 135, 94])\n",
"confidence_connected.AddSeed([63, 157, 90])\n",
"confidence_connected.AddSeed([111, 150, 90])\n",
"confidence_connected.AddSeed([111, 50, 88])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "5d0fab5c630e4ed28e79fd4253b94f53",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Viewer(annotations=False, cmap='BuPu', gradient_opacity=0.22, rendered_image=<itkImagePython.itkImageSS3; prox…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"confidence_connected.Update()\n",
"view(confidence_connected, ui_collapsed=True, cmap='BuPu', shadow=False, annotations=False)"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"## History of ITK"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Insight into Images\n",
"\n",
"\n",
"\n",
"http://itk.org"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### History\n",
"\n",
"In 1999, the US National Institute of Health’s (NIH) National Library of Medicine (NLM) started a project to support the Visible Human Project.\n",
"\n",
"\n",
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Goals\n",
"\n",
"* Collect best-of-the-best image analysis algorithms for reproducible science.\n",
"* Provide a software resource for teaching medical image analysis algorithms.\n",
"* Establish a foundation for future research.\n",
"* Support commercial applications.\n",
"* Create conventions for future work.\n",
"* Grow a self-sustaining community of software users and developers."
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Continued Development\n",
"\n",
"* Development has progressed since 1999\n",
"* Contributions from over 267 developers\n",
"* Over 1.6 million lines of code\n",
"* Downloaded over 500,000 times\n",
"\n",
"\n",
"\n",
"ITK contributors locations for the 4.8 and 4.9 releases."
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"## Features"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### N-Dimensional Image Filtering\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Filtering Algorithms Classes\n",
"\n",
"* Fast marching methods\n",
"* Convolution\n",
"* Image gradient\n",
"* Denoising\n",
"* Thresholding\n",
"* Mathematical morphology\n",
"* Smoothing\n",
"* Image features\n",
"* Image statistics\n",
"* Bias correction\n",
"* Image grid operations\n",
"* ...."
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Segmentation\n",
"\n",
"\"Image segmentation is the process of partitioning a digital image into multiple segments, i.e. sets of pixels. The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze.\"\n",
"\n",
"Source: [Wikipedia](https://en.wikipedia.org/wiki/Image_segmentation)"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Segmentation\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Segmentation\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Segmentation\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Segmentation\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Segmentation\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Segmentation\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Registration\n",
"\n",
"\"Image registration is the process of transforming different sets of data into one coordinate system. [...] Registration is necessary in order to be able to compare or integrate the data obtained from these different measurements.\"\n",
"\n",
"Source: [Wikipedia](https://en.wikipedia.org/wiki/Image_registration)"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Registration\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Other Data Structures\n",
"\n",
"* Mesh's\n",
"* Transforms's\n",
"* SpatialObject's\n",
"* Path's\n",
"* LabelMap's\n",
"\n",
"\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### ITK Resources\n",
"\n",
"* ITK Software Guide: https://www.itk.org/ItkSoftwareGuide.pdf\n",
"\n",
"* Discourse Discussion: https://discourse.itk.org\n",
"\n",
"* Sphinx Examples: https://www.itk.org/ITKExamples\n",
"\n",
"* `Examples/` directory in the ITK repository\n",
"\n",
"* Wiki Examples: http://www.itk.org/Wiki/ITK/Examples\n",
"\n",
"* Doxygen: http://www.itk.org/Doxygen/html/index.html\n",
"\n",
"* Kitware: https://www.kitware.com/"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Kitware, Inc\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"- Collaborative, Open Source, Scientific Software Development\n",
"- Carrboro, NC, near University of North Carolina-Chapel Hill, in the Research Triangle"
]
},
{
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "subslide"
}
},
"source": [
"### Enjoy ITK!"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.3"
}
},
"nbformat": 4,
"nbformat_minor": 1
}