Classified information.

Dr Vipoir's mission this month (which he has chosen to accept) is to highlight some of the features of Volocity Classification which can help you to find and measure objects in 3D quickly and accurately.

I'm going to use the 3D volume dataset shown above, which shows a large number of vesicles that occur throughout the whole volume. The image here is just one Image view from the set that I will be using in this demonstration.

You may or may not already know what the Classifier is, but for those of you that don't;

The Classifier in Volocity is all about object identification, this will allow you to measure objects in 2D, 3D and 4D.
The classifier will allow us to identify objects on the basis of Intensity, Size, Shape;
with further tools to;
Reduce noise in selection
Fill holes within objects
Ignore objects that touch the edge of the sample
Separate touching objects.

The first thing to do is select a region that is typical of the objects that you want to count and measure, the magic wand Region of Interest tool is ideally suited to this, see how I have selected a region below.

Lets make a new classifier. Open the Classifier palette and click on the New Classifier button to make one.
This will automatically open the "Edit Classifier" dialog.

The "Get From Selection" button will look at your selection and set some of the classifier parameters based on your selection. Remember that you can interact with the Image view and the Edit Classifier window at the same time - this makes life a whole lot easier.

For purposes of this demonstration we will use the "Intensity Mode" but just for the record there are two other modes namely HSI (Hue, saturation and intensity) and RGB (Red, Green and Blue intensity).
The HSI mode has three histograms that allow the selection of Hue, Saturation and Intensity.
The RGB mode also has three histograms that allow the selection of Red, Green and Blue Intensities.
Let's have a closer look at the histogram.

The Classifier will only include those intensities which fall between the red bars. In Volocity you can move the bars to adjust the range, this feature is pretty similar to Density Slicing in Openlab.

But the Classifier has lots of bonus material for ease of identification. Let's look at these with my sample with these features in mind.

Firstly there is a size threshold that will allow you to exclude large or small objects from the classification. When you click on the get from selection button the classifer will be updated with the selected information.

So this tool is pretty straight forward.

Shape recognition will allow you to select objects based on their shape. This tool will match objects to a series of models and exclude those that do not fall within the required parameters.
There are a lot of shapes to pick from, but you also have the option to create a custom shape, or better yet obtain the shape from the selection. Below I have obtained the shape from the selection I made in the Image view.

The option to get the shape "From Selection" is found in the drop down menu for Shape Recognition:

If the option is grayed out, make sure that you have selected an ROI in the image view, then click on the "Get from Selection" button on the Edit Classifier window, before returning to the "From Selection" option.

The "Fill Holes" option will fill holes in an object (i.e holes that are surrounded on all sides, within the object).

Of particular interest is the "Reduce Noise" feature. This will apply a 3x3x3 median filter to the selection.
Look at the before and after results below.



"Ignore Objects Touching the Edge of the Sample" will exclude objects that touch the edge of the sample in either X,Y or Z.

As you can see for the image below it has excluded an object at the sample's edge.

"Separate touching objects" will look at the voxel distribution of one object and determine if it is constituted of two or more objects on the basis of the other selection criteria.
See below - pay particular attention to the two objects to the left of the image which have been separated by using this tool:

At any time when you are using the Classifier, if you click on the "Apply" button this will apply the Classifier to your data set so that you can take a look at what it has found in the Image view.
If selected, the "Auto Apply" button will do this automatically each time you change one of the Classifier parameters.
When you are happy with the Classifier remember to give it a name and save it.
Remember you don't have to use all of the above criteria, think of them as tools to get the best "fit" to the objects that you want to identify and measure.

Always be mindful of what selection criteria you need to use !!

Your mission should you choose to accept it is to read the Volocity User Guide which contains further details on the use of Classification in Volocity.

Until next time.