I have a dataset which consists of computed tomography images (CT scans) of parts that contain pores and cracks. The sets for each part are of about 1100 * 1100 * 3000-ish resolution. Currently, I use a method of thresholding and calculations to find the volumes and locations of these defects, and I would like to reproduce those results with a machine learning approach.

What are the methods known for this type of problem, and what are your general recommendations?


  • Here is the current method I am using : Current approach
  • And this is what I aim to achieve : Desired outcome
  • $\begingroup$ Hello. To give a more concrete idea of your problem, you could post an example of an image that you have and what you want to find in the image. $\endgroup$
    – nbro
    Jul 1 at 11:05
  • $\begingroup$ I will edit post to include more details. $\endgroup$
    – winsid
    Jul 1 at 11:11
  • $\begingroup$ I added images from the data set and outputs. $\endgroup$
    – winsid
    Jul 1 at 11:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.