Look into pydicom to load your images. Then, you will need to either manually or - more difficult - automatically segment the breast(s), excluding the pectoralis muscles and adjacent air. The data in your images should be Hounsfield units, which are calibrated to quantitatively measure density (0 is water, -1000 is air at the scanner, everything positive is more dense than water). There are many published ranges you could use to start with to differentiate fat from non-fat tissue in your area of interest. Scikit-Image will likely be most helpful in the segmentation phase. There are several thresholding algorithms which may be of use also, if a simple threshold isn't ideal. Please note that differentiating fat from other soft tissue is relatively easy; differentiating glandular from 'other soft tissue' is not as they will share the same density. If this is a key part of the project, simple density-based thresholding will not be sufficient. On Wed, Nov 14, 2018 at 12:45 PM <deborah.akuoko@postgrad.manchester.ac.uk> wrote:

I have over 500 images from cancer imaging archive. All these are CT images of the chest area (breast). I want to use scikit image to determine which part of the CT represent Fatty tissue and which part represents glands tissue. This might be based of gray scale levels or density I’m not sure.

For instance I want to be able to label image 01 as : 10% fatty tissue 80% fibro glandular tissue and 10% other soft tissue

I have never used scikit image for anything but I have some python programming experience

I really need a good beginner explanation to get this done using sci kit image. I have seen the documentation but it’s too general. I need something specific for what I want to accomplish as stated above.

Please assist if possible. _______________________________________________ scikit-image mailing list -- scikit-image@python.org To unsubscribe send an email to scikit-image-leave@python.org