Liver Tumor Segmentation from MR Images Using 3D Fast Marching Algorithm and Single Hidden Layer Feedforward Neural Network

Figure 2

The intermediate results of the proposed scheme. (a) A slice of the original 3D image. (b) A slice of the 3D region of interest containing the liver tumor which was extracted from the original 3D MR image. (c) The edge image generated by applying the gradient magnitude filter. (d) The labeled regions generated by the fast marching algorithm and thresholding filter. (e) Unlabeled voxels were classified by using the SLFN. (f) The segmented liver tumor. (g) A comparison between the computerized liver tumor segmentation (black contour) and the “ground-truth” manual liver tumor segmentation (white contour).

(a)

(b)

(c)

(d)

(e)

(f)

(g)