wchn/ctseg

Brain CT image segmentation, normalisation, skull-stripping and total brain/intracranial volume computation.

ctseg's Issues

Error using websave when running Docker in Windows

Firstly, thank you a lot for creating this useful tool for neuroimaging.

I'm using Docker to run CTseg on Windows.

Command use:
docker run --rm -it -v D:\Softwares\CTseg\data:/data ubuntu:ctseg function spm_CTseg '/data/CT.nii.gz'

Issue:

It seems 'prior_CTseg.mat' and 'mu_CTseg.nii' cannot be downloaded automatically. So my quick solution is I downloaded it manually and saved to my local machine. And now I want to copy it to Docker container and deprecate the 'websave' function.
But I hit some questions:

What location in Docker containter should it be copied to?
And where can I find spm_CTseg.m so that i can remove websave?
Or could you please mind suggesting a better solution?

Thank you a lot again!

Undefind function

Dear all:
Hi! I am currently using this tool in spm, but it is failed since there is no function 'spm_subFun' in the spm source code.
It shows:
Undefined function 'spm_subFun' corresponding to input parameter of type 'cell'

Could anyone help me with this?

Best,
Fiona

Error when building Dockerfile, step18

I have an error when building the docker image. System is an Ubuntu 20.04 server.
The error persists, also when I'm running the given docker command for segmentation.
Is there an easy solution or fix? Thanks for sharing!

Step 18/20 : RUN /opt/spm12/spm12 eval "spm_CTseg(1)"; exit 0
 ---> Running in c38a6bc18c43
SPM12, version 8168 (standalone)
MATLAB, version 9.11.0.1769968 (R2021b)
 ___  ____  __  __                                            
/ __)(  _ \(  \/  )                                           
\__ \ )___/ )    (   Statistical Parametric Mapping           
(___/(__)  (_/\/\_)  SPM12 - https://www.fil.ion.ucl.ac.uk/spm/

Downloading model files (first use only)... done.
Extracting model files  (first use only)... done.
Error using nifti (line 101)
Invalid syntax.
Error in nifti (line 101)
Error in spm_CTseg (line 138)
Error in spm_standalone (line 146)

Error using get_par>get_lkp (line 59) max(lkp) ~= K

This error occurred when getting to the GMM estimation part

------------------------------------------------------------------------
08-Oct-2019 16:23:00 - Running job #1
------------------------------------------------------------------------
08-Oct-2019 16:23:00 - Running '3D to 4D File Conversion'
08-Oct-2019 16:23:02 - Done    '3D to 4D File Conversion'
08-Oct-2019 16:23:02 - Done

Start making initial estimates of GMM parameters...

Error in get_par (line 24)
        [varargout{1:nargout}] = get_lkp(varargin{:});

Error in get_gmms (line 9)
parfor s=1:S0

Error in init_gmm (line 24)
[dat,model] = get_gmms(obs,model,dat,opt);

Error in init_all (line 32)
    [dat,model] = init_gmm(dat,model,opt);

Error in SegModel>SegModel_segment (line 187)
[dat,model,opt] = init_all(dat,opt);

Error in SegModel (line 40)
        [varargout{1:nargout}] = SegModel_segment(varargin{:});

Error in spm_segment_ct>segment_ct (line 366)
opt = SegModel('segment',dat,opt);

Error in spm_segment_ct (line 103)
opt = segment_ct(Nii,DirOut,PthToolboxes,VerboseSeg,CleanBrain,Write,Samp,MRF);

Error in batch_segment_CTs>predict_mask_CTseg (line 38)
    spm_segment_ct(Image, DirOut)

Error in batch_segment_CTs (line 21)
        pred_masks{i} = predict_mask_CTseg(test_CTs, test_CT_files(i).name);

With default values, the K = 6, and lkp has 14 elements, and the max (8) is not equal to 8:

lkp =

  Columns 1 through 13

     1     1     1     2     2     2     3     4     5     6     7     8     8

  Column 14

     8

This seems to correspond to this setting:

CTseg/spm_segment_ct.m

Line 354 in c6cd2da

map('CT') = [1 1 1 2 2 2 3 4 5 6 7 8 8 8];

But then the default K is 6, which of them should be changed? I changed this to 8 and made it work:

CTseg/toolboxes/segmentation-model/code/default_opt.m

Line 343 in c6cd2da

opt.template.K = 6;

Failed: Deformations

23-Jul-2022 22:25:03 - Running job #4

23-Jul-2022 22:25:03 - Running 'Deformations'
23-Jul-2022 22:25:03 - Failed 'Deformations'
错误使用 read_hdr (第 39 行)
Error reading header file "C:\Users\Dawn\Desktop\science\spm12-CTseg\y_*.nii".
In file "C:\Users\Dawn\Desktop\science\spm12-CTseg@nifti\private\read_hdr.m" (v7504), function "read_hdr" at line 39.
In file "C:\Users\Dawn\Desktop\science\spm12-CTseg@nifti\nifti.m" (v7758), function "nifti" at line 26.
In file "C:\Users\Dawn\Desktop\science\spm12-CTseg\spm_deformations.m" (v7700), function "get_def" at line 191.
In file "C:\Users\Dawn\Desktop\science\spm12-CTseg\spm_deformations.m" (v7700), function "get_job" at line 78.
In file "C:\Users\Dawn\Desktop\science\spm12-CTseg\spm_deformations.m" (v7700), function "get_comp" at line 48.
In file "C:\Users\Dawn\Desktop\science\spm12-CTseg\spm_deformations.m" (v7700), function "spm_deformations" at line 17.

The following modules did not run:
Failed: Deformations

错误使用 MATLABbatch system
Job execution failed. The full log of this run can be found in MATLAB command window, starting with the lines (look for the line showing
the exact #job as displayed in this error message)

how to solve this problem?

How to output only skull removal images?

Undefined function 'spm_CTseg'

I am using my forked repository of the original here : https://github.com/Alvi305/CTseg/tree/master.

The change is in the # Install SPM Standalone in /opt/spm12/ section where my Dockerfile uses SPM_REVISION r7771 and specific URL to download SPM since the original one gives me the following error:

` ERROR [4/5] RUN wget --no-check-certificate --progress=bar:force -P /opt https://www.fil.ion.ucl.ac.uk/spm/do 3.3s

[4/5] RUN wget --no-check-certificate --progress=bar:force -P /opt https://www.fil.ion.ucl.ac.uk/spm/download/restricted/utopia/dev/tbx/spm12_latest_tbx_Linux_R2019b.zip && unzip -q /opt/spm12_latest_tbx_Linux_R2019b.zip -d /opt && rm -f /opt/spm12_latest_tbx_Linux_R2019b.zip && /opt/spm12/spm12 function exit && chmod +x /opt/spm12/spm12:
0.434 --2023-12-31 05:18:15-- https://www.fil.ion.ucl.ac.uk/spm/download/restricted/utopia/dev/tbx/spm12_latest_tbx_Linux_R2019b.zip
0.454 Resolving www.fil.ion.ucl.ac.uk (www.fil.ion.ucl.ac.uk)... 193.62.66.18
1.900 Connecting to www.fil.ion.ucl.ac.uk (www.fil.ion.ucl.ac.uk)|193.62.66.18|:443... connected.
2.428 HTTP request sent, awaiting response... 404 Not Found
3.218 2023-12-31 05:18:18 ERROR 404: Not Found.
3.218

Dockerfile:36

35 | # Also, set +x on the entrypoint for non-root container invocations
36 | RUN wget --no-check-certificate --progress=bar:force -P /opt https://www.fil.ion.ucl.ac.uk/spm/download/restricted/utopia/dev/tbx/spm${SPM_VERSION}_${SPM_REVISION}_tbx_Linux_${MATLAB_VERSION}.zip
37 | && unzip -q /opt/spm${SPM_VERSION}${SPM_REVISION}tbx_Linux${MATLAB_VERSION}.zip -d /opt
38 | && rm -f /opt/spm${SPM_VERSION}${SPM_REVISION}tbx_Linux${MATLAB_VERSION}.zip
39 | && /opt/spm${SPM_VERSION}/spm${SPM_VERSION} function exit
40 | && chmod +x /opt/spm${SPM_VERSION}/spm${SPM_VERSION}
41 |

ERROR: failed to solve: process "/bin/sh -c wget --no-check-certificate --progress=bar:force -P /opt https://www.fil.ion.ucl.ac.uk/spm/download/restricted/utopia/dev/tbx/spm${SPM_VERSION}_${SPM_REVISION}_tbx_Linux_${MATLAB_VERSION}.zip && unzip -q /opt/spm${SPM_VERSION}${SPM_REVISION}tbx_Linux${MATLAB_VERSION}.zip -d /opt && rm -f /opt/spm${SPM_VERSION}${SPM_REVISION}tbx_Linux${MATLAB_VERSION}.zip && /opt/spm${SPM_VERSION}/spm${SPM_VERSION} function exit && chmod +x /opt/spm${SPM_VERSION}/spm${SPM_VERSION}" did not complete successfully: exit code: 8`

Using my Dockerfile does not give the above error. However, when I try to run the spm_CTseg function using the docker command: docker run --rm -it -v C:\Braillic\CTseg:/data ubuntu:ctseg function spm_CTseg '/data/MR_Gd.nii', I get this error:

C:\Braillic\CTseg>docker run --rm -it -v "C:\Braillic\CTseg":/data ubuntu:ctseg function spm_CTseg '/data/MR_Gd.nii'
SPM12, version 7771 (standalone)
MATLAB, version 9.7.0.1737446 (R2019b) Update 9

---

/ )( _ ( / )
_ \ )/ ) ( Statistical Parametric Mapping
(/(_) (_//_) SPM12 - https://www.fil.ion.ucl.ac.uk/spm/

Error using feval
Undefined function 'spm_CTseg' for input arguments of type 'char'.
Error in spm_standalone (line 132)

Could anyone kindly tell me how I can resolve the issue?

Thank you.

Error reading header file

Hello, I was trying to test on docker with:
docker run --rm -it -v dir_host:/scanner ubuntu:ctseg function spm_CTseg '/scanner/patient_001_S1.nii'
but I have the following error:
Error using read_hdr (line 39) Error reading header file "/scanner/patient_001_S1.nii". Error in read_hdr (line 39) Error in nifti (line 26) Error in spm_CTseg (line 138) Error in spm_standalone (line 132)
but I have no idea what is wrong with the header
the original file was in DICOM, and I converted it in nifti using MRIcroGL (https://www.nitrc.org/projects/mricrogl)
Thanks in advance

Some question about MATLAB Runtime R2020a for linux

1、There were some errors while I was processing my .nii image (536512512)
Failed 'CT Segmentation'
Error using spm_gmm_lib > loop (line 398)
At least one of Prop, LogProp or Dir must be provided

Error using spc_cli (line 141)
Job failed.
Error in spm_cli （line 141）
Error in spm_standalone （line 157）

2、The option "tc" can not set to False, but I just need the Skull-stripped image.

3、It took a lot of time (nearly 2 hours) to process an image (536512512).

Behavior of realign2mni?

Is it intentional that in the preprocessing, the realign2mni() is not actually applying the MNI alignment to the input data?

Both transformation matrices (origin reset and MNI alignment) are computed, but only the reset origin one is applied to the CT volume?

[Image,M] = reset_origin(Image);

Resetting origin... (reset_origin.m)   ... number of elements in = 1 
 --- Size of the img before reset = 512  512  137
 --- --- Size of the img after reset = 514  504  178

Elapsed time is 2.807755 seconds.

>> M{1}

ans =

    1.0000         0         0    0.2784
         0    1.0000         0   -0.4952
         0         0    1.0000  103.5000
         0         0         0    1.0000

[Image,M] = realign2mni(Image,M)

Realigning to MNI...   ... number of elements in = 1
 --- Size of the img before realign2mni = 514  504  178
 --- --- Size of the img after realign2mni = 514  504  178

Elapsed time is 36.333279 seconds.

>> M{1}

ans =

    0.9971    0.0747   -0.0152   17.9785
   -0.0762    0.9789   -0.1895    1.0920
    0.0007    0.1901    0.9818   92.2344
         0         0         0    1.0000

Image{1} = 

NIFTI object: 1-by-1
            dat: [514×504×178 file_array]
            mat: [4×4 double]
     mat_intent: 'Aligned'
           mat0: [4×4 double]
    mat0_intent: 'Aligned'
        descrip: 'CT'

Image{1}.mat =

   -0.4421   -0.0338    0.0007  104.7872
   -0.0331    0.4340    0.1901 -118.8067
    0.0067   -0.0840    0.9818  -56.7537
         0         0         0    1.0000

Image{1}.mat0 =

   -0.4434         0         0  114.1649
         0    0.4434         0 -111.9482
         0         0    1.0000  -89.5000
         0         0         0    1.0000

And similarly it seems that in the output folder, only the reset origin is saved to the header?

             Filemoddate: '04-Nov-2019 17:01:30'
                 Filesize: 184448224
                  Version: 'NIfTI1'
              Description: 'Bias Field Corrected Image'
                ImageSize: [514 504 178]
          PixelDimensions: [0.4434 0.4434 1]
                 Datatype: 'single'
             BitsPerPixel: 32
               SpaceUnits: 'Millimeter'
                TimeUnits: 'Second'
           AdditiveOffset: 0
    MultiplicativeScaling: 1
               TimeOffset: 0
                SliceCode: 'Unknown'
       FrequencyDimension: 0
           PhaseDimension: 0
         SpatialDimension: 0
    DisplayIntensityRange: [0 0]
            TransformName: 'Sform'
                Transform: [1×1 affine3d]
                  Qfactor: -1
                      raw: [1×1 struct]

Transform =

   -0.4434         0         0         0
    0.0000    0.4434         0         0
         0         0    1.0000         0
  114.0000 -112.0000   15.0000    1.0000

How to use CTseg in python?

CTseg is really a good project. Is it available in python? A python package may make the installation easy.

can I increase `sett.nworker`?

zoom=1/16: 12 x 16 x 17
sett.nworker = 0

When executing the program it shows sett.nworker = 0. Is there any way that I can set number of workers ? or is that default?
I have compile `SPM' with OpenMP support also

Error in running CT-SEG (Docker Image)

I have been facing a problem when I am ruining CT-SEG using Docker image: The 'temp' files are created, but process stops quickly and the segmentation files are not generated.

For exemple, when I enter:

docker run --rm -it -v dir_host:/data ubuntu:ctseg eval "spm_CTseg('/data/CT.nii',ct_result',true,true,true,true,1,2,0.0005)"

I realized that the process stops when it reaches 15.5GB of memory. Do you know if there is a way to limit or parallelize this processes within the Dockerfile , so it will not stop when it attempts to reaches the full RAM memory?

Missing probabalistic atlas

Hello, I tried to put the toolbox in spm12 and run it, but the probabilistic atlas seems to be missing, so that the code would ended in error. Did I miss anything, or is there a place/website that I should visit first?

Reference to non-existent field 'pth_gr'.

After getting the Start making initial estimates of GMM parameters... done! and Start making initial estimate of template...done!

This error comes

Error using segment_subject (line 449)
Reference to non-existent field 'pth_gr'.

Error in distribute_local (line 20)
    parfor (n=1:N, double(opt.client.workers))

Error in distribute (line 183)
        [varargout{2:numel(varargout)}] = distribute_local(opt, func, args, flags, access, N);

Error in SegModel>SegModel_segment (line 193)
[~,dat] = distribute(holly,'segment_subject','inplace',dat,'iter',model,opt);

Error in SegModel (line 40)
        [varargout{1:nargout}] = SegModel_segment(varargin{:});

Error in spm_segment_ct>segment_ct (line 366)
opt = SegModel('segment',dat,opt);

Error in spm_segment_ct (line 103)
opt = segment_ct(Nii,DirOut,PthToolboxes,VerboseSeg,CleanBrain,Write,Samp,MRF);

So I assume that somehow this check is skipped?

CTseg/toolboxes/segmentation-model/code/init_load_a_der.m

Line 9 in 2710377

if ~isfield(dat{s}.template,'pth_gr') && ~isfield(dat{s}.template,'pth_H')

So maybe the pth_H ,but not pth_gr is set?

And when I added "double-checking" of the variables defined within the structure, it worked:

CTseg/toolboxes/segmentation-model/code/segment_subject.m

Line 449 in 2710377

% Write derivatives to disk

% Double-checking that the paths actually are defined
    s = 1; % subscript used in "segmentation-model/code/init_load_a_der.m"
    if ~isfield(dat.template,'pth_gr')
        disp('... "pth_gr" was not defined, defining it again')
        dat.template.pth_gr = fullfile(opt.dir_a_der,['gr-' num2str(s) '.nii']);
    end    
        
    if ~isfield(dat.template,'pth_H')
        disp('... "pth_H" was not defined, defining it again')
        dat.template.pth_H  = fullfile(opt.dir_a_der,['H-' num2str(s) '.nii']);               
    end

and indeed only pth_gr was undefined and pth_H was defined for "initial estimate", and both were undefined for the "Analyzing and transferring files to the workers ...done." part

Start making initial estimate of template...done!
... "pth_gr" was not defined, defining it again
Analyzing and transferring files to the workers ...done.
... "pth_gr" was not defined, defining it again
... "pth_H" was not defined, defining it again

Error running the code.

What is wrong with padarray?

Segmentation obtained doesn't seem to be right

Hello, I applied the algorithm to a CT scan that I have, and the resulting segmentation in itself seems to be good, it looks like a nice brain, but it doesn't seem to fit my the CT scan that was in input. Indeed, first I have to translate the segmentation because it is far away from where the head is on the CT scan, and secondly the shapes and the size don't fit, it seems like it is showing the results from another head.
I used the line docker run --rm -it -v "/home/labeyrie/Téléchargements/CTseg":/data ubuntu:ctseg function spm_CTseg '/data/patient_001_S1.nii'
and here are the results, displaying the input CT scan:

wc version:

mwc version:

Am I doing something wrong?

Error building docker image: install_unix_legacy: not found

Trying to build docker image via docker build -t ubuntu:ctseg -f CTseg/Dockerfile .
Process failed due to install_unix_legacy: not found

System: macOS Monterey (12.5.1)
Architecture: M1

Error logs included:

Desktop % docker build -t ubuntu:ctseg -f CTseg/Dockerfile .
[+] Building 1.7s (10/17)                                                                                   
 => [internal] load build definition from Dockerfile                                                   0.0s
 => => transferring dockerfile: 1.91kB                                                                 0.0s
 => [internal] load .dockerignore                                                                      0.0s
 => => transferring context: 2B                                                                        0.0s
 => [internal] load metadata for docker.io/library/ubuntu:20.04                                        1.3s
 => [ 1/14] FROM docker.io/library/ubuntu:20.04@sha256:0e0402cd13f68137edb0266e1d2c682f217814420f2d43  0.0s
 => CACHED [ 2/14] RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get -y install      unzip  0.0s
 => CACHED [ 3/14] RUN mkdir /opt/mcr_install                                                          0.0s
 => CACHED [ 4/14] RUN mkdir /opt/mcr                                                                  0.0s
 => CACHED [ 5/14] RUN wget --progress=bar:force -P /opt/mcr_install https://ssd.mathworks.com/suppor  0.0s
 => CACHED [ 6/14] RUN unzip -q /opt/mcr_install/MATLAB_Runtime_R2021b_glnxa64.zip -d /opt/mcr_instal  0.0s
 => ERROR [ 7/14] RUN /opt/mcr_install/install -destinationFolder /opt/mcr -agreeToLicense yes -mode   0.3s
------                                                                                                      
 > [ 7/14] RUN /opt/mcr_install/install -destinationFolder /opt/mcr -agreeToLicense yes -mode silent:
#10 0.269 /opt/mcr_install/install: 1: exec: /opt/mcr_install/bin/unknown/install_unix_legacy: not found
------
executor failed running [/bin/sh -c /opt/mcr_install/install -destinationFolder /opt/mcr -agreeToLicense yes -mode silent]: exit code: 127

HOW to produce final coloful CTSeg?

I have reproduced code using docker,final dir_out including c[1-6],wc[1-6],mwc[1-6],y_~, I want to asked that is all the output imaging?but how i form the colorful CTSeg as you gaved the example. thanks.

Data share

Hi @brudfors , I wonder if the data can be made public,and if yes,i just need two examples.Thanks！

[Feature request] spm_CTseg_warp should be able to warp multiple images

Currently, spm_CTseg_warp only takes a single image. Most of the standard tools to apply deformation fields accept multiple images. Would it run faster if it worked on a list of image using the same deformation field?

Error running CTseg in Docker

1. correction in running the docker image should be to use ubuntu:ctseg instead of ubuntu/ctseg for the image name.

2. I had to wrap function spm_CTseg('/data/CT.nii') in double quotes to avoid getting the error:
   bash: syntax error near unexpected token ('`

3. With the above correction implemented, when I try to run CTseg I get the following errors:
   docker run --rm -it -v /data/CT.nii:/data/CT.nii ubuntu:ctseg function "spm_CTseg('/data/CT.nii')"

Error using spm_cli (line 56)
Cannot find module function spm_CTseg('/data/CT.nii').

Error in spm_cli (line 56)
Error in spm_standalone (line 157)

I tried another spm function (spm_get_space) and got the same error. However, spm_get_space works if a use eval instead of function
e.g.
docker run --rm -it -v /data/CT.nii:/data/CT.nii ubuntu:ctseg eval "spm_get_space('/data/CT.nii')"

but when I try it with CTSeg I get:

docker run --rm -it -v /data/CT.nii:/data/CT.nii ubuntu:ctseg eval "spm_CTSeg('/data/CT.nii')"

Error using eval
Undefined function 'spm_CTSeg' for input arguments of type 'char'.
Error in spm_standalone (line 146)

Any thoughts?

Reference to non-existent field 'dir_model'.

You seem to be missing a field dir_model (Create directory that will store all that is model related) from your opt structure, when running with two input arguments spm_segment_ct(Image, DirOut):

Image = fullfile(path_base, file_to_analyze);
DirOut = fullfile(path_base, 'output');

This come out as the error:

Reference to non-existent field 'dir_model'.

Error in init_uniform_template (line 15)
dir_model = opt.dir_model;

Error in load_model (line 34)
        model{s} = init_uniform_template(dat,opt);

Error in init_all (line 43)
    [dat,model,opt] = load_model(dat,opt); % Get model parameters (model)

Error in SegModel>SegModel_segment (line 187)
[dat,model,opt] = init_all(dat,opt);

Error in SegModel (line 40)
        [varargout{1:nargout}] = SegModel_segment(varargin{:});

Error in spm_segment_ct>segment_ct (line 366)
opt = SegModel('segment',dat,opt);

Error in spm_segment_ct (line 103)
opt = segment_ct(Nii,DirOut,PthToolboxes,VerboseSeg,CleanBrain,Write,Samp,MRF);

So the dir_model is not saved when calling init_uniform_template here:

CTseg/toolboxes/segmentation-model/code/load_model.m

Line 34 in c6cd2da

model{s} = init_uniform_template(dat,opt);

Which seemed to be due to this flag being false

CTseg/spm_segment_ct.m

Line 300 in c6cd2da

opt.template.do = false;