Skip to main content
. 2017 Jun 21;4(2):027501. doi: 10.1117/1.JMI.4.2.027501

Algorithm 5.

Three level EGVD algorithm (THREE-LEVEL-EGVD).

Inputs:
 - Iseed is the binary seed mask. White regions are seed objects on a black background.
 - Igland_map is the grayscale gland image. Grayscale regions are glands on a black background.
 - Inuclei is the binary nuclei mask. White regions are nuclei on a black background.
Output:
 - Iglandresult is the binary gland mask. White regions depict gland on a black background.
Function and variable description:
 - DILATE(I,d) conducts “d” dilation operations on binary image I with a 3×3 pixels dilation window. Output image is also binary.
 - EGVD(Is,If) is the image segmentation algorithm described by Yu et al.50 where Is is the seed image and If is the grayscale image. It returns the binary segmentation result.
 - IaIb is a Boolean operation defining the pixel-wise OR operation between Ia and Ib.
Parameters:
 - Select number of dilation operations d=8. This value for d was optimized empirically.
1:  Procedure THREE-LEVEL-EGVD(Iseed, Igland_map, Inuclei)
2:    Inucleiborder=DILATE(Inuclei,8).    ⊳ Inucleiborder indicates nuclei border pixels in white.
3:    Put all white pixels indicated by Inucleiborder in Igland_map as black to compute Igland_temp.
4:    IEGVDoutput1=EGVD(Iseed,Igland_temp).
5:    Remove small objects and noise in IEGVDoutput1 and then save it to IEGVDoutput1denoised.
6:    Iseed2=IEGVDoutput1denoisedIseed.
7:    IEGVDoutput2=EGVD(Iseed2,Igland_map).
8:    Remove small objects and noise in IEGVDoutput2 and then save it to IEGVDoutput2denoised.
9:    Erode IEGVDoutput2denoised to compute Iseed3.
10:   IEGVDoutput3=EGVD(Iseed3,Igland_map).
11:   Remove small objects and noise in IEGVDoutput3 and then save it to Iglandresult.
12:   return binary gland mask Iglandresult.
13: end procedure