As I'm beginner in image processing, I am having difficulty in segmenting all the parts in DICOM image.

Currently, I'm applying watershed algorithm, but it segments only that part that has tumour.

I have to segment all parts in the image. Which algorithm will be helpful to perform this task?

The image below contains the tumour.

enter image description here

This image is the actual DICOM image

enter image description here


1 Answer 1


I looked at some picture from DICOM, and it seems that these images usually don't have many local minima, so I guess that's why watershed isn't optimal. However, it seems that in DICOM the color gradients are often strong, so I suggest to use techniques that works well with gradients:

  • Direct Gradient computations, either convolutional gradients or morphological gradients (selects shape of your different objects)

  • Normalized Cut on Similarity Graphs

If you want to know more about these you can read this post.


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .