A Registration Method Based on Contour Point Cloud for 3D Whole-Body PET and CT Images

Figure 5

An example of PET preprocessing results. (a) The source PET image (128 × 128). (b) is got by applying binary threshold segmentation on (a). (c) The interpolation result (512 × 512). (d) The median filtering result. (e) The final preprocessing result. (f) is got by applying a binary threshold segmentation on (e). (g) The feature image obtained.

(a)

(b)

(c)

(d)

(e)

(f)

(g)