MRI Partitioning

MRI Knowledge Hub

MRI Soft Visualization

The prototypes found by the connectionist scheme define partitions of pixels in the image. In order to enable construction of soft partitions so that alternative possibilities and inherent variabilities in the pixel values can be taken care of, a fuzzy membership function is defined for the partitions. Each intensity value is associated with multiple fuzzy memberships (GLS) using its distance from each prototype along the histogram as shown in Figure 1. If an intensity value is a prototype its membership in the partition will be obviously 1. As an example, consider the histogram of an MR image; the connectionist scheme finds six prototypes  spread over the intensity range. In this case each intensity value has six membership values depending upon its distance from different prototypes. The intensity values near  prototype have a high membership in the partition defined by P1 as compared to its membership value and belongingness to the partitions defined by the other prototypes. Using these membership functions a fuzzy segmentation of the MR image can be obtained.

Soft visualization Scheme

1.      Select interactively any two cluster-prototypes (figure 1, 2, 3, 4);

2.      Assign membership values using triangular function to each intensity value based on distance from prototype (Figure 4);

3.      Select different alpha values interactively for virtual segmentation;

4.      Segments displayed using pseudo-color;

5.      Change alpha values to generate soft boundaries with overlapping pixels for alternate interpretations. (Figure 5)

References
  1. A soft-segmentation visualization scheme for magnetic resonance images – ScienceDirect; Shashi Bhushan Mehta SantanuChaudhury AsokBhattacharyya AmarnathJena Volume 23, Issue 7, September 2005, Pages 817-828
Figure 1
MRI visualization through Soft Segmentation
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5