search

mattmacy / vnet.pytorch

A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
https://mattmacy.github.io/vnet.pytorch
BSD 3-Clause "New" or "Revised" License
688 stars 201 forks source link

Preprocess for LUNA16 dataset? #5

Closed lilhope closed 7 years ago

lilhope commented 7 years ago

Hi, I'm a quite a newer to LUNA16 dataset,and I seems your code need some preprocess for LANA16 dataset, I can see you list some functions in lana16.py,but I have no idea how to use it(e.g.fisrt to do so?and next what?),could you give me some simple process about it? Thanks a lot!

lilhope commented 7 years ago

especially, I wonder what's the X_MAX,Y_MAX,Z_MAXmean?

mattmacy commented 7 years ago

X_MAX, Y_MAX, Z_MAX are variables to specify the maximum dimensions when trying to normalize all of the scans. vox_spacing is the voxel spacing in millimeters. I don't have the sample code where I am now, but something like

dmean, dstddev = normalize_lung_CT(src="luna_dir", dst="luna_resize_dir", X_MAX=128, Y_MAX=160, Z_MAX=128, vox_spacing=2)

You'll have to look at the actual dimensions to determine what sane values are.

tomclavmaster commented 6 years ago

Hi @lilhope, I'm wondering what values for X_MAX, Y_MAX, and Z_MAX you ended up using. @mattmacy Do you have the sample code so you can take a look at the values you used for preprocessing? I'm struggling with this step.