ITK | Insight Toolkit -- Official Repository | Machine Learning library

I am trying to implement some kind of numpy.where() for my ITK images in C++. ITK's way seems to be with Functors. I am not very experienced with templates, so my whole approach might be flawed, but here is my go:

so I'd like to simulate CT images from ultrasound images using GAN and I am currently working on the data preparation.

By nature of the ultrasound these images are stored in a cone shaped kind of form:

But what I want to have is the image in the following form:

I belief it is easier to simulate the CT image that way.

I am using simple ITK. I guess this should be a common transformation. Is there maybe a filter from sITK that I am not aware of? Or is there an other simple way to do this transformation?

I have an array of values (concentration values), with each value taken at a different time point. I need to fit a gamma-variate curve (formula is in the picture below) to these values (i.e. find alpha and beta such that the curve best fits those points - all other variables are known.)

an example of the values i might get (crosses), and the curve I'd want to fit:

I have no idea how to do this. I tried to fit a simplified version of the formula, one that can be solved by using linear regression, by using matrices but I couldn't get it to work. That version of the formula (in which you only solve for one variable, alpha) looks like this:

simplified version, which would also be fine:

my attempt to solve fit the linear regression curve using matrices, using the vnl library (https://vxl.github.io/doc/release/core/vnl/html/index.html) looked like this. I was following this guy's tutorial (https://machinelearningmastery.com/solve-linear-regression-using-linear-algebra/)

I am trying to make tkinter UI that changes the image by control: loading folder/file, initiate, etc.

My code is at below and it does not load any image.

Thanks to lots of people's help, I made an tkinter UI that drag/drop the cards.

However, I met another big problem. I want to bind the specific cards using line, but the binding does not work correctly when the number of line is larger than 8.

I have a folder of 2D jpg images. I would like to convert that images to 3D image so that i can generate Digital Radiograph using ITK.

I know that it is easy to convert the 2D images to DICOM format and by using vtkDICOMImageReader, an then to give the output of vtkDICOMImageReader to the itk's DRR. But i don't want that because my 2D images have no information about series number, instance number, image position patient,etc.

Is there any way to give the folder of 2D jpg images to the input of ITK's DRR?

I wonder how to lift and lower a canvas object in Python Tkinter. I tried canvas.lower() but it's resulting in an error prompting

I am trying to deploy a bottle application using the vestacp panel. I keep getting a 500 error, and apparently this is due to incorrect server settings. I have three configuration files:

• wsgi.sh (for this file I did not find configuration information, apparently it is not correctly configured, for django by default)

I'm a wee bit stuck.

I have a 3D point cloud (an array of (n,3) vertices), in which I am trying to generate a 3D triangular mesh from. So far I have had no luck.

The format my data comes in:

• (x,y) values in regularly spaced (z) intervals. Think of the data as closed loop planar contours stored slice by slice in the z direction.
• The vertices in my data must be absolute positions for the mesh triangles (i.e. I don't want them to be smoothed out such that the volume begins to change shape, but linear interpolation between the layers is fine).

Illustration: