From Ohm

ITK Dicom Examples

In the previous sections we have seen that medical data can be pretty noisy. In the following we use the ITK filter pipeline to denoise a MRI angiography data set. We also use it to emphasize vessel structures.

Our ITK example pipeline contains the following filters:

  1. Read a DICOM series into a 3D image
  2. Mask low scalar values by using a threshold filter
  3. Denoise the angio data by using an anisotropic diffusion filter
  4. Emphasize the data by using the vesselness operator published by Frangi et al.
    1. “Multiscale vessel enhancement filtering”, Alejandro F. Frangi, Wiro J. Niessen, Koen L. Vincken, Max A. Viergever. Image Sciences Institute, Utrecht University Hospital.
    2. “3D Multi-scale line filter for segmentation and visualization of curvilinear structures in medical images”, Yoshinobu Sato, Shin Nakajima, Hideki Atsumi, Thomas Koller, Guido Gerig, Shigeyuki Yoshida, Ron Kikinis.
  5. Write the data as a new 3D image

Retrieved from

Page last modified on December 19, 2014, at 06:50 PM