# How do I use Discrete Wavelet Transform for feature extraction on MRI DICOM image? [closed]

As an example, I would like to extract different features from the following image:

I could do this in 3D slicer but since I could code a bit in Mathematica (I just moved to Mathematica 11 from 9 recently), I would love to use Mathematica for all my the feature extraction processes.

1. I was wondering how I could use the discrete wavelet transform to extract image features (MEAN INTENSITY, PIXEL ORIENTATION, CONTRAST, AREA and SHAPE INDEX).
2. I want to represent the numerical data describing the extracted features in the MS Excel format.
3. I want to find the equation of best fit for the Excel data and probably introduce a manipulate function where I could easily change my equation of best fit until it gives good results.

Even if some of these are not possible, I would still be glad to have your comments in this regard. Thanks guys!

## closed as too broad by Niki Estner, Szabolcs, José Antonio Díaz Navas, Kuba♦Feb 18 '18 at 11:21

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

• Thanks for the edits, @C. E. – Dean Feb 18 '18 at 13:10
• Are there particular features you wish to extract? You can get pretty pictures, i.stack.imgur.com/cLb8i.png, but I doubt whether they are at all useful. If you focus the question on a particular feature, you're more likely to get help. – Michael E2 Feb 18 '18 at 14:41
• Thanks a lot @Michael E2, the features I wish to extract are: Intensity, Texture (as related to image contrast) and shape. However, I am most interested in the Intensity! – Dean Feb 18 '18 at 19:00
• What does it mean to "extract shape"? I think that the question is still much too broad. It would be better if you could explain what you want to do in mathematical terms, or at least provide concrete examples. – Szabolcs Feb 19 '18 at 14:11
• Thanks @Szabolcs, I have edited my question to cover specific image features-mean intensity, pixel orientation, contrast, area (shape) and shape index. Thank you! – Dean Feb 21 '18 at 0:09