Merge pull request #459 from zivy/updateURLs

Manually update code urls.

Python_html/04_Image_Display.html

@@ -7550,7 +7550,7 @@
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
 <h1>Image Display <a href="https://mybinder.org/v2/gh/InsightSoftwareConsortium/SimpleITK-Notebooks/master?filepath=Python%2F04_Image_Display.ipynb"><img alt="No description has been provided for this image" src="https://mybinder.org/badge_logo.svg" style="float: right;"/></a></h1>
 <p>The native SimpleITK approach to displaying images is to use an external viewing program. In the notebook environment it is convenient to use matplotlib to display inline images and if the need arises we can implement some reasonably rich inline graphical user interfaces, combining control components from the ipywidgets package and matplotlib based display.</p>
-<p>In this notebook we cover the usage of external programs and matplotlib for viewing images. We also instantiate a more involved inline interface that uses ipywidgets to control display. For the latter type of moderately complex display, used in many of the notebooks, take a look at the <a href="gui.py">gui.py</a> file.</p>
+<p>In this notebook we cover the usage of external programs and matplotlib for viewing images. We also instantiate a more involved inline interface that uses ipywidgets to control display. For the latter type of moderately complex display, used in many of the notebooks, take a look at the <a href="https://github.com/InsightSoftwareConsortium/SimpleITK-Notebooks/blob/master/Python/gui.py">gui.py</a> file.</p>
 </div>
 </div>
 </div>

Python_html/05_Results_Visualization.html

@@ -7558,7 +7558,7 @@ <h1>Visualization of Segmentation and Registration Results <a href="https://mybi
 <p>The following filters and their procedural counterparts are useful for various image creation tasks, as illustrated in this notebook:</p>
 <ul>
 <li><a href="https://simpleitk.org/doxygen/latest/html/classitk_1_1simple_1_1CastImageFilter.html">CastImageFilter</a></li>
-<li><a href="https://simpleitk.org/doxygen/latest/html/classitk_1_1simple_1_1ResampleImageFilter.html">ResampleImageFilter</a>, one of the more important filters in your toolbox, see <a href="21_Transforms_and_Resampling.ipynb">this notebook</a> for additional usage details.</li>
+<li><a href="https://simpleitk.org/doxygen/latest/html/classitk_1_1simple_1_1ResampleImageFilter.html">ResampleImageFilter</a>, one of the more important filters in your toolbox, see <a href="http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/21_Transforms_and_Resampling.html">this notebook</a> for additional usage details.</li>
 <li><a href="https://simpleitk.org/doxygen/latest/html/classitk_1_1simple_1_1TileImageFilter.html">TileImageFilter</a></li>
 <li><a href="https://simpleitk.org/doxygen/latest/html/classitk_1_1simple_1_1CheckerBoardImageFilter.html">CheckerBoardImageFilter</a></li>
 <li><a href="https://simpleitk.org/doxygen/latest/html/classitk_1_1simple_1_1ComposeImageFilter.html">ComposeImageFilter</a></li>

Python_html/21_Transforms_and_Resampling.html

@@ -7773,7 +7773,7 @@ <h2 id="Creating-and-Manipulating-Transforms">Creating and Manipulating Transfor
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<p>A number of other transforms exist to represent non-affine deformations, well-behaved rotation in 3D, etc. See the <a href="22_Transforms.ipynb">Transforms</a> tutorial for more information.</p>
+<p>A number of other transforms exist to represent non-affine deformations, well-behaved rotation in 3D, etc. See the <a href="http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/22_Transforms.html">Transforms</a> tutorial for more information.</p>
 </div>
 </div>
 </div>

Python_html/34_Segmentation_Evaluation.html

@@ -7571,7 +7571,7 @@ <h1>Segmentation Evaluation <a href="https://mybinder.org/v2/gh/InsightSoftwareC
 </ul>
 <p>The relevant criteria are task dependent, so you need to ask yourself whether you are interested in detecting spurious errors or not (mean or max surface distance), whether over/under segmentation should be differentiated (volume similarity and Dice or just Dice), and what is the ratio between acceptable errors and the size of the segmented object (Dice coefficient may be too sensitive to small errors when the segmented object is small and not sensitive enough to large errors when the segmented object is large).</p>
 <p>The data we use in the notebook is a set of manually segmented liver tumors from a single clinical CT scan. The relevant publication is: T. Popa et al., "Tumor Volume Measurement and Volume Measurement Comparison Plug-ins for VolView Using ITK", SPIE Medical Imaging: Visualization, Image-Guided Procedures, and Display, 2006.</p>
-<p><strong>Note</strong>: The approach described here can also be used to evaluate Registration, as illustrated in the <a href="65_Registration_FFD.ipynb">free form deformation notebook</a>.</p>
+<p><strong>Note</strong>: The approach described here can also be used to evaluate Registration, as illustrated in the <a href="http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/65_Registration_FFD.html">free form deformation notebook</a>.</p>
 <p><strong>Recommended read</strong>: A community effort describing limitations of various evaluation metrics,
 A. Reinke et al., "Common Limitations of Image Processing Metrics: A Picture Story", available from arxiv (<a href="https://arxiv.org/pdf/2104.05642.pdf">PDF</a>).</p>
 </div>

Python_html/61_Registration_Introduction_Continued.html

@@ -7549,7 +7549,7 @@
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
 <h1 id="Introduction-to-SimpleITKv4-Registration---Continued">Introduction to SimpleITKv4 Registration - Continued<a class="anchor-link" href="#Introduction-to-SimpleITKv4-Registration---Continued">¶</a></h1><h2 id="ITK-v4-Registration-Components">ITK v4 Registration Components<a class="anchor-link" href="#ITK-v4-Registration-Components">¶</a></h2><p><img alt="No description has been provided for this image" src="ITKv4RegistrationComponentsDiagram.svg" style="width:700px"/><br/><br/></p>
-<p>Before starting with this notebook, please go over the first introductory notebook found <a href="60_Registration_Introduction.ipynb">here</a>.</p>
+<p>Before starting with this notebook, please go over the first introductory notebook found <a href="http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/60_Registration_Introduction.html">here</a>.</p>
 <p>In this notebook we will visually assess registration by viewing the overlap between images using external viewers.
 The two viewers we recommend for this task are <a href="http://www.itksnap.org">ITK-SNAP</a> and <a href="http://www.slicer.org/">3D Slicer</a>. ITK-SNAP supports concurrent linked viewing between multiple instances of the program. 3D Slicer supports concurrent viewing of multiple volumes via alpha blending.</p>
 </div>

Python_html/65_Registration_FFD.html

@@ -8034,7 +8034,7 @@ <h2 id="Perform-Registration">Perform Registration<a class="anchor-link" href="#
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
 <p>Another option for evaluating the registration is to use segmentation. In this case, we transfer the segmentation from one image to the other and compare the overlaps, both visually, and quantitatively.</p>
-<p><b>Note</b>: A more detailed version of the approach described here can be found in the <a href="34_Segmentation_Evaluation.ipynb">Segmentation Evaluation notebook</a>.</p>
+<p><b>Note</b>: A more detailed version of the approach described here can be found in the <a href="http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/34_Segmentation_Evaluation.html">Segmentation Evaluation notebook</a>.</p>
 </div>
 </div>
 </div>

Python_html/70_Data_Augmentation.html

@@ -8571,7 +8571,7 @@ <h2 id="Radial-Distortion">Radial Distortion<a class="anchor-link" href="#Radial
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<h3 id="Transferring-deformations---exercise-for-the-interested-reader">Transferring deformations - exercise for the interested reader<a class="anchor-link" href="#Transferring-deformations---exercise-for-the-interested-reader">¶</a></h3><p>Using SimpleITK we can readily transfer deformations from a spatio-temporal data set to another spatial data set to simulate temporal behavior. Case in point, using a 4D (3D+time) CT of the thorax we can estimate the respiratory motion using non-rigid registration and <a href="65_Registration_FFD.ipynb">Free Form Deformation</a> or <a href="66_Registration_Demons.ipynb">displacement field</a> transformations. We can then register a new spatial data set to the original spatial CT (non-rigidly) followed by application of the temporal deformations.</p>
+<h3 id="Transferring-deformations---exercise-for-the-interested-reader">Transferring deformations - exercise for the interested reader<a class="anchor-link" href="#Transferring-deformations---exercise-for-the-interested-reader">¶</a></h3><p>Using SimpleITK we can readily transfer deformations from a spatio-temporal data set to another spatial data set to simulate temporal behavior. Case in point, using a 4D (3D+time) CT of the thorax we can estimate the respiratory motion using non-rigid registration and <a href="http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/65_Registration_FFD.html">Free Form Deformation</a> or <a href="http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/66_Registration_Demons.html">displacement field</a> transformations. We can then register a new spatial data set to the original spatial CT (non-rigidly) followed by application of the temporal deformations.</p>
 <p>Note that unlike the arbitrary spatial transformations we used for data-augmentation above this approach is more computationally expensive as it involves multiple non-rigid registrations. Also note that as the goal is to use the estimated transformations to create plausible deformations you may be able to relax the required registration accuracy.</p>
 </div>
 </div>

Python_html/71_Trust_But_Verify.html

@@ -7548,7 +7548,7 @@
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<h1 id="Trust-but-Verify---Inspection-of-Large-Image-Collections">Trust but Verify - Inspection of Large Image Collections<a class="anchor-link" href="#Trust-but-Verify---Inspection-of-Large-Image-Collections">¶</a></h1><p>This notebook and accompanying <a href="scripts/characterize_data.py">Python script</a> illustrate the use of SimpleITK as a tool for efficient data inspection on large image collections, as part of familiarizing oneself with the data and performing cleanup prior to its use in deep learning or any other supervised machine learning approach.</p>
+<h1 id="Trust-but-Verify---Inspection-of-Large-Image-Collections">Trust but Verify - Inspection of Large Image Collections<a class="anchor-link" href="#Trust-but-Verify---Inspection-of-Large-Image-Collections">¶</a></h1><p>This notebook and accompanying <a href="https://github.com/InsightSoftwareConsortium/SimpleITK-Notebooks/blob/master/Python/scripts/characterize_data.py">Python script</a> illustrate the use of SimpleITK as a tool for efficient data inspection on large image collections, as part of familiarizing oneself with the data and performing cleanup prior to its use in deep learning or any other supervised machine learning approach.</p>
 <p>The reasons for inspecting your data before using it include:</p>
 <ol>
 <li>Identification of corrupt images.</li>
@@ -7643,7 +7643,7 @@ <h1 id="Trust-but-Verify---Inspection-of-Large-Image-Collections">Trust but Veri
 </div>
 <div class="jp-InputArea jp-Cell-inputArea"><div class="jp-InputPrompt jp-InputArea-prompt">
 </div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput" data-mime-type="text/markdown">
-<h2 id="Data">Data<a class="anchor-link" href="#Data">¶</a></h2><p>For convenience, we use the heterogeneous notebook data. This dataset includes both 2D and 3D images, color and greyscale and 3D images stored as a set of 2D slices (DICOM series). Before starting down this path, make sure you have downloaded all notebook data. Downloading the data is described in the <a href="00_Setup.ipynb">setup notebook</a>.</p>
+<h2 id="Data">Data<a class="anchor-link" href="#Data">¶</a></h2><p>For convenience, we use the heterogeneous notebook data. This dataset includes both 2D and 3D images, color and greyscale and 3D images stored as a set of 2D slices (DICOM series). Before starting down this path, make sure you have downloaded all notebook data. Downloading the data is described in the <a href="http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/00_Setup.html">setup notebook</a>.</p>
 <p>Generally speaking, in the context of deep learning most datasets will be larger and more homogeneous. A nicely sized dataset that is "just right" in terms of download time, yet is large enough to illustrate the utility of data inspection, more than 7000 images, is the OpenI Indiana chest x-ray dataset (+100GB of DICOM images in a <a href="https://openi.nlm.nih.gov/imgs/collections/NLMCXR_dcm.tgz">single tgz file</a>).</p>
 <p>The publication describing the dataset is: D. Demner-Fushman et. al., "Preparing a collection of radiology examinations for distribution and retrieval", J Am Med Inform Assoc., 23(2):304-310, 2016.</p>
 <p>Using the Indiana dataset, see how long it takes you to identify several images that should have not been included. See if you could identify them only using the textual based csv summary report file.</p>