How to use the Segmentations

With regards to the naming structure, *S2-1.les: S2 means DCE-MRI sequence 2, lesion #1. Sometimes, there are multiple DCE-MRI sequences on TCIA data, and so the team used the sequence that corresponded to the one on which the radiologists annotated the truth.  Each of our tumor segmentation files is a binary file, consisting of the following format:

1. six uint16 values for the inclusive coordinates of the lesion’s cuboid , relative to the image:
y_start y_end
x_start x_end
z_start z_end

2. the N int8 on/off voxels (0 or 1) for the above specified cube, where N = (y_end y_start +1) * (x_end – x_start + 1) * (z_end – z_start + 1).

A voxel value of 1 denotes that it is part of the lesion, while a value of zero denotes it is not.

Please reference these data  extracted using version  V2010  of the UChicago MRI Quantitative Radiomics workstation.

The LES file is binary in format and contains the coordinates and shape mask volume of the lesion. It consists of six 2-byte short integer values which represent a 3×2 array of y,x,z start and end points. The remainder of the file contains the 1-byte mask values for the lesion voxels.

The following MATLAB statement reads a LES file:

[binles, lesRange] = loadlesion(targetfile);

where targetfile is a string of the file name path.

and where loadlesion.m is:

function [binles,rg]=loadlesion(targetfile)

    fid=fopen(targetfile,’r’);

    if fid ~=-1

        rg=fread(fid,[3 2],’uint16′)

        sz=rg(:,2)-rg(:,1)+1;

        binles=fread(fid,[prod(sz) 1],’int8′);

        binles=reshape(binles,sz’);

        fclose(fid);

        range=[rg(5)-rg(2)+1,rg(4)-rg(1)+1,rg(6)-rg(3)+1]

    else

        binles=[];

        rg=[];

    end

end

For example, if

rg =

122   150

327   379

71    84

then

yEnd = 150 and yStart = 122

xEnd = 379 and xStart = 327

zEnd = 84 and zStart = 71

TCIA maintains a list of publications that leverage TCIA data. If you have a manuscript you’d like to add please contact TCIA’s Helpdesk.