CerebNet does not segment part of the cerebellum #748
Description
IMPORTANT: Please make sure to fill out the information about your environment (see below). This is often critical information we need to help you.
Question/Support Request
A clear and concise description of a question you may have or a problem for which you would like to request support.
CerebNet fails to segment parts of the cerebellum.
Screenshots / Log files
Screenshot of the CerebNet segmentation overlaid on aparc.DKTatlas+aseg.deep.mgz and orig_nu.mgz.
The whole cerebellum is nicely covered in aparc.DKTatlas+aseg.deep.mgz (here shown in turquoise ), while partly missing in the Cerebnet segmentation,
I have seen this in several subjects.
No error messages. The mask is okay and covers the whole cerebellum
cat deep-seg.log :
=========================================================
Start of the log for a new run_fastsurfer.sh invocation
=========================================================
Version: 2.4.2+7e53343
Mon Nov 24 11:25:01 CET 2025
Log file for FastSurfer pipeline, run_fastsurfer.sh and segmentation(s)
WARNING: The --parallel flag is obsolete and will be removed in FastSurfer 3.
Hemispheres are now automatically processed in parallel, if threads for surface
reconstruction are more than 1 (defined via --threads 2 or --threads_surf 2)!
IMPORTANT NOTE: The threads behavior has also changed, --threads used to define the
number of threads per hemisphere, it now defines the number of threads in total!
python3.10 -s /fastsurfer/FastSurferCNN/run_prediction.py --t1 /data/001.mgz --asegdkt_segfile /output/sub-via434-ses02/mri/aparc.DKTatlas+aseg.deep.mgz --conformed_name /output/sub-via434-ses02/mri/orig.mgz --brainmask_name /output/sub-via434-ses02/mri/mask.mgz --aseg_name /output/sub-via434-ses02/mri/aseg.auto_noCCseg.mgz --sid sub-via434-ses02 --seg_log /output/sub-via434-ses02/scripts/deep-seg.log --vox_size min --batch_size 1 --viewagg_device auto --device auto --threads 2 --sd /output
[INFO: run_prediction.py: 647]: Checking or downloading default checkpoints ...
[INFO: common.py: 820]: Single subject with absolute file path for input.
[INFO: common.py: 878]: Analyzing single subject /data/001.mgz
[INFO: common.py: 979]: Output will be stored in Subjects Directory: /output
[INFO: common.py: 106]: Using device: cuda
[INFO: common.py: 106]: Using viewagg_device: cuda
[INFO: run_prediction.py: 245]: Running view aggregation on cuda
[INFO: inference.py: 200]: Loading checkpoint /fastsurfer/checkpoints/aparc_vinn_coronal_v2.0.0.pkl
[INFO: inference.py: 200]: Loading checkpoint /fastsurfer/checkpoints/aparc_vinn_sagittal_v2.0.0.pkl
[INFO: inference.py: 200]: Loading checkpoint /fastsurfer/checkpoints/aparc_vinn_axial_v2.0.0.pkl
[INFO: run_prediction.py: 324]: Successfully loaded image from /data/001.mgz.
[INFO: run_prediction.py: 441]: Output image directory /output/sub-via434-ses02/mri/orig does not exist. Creating it now...
[INFO: run_prediction.py: 454]: Successfully saved image as /output/sub-via434-ses02/mri/orig/001.mgz.
[INFO: conform.py: 823]: The input image is not conformed.
[INFO: conform.py: 826]: A min-conformedconformed image must satisfy the following criteria:
[INFO: conform.py: 828]: - Number of Dimensions 3 : True
[INFO: conform.py: 828]: - Dimensions 289x289x289 : BUT image dimensions (192, 288, 288)
[INFO: conform.py: 828]: - Voxel Size 0.9x0.9x0.9 : BUT image 0.90000004x0.90277785x0.90277773
[INFO: conform.py: 828]: - Orientation LIA : BUT strict: [[-0.9 -0.06 0.01] [-0.06 0.9 0. ] [ 0.01 0. 0.9 ]]
[INFO: conform.py: 828]: - Dtype uint8 : BUT dtype >f4
[INFO: run_prediction.py: 337]: Conforming image
[INFO: run_prediction.py: 454]: Successfully saved image as /output/sub-via434-ses02/mri/orig.mgz.
[INFO: run_prediction.py: 400]: Run coronal prediction
[INFO: dataset.py: 78]: Loading Coronal with input voxelsize (0.9, 0.9)
[INFO: inference.py: 408]: Inference on 289 batches for coronal successful
[INFO: inference.py: 469]: Coronal inference on /data/001.mgz finished in 6.0258 seconds
[INFO: run_prediction.py: 400]: Run sagittal prediction
[INFO: dataset.py: 69]: Loading Sagittal with input voxelsize (0.9, 0.9)
[INFO: inference.py: 408]: Inference on 289 batches for sagittal successful
[INFO: inference.py: 469]: Sagittal inference on /data/001.mgz finished in 6.0469 seconds
[INFO: run_prediction.py: 400]: Run axial prediction
[INFO: dataset.py: 74]: Loading Axial with input voxelsize (0.9, 0.9)
[INFO: inference.py: 408]: Inference on 289 batches for axial successful
[INFO: inference.py: 469]: Axial inference on /data/001.mgz finished in 6.1110 seconds
[INFO: run_prediction.py: 454]: Successfully saved image as /output/sub-via434-ses02/mri/aparc.DKTatlas+aseg.deep.mgz.
[INFO: run_prediction.py: 724]: Creating brainmask based on segmentation...
[INFO: run_prediction.py: 454]: Successfully saved image as /output/sub-via434-ses02/mri/mask.mgz.
[INFO: run_prediction.py: 743]: Creating aseg based on segmentation...
[INFO: run_prediction.py: 454]: Successfully saved image as /output/sub-via434-ses02/mri/aseg.auto_noCCseg.mgz.
[INFO: run_prediction.py: 762]: Running volume-based QC check on segmentation...
INFO: Running N4 bias-field correction...
python3.10 -s /fastsurfer/recon_surf/N4_bias_correct.py --in /output/sub-via434-ses02/mri/orig.mgz --rescale /output/sub-via434-ses02/mri/orig_nu.mgz --aseg /output/sub-via434-ses02/mri/aseg.auto_noCCseg.mgz --threads 2
N4 Bias Correction Parameters:
- verbosity: -1
- input volume: /output/sub-via434-ses02/mri/orig.mgz
- output volume: do not save
- rescaled volume: /output/sub-via434-ses02/mri/orig_nu.mgz
- mask: default (>0)
- aseg: /output/sub-via434-ses02/mri/aseg.auto_noCCseg.mgz
- shrink factor: 4
- number fitting levels: 4
- number iterations: 50
- convergence threshold: 0.0
- threads: 2
read MGZ (FreeSurfer) image via nibabel...
executing N4 correction ...
- mask: ones (default)
normalize WM to 105.0 (find WM from aseg)
read MGZ (FreeSurfer) image via nibabel...
- source white matter intensity: 104.14
- m: 0.9795
converting rescaled to UCHAR
writing PosixPath: /output/sub-via434-ses02/mri/orig_nu.mgz
write MGZ (FreeSurfer) image via nibabel...
python3.10 -s /fastsurfer/FastSurferCNN/segstats.py --segfile /output/sub-via434-ses02/mri/aparc.DKTatlas+aseg.deep.mgz --segstatsfile /output/sub-via434-ses02/stats/aseg+DKT.stats --normfile /output/sub-via434-ses02/mri/orig_nu.mgz --threads 2 --empty --excludeid 0 --sd /output --sid sub-via434-ses02 --ids 2 4 5 7 8 10 11 12 13 14 15 16 17 18 24 26 28 31 41 43 44 46 47 49 50 51 52 53 54 58 60 63 77 251 252 253 254 255 1002 1003 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1034 1035 2002 2003 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2034 2035 --lut /fastsurfer/FastSurferCNN/config/FreeSurferColorLUT.txt measures --compute Mask(/output/sub-via434-ses02/mri/mask.mgz) BrainSeg BrainSegNotVent SupraTentorial SupraTentorialNotVent SubCortGray rhCerebralWhiteMatter lhCerebralWhiteMatter CerebralWhiteMatter
None of the labels [251, 252, 253, 254, 255] for merged label 10007 exist in the segmentation.
Partial volume stats for 100 labels written to /output/sub-via434-ses02/stats/aseg+DKT.stats.
Calculation took 8.79 seconds using up to 2 threads.
python3.10 -s /fastsurfer/CerebNet/run_prediction.py --t1 /data/001.mgz --asegdkt_segfile /output/sub-via434-ses02/mri/aparc.DKTatlas+aseg.deep.mgz --conformed_name /output/sub-via434-ses02/mri/orig.mgz --cereb_segfile /output/sub-via434-ses02/mri/cerebellum.CerebNet.nii.gz --seg_log /output/sub-via434-ses02/scripts/deep-seg.log --async_io --batch_size 1 --viewagg_device auto --device auto --threads 2 --norm_name /output/sub-via434-ses02/mri/orig_nu.mgz --cereb_statsfile /output/sub-via434-ses02/stats/cerebellum.CerebNet.stats --sd /output
[INFO: run_prediction.py: 154]: Checking or downloading default checkpoints ...
[INFO: common.py: 820]: Single subject with absolute file path for input.
[INFO: common.py: 878]: Analyzing single subject /data/001.mgz
[INFO: common.py: 106]: Using device: cuda
[INFO: common.py: 106]: Using viewagg_device: cuda
[INFO: inference.py: 434]: 25-11-24_11:28:39
[INFO: conform.py: 823]: The input image is not conformed.
[INFO: conform.py: 826]: A conformedconformed image must satisfy the following criteria:
[INFO: conform.py: 828]: - Number of Dimensions 3 : True
[INFO: conform.py: 828]: - Dimensions 256x256x256 : BUT image dimensions (289, 289, 289)
[INFO: conform.py: 828]: - Voxel Size 1.0x1.0x1.0 : BUT image 0.9x0.9x0.9
[INFO: conform.py: 828]: - Orientation LIA : True
[INFO: conform.py: 828]: - Dtype uint8 : True
[INFO: data_utils.py: 101]: Conforming image to UCHAR, RAS orientation, and minimum isotropic voxels
[INFO: conform.py: 823]: The input image is not conformed.
[INFO: conform.py: 826]: A conformedconformed image must satisfy the following criteria:
[INFO: conform.py: 828]: - Number of Dimensions 3 : True
[INFO: conform.py: 828]: - Dimensions 256x256x256 : BUT image dimensions (192, 288, 288)
[INFO: conform.py: 828]: - Voxel Size 1.0x1.0x1.0 : BUT image 0.90000004x0.90277785x0.90277773
[INFO: conform.py: 828]: - Orientation LIA : BUT strict: [[-0.9 -0.06 0.01] [-0.06 0.9 0. ] [ 0.01 0. 0.9 ]]
[INFO: conform.py: 828]: - Dtype uint8 : BUT dtype >f4
[INFO: data_utils.py: 101]: Conforming image to UCHAR, RAS orientation, and minimum isotropic voxels
[INFO: dataset.py: 260]: The conformed image and the segmentation do not share the same affine. The cerebellum mask is being resampled to localize it in the conformed image.
[INFO: inference.py: 357]: Saving CerebNet cerebellum segmentation at /output/sub-via434-ses02/mri/cerebellum.CerebNet.nii.gz
[INFO: inference.py: 512]: Subject 1/1 with id '001.mgz' processed in 15.90 sec.
python3.10 -s /fastsurfer/HypVINN/run_prediction.py --sd /output --sid sub-via434-ses02 --reg_mode coreg --threads 2 --async_io --batch_size 1 --seg_log /output/sub-via434-ses02/scripts/deep-seg.log --device auto --viewagg_device auto --t1 /output/sub-via434-ses02/mri/orig_nu.mgz
[INFO: mode_config.py: 49]: Setting up input mode...
[INFO: run_prediction.py: 437]: Checking or downloading default checkpoints ...
[INFO: run_prediction.py: 282]: Running HypVINN segmentation pipeline on subject sub-via434-ses02
[INFO: run_prediction.py: 285]: Output will be stored in: /output/sub-via434-ses02
[INFO: run_prediction.py: 286]: T1 image input /output/sub-via434-ses02/mri/orig_nu.mgz
[INFO: run_prediction.py: 287]: T2 image input None
[INFO: run_prediction.py: 306]: Setting up HypVINN run
[INFO: run_prediction.py: 311]: axial model configuration from /fastsurfer/HypVINN/config/HypVINN_axial_v1.1.0.yaml
[INFO: run_prediction.py: 311]: coronal model configuration from /fastsurfer/HypVINN/config/HypVINN_coronal_v1.1.0.yaml
[INFO: run_prediction.py: 311]: sagittal model configuration from /fastsurfer/HypVINN/config/HypVINN_sagittal_v1.1.0.yaml
[INFO: run_prediction.py: 505]: Loading T1 image from : /output/sub-via434-ses02/mri/orig_nu.mgz
[INFO: common.py: 106]: Using device: cuda
[INFO: common.py: 106]: Using viewagg_device: cuda
[INFO: inference.py: 109]: Running view aggregation on cuda
[INFO: run_prediction.py: 340]: ------------------------------------------------------------------------------------------------------------------------
[INFO: run_prediction.py: 341]: Evaluating hypothalamus model on sub-via434-ses02
[INFO: run_prediction.py: 350]: Scale factor: (0.9, 0.9, 0.9)
[INFO: run_prediction.py: 609]: Evaluating axial model, cpkt :/fastsurfer/checkpoints/HypVINN_axial_v1.1.0.pkl
[INFO: inference.py: 183]: Loading checkpoint /fastsurfer/checkpoints/HypVINN_axial_v1.1.0.pkl
[INFO: dataset.py: 166]: Loading t1 axial with input voxelsize (0.9, 0.9)
[INFO: dataset.py: 114]: Successfully loaded Image from sub-via434-ses02 for axial model
[INFO: dataset.py: 126]: For inference T1 block weight was set to: 1.0 and the T2 block was set to: 0.0
[INFO: inference.py: 345]: ---> axial Model Testing Done.
[INFO: inference.py: 404]: axial Inference on sub-via434-ses02 finished in 9.1932 seconds
[INFO: run_prediction.py: 609]: Evaluating coronal model, cpkt :/fastsurfer/checkpoints/HypVINN_coronal_v1.1.0.pkl
[INFO: inference.py: 183]: Loading checkpoint /fastsurfer/checkpoints/HypVINN_coronal_v1.1.0.pkl
[INFO: dataset.py: 160]: Loading t1 coronal with input voxelsize (0.9, 0.9)
[INFO: dataset.py: 114]: Successfully loaded Image from sub-via434-ses02 for coronal model
[INFO: dataset.py: 126]: For inference T1 block weight was set to: 1.0 and the T2 block was set to: 0.0
[INFO: inference.py: 345]: ---> coronal Model Testing Done.
[INFO: inference.py: 404]: coronal Inference on sub-via434-ses02 finished in 8.7654 seconds
[INFO: run_prediction.py: 609]: Evaluating sagittal model, cpkt :/fastsurfer/checkpoints/HypVINN_sagittal_v1.1.0.pkl
[INFO: inference.py: 183]: Loading checkpoint /fastsurfer/checkpoints/HypVINN_sagittal_v1.1.0.pkl
[INFO: dataset.py: 153]: Loading t1 sagittal with input voxelsize (0.9, 0.9)
[INFO: dataset.py: 114]: Successfully loaded Image from sub-via434-ses02 for sagittal model
[INFO: dataset.py: 126]: For inference T1 block weight was set to: 1.0 and the T2 block was set to: 0.0
[INFO: inference.py: 345]: ---> sagittal Model Testing Done.
[INFO: inference.py: 404]: sagittal Inference on sub-via434-ses02 finished in 10.6013 seconds
[INFO: run_prediction.py: 363]: Model prediction finished in 31.1269 seconds
[INFO: run_prediction.py: 364]: Saving results in /output/sub-via434-ses02
[INFO: img_processing_utils.py: 230]: Check Optic Labels
[INFO: img_processing_utils.py: 97]: Orig data orientation : ('L', 'I', 'A')
[INFO: img_processing_utils.py: 101]: HypVINN Mask orientation: ('R', 'A', 'S')
[INFO: img_processing_utils.py: 103]: HypVINN Mask after re-orientation: ('L', 'I', 'A')
[INFO: img_processing_utils.py: 109]: HypVINN Prediction orientation: ('R', 'A', 'S')
[INFO: img_processing_utils.py: 111]: HypVINN Prediction after re-orientation: ('L', 'I', 'A')
[INFO: run_prediction.py: 381]: Prediction successfully saved in 4.496723175048828 seconds.
[INFO: run_prediction.py: 395]: Computing stats
[INFO: brainvolstats.py: 1415]: Replacing segmentation volume to compute volume measures from with the segmentation file /output/sub-via434-ses02/mri/hypothalamus.HypVINN.nii.gz.
[INFO: run_prediction.py: 405]: Processing segmentation finished in 37.4735 seconds.
[INFO: run_prediction.py: 416]: Processing whole pipeline finished in 37.5063 seconds.
(base)
Please provide error messages (can be a screenshot), stack traces, log files (specifically $SUBJECTS_DIR/$SUBJECT_ID/scripts/deep-seg.log and $SUBJECTS_DIR/$SUBJECT_ID/scripts/recon-surf.log) and any snippets useful in describing your problem here
Environment
- FastSurfer Version: please run
run_fastsurfer.sh --version alland copy/attach the resulting output - Installation type: official docker/custom docker/singularity/native
- FreeSurfer Version: 7.4.1/7.3.2
- OS: Windows/Linux/macOS
- GPU: none/RTX 2080/...
Singularity sandbox (singularity build --sandbox fastsurfer-sandbox-v2.4.2 docker://deepmi/fastsurfer:latest)
RNAME="Red Hat Enterprise Linux"
VERSION="9.6 (Plow)"
ID="rhel"
ID_LIKE="fedora"
VERSION_ID="9.6"
PLATFORM_ID="platform:el9"
PRETTY_NAME="Red Hat Enterprise Linux 9.6 (Plow)"
GPUs. e.g. nvidia_geforce_rtx_3090
2.4.2+7e53343 (stable)
==========
git status:
==========
## stable...upstream/stable
Build.log
==========
checkpoints:
==========
ab1339037fe72a96474918e3e43230ea checkpoints/HypVINN_axial_v1.1.0.pkl
7d400765666150f14389764703f837f2 checkpoints/HypVINN_sagittal_v1.1.0.pkl
fa699af3d60ca9ee06950e62ed04c288 checkpoints/aparc_vinn_coronal_v2.0.0.pkl
840f87fa05cffdbf8b9d7e385acc76be checkpoints/CerebNet_coronal_v1.0.0.pkl
f28ab87df75492ad91f9ff5e49a2583c checkpoints/aparc_vinn_sagittal_v2.0.0.pkl
55e30ae9c3e888bd3be3fccfbc7fbe04 checkpoints/HypVINN_coronal_v1.1.0.pkl
eb836ed90893dc32950e83c8b060a360 checkpoints/CerebNet_sagittal_v1.0.0.pkl
b62511c32e7ce059a68bb4e2728d5546 checkpoints/CerebNet_axial_v1.0.0.pkl
f16e78dd069eed2ec659674e0fdb697b checkpoints/aparc_vinn_axial_v2.0.0.pkl
==========
python packages:
==========
Package Version Location Installer
------------------------ ------------ ---------------------------------- ---------
absl-py 2.1.0 /venv/lib/python3.10/site-packages conda
Brotli 1.1.0 /venv/lib/python3.10/site-packages conda
cached-property 1.5.2 /venv/lib/python3.10/site-packages conda
certifi 2024.12.14 /venv/lib/python3.10/site-packages conda
cffi 1.17.1 /venv/lib/python3.10/site-packages conda
charset-normalizer 3.4.1 /venv/lib/python3.10/site-packages conda
click 8.1.8 /venv/lib/python3.10/site-packages pip
colorama 0.4.6 /venv/lib/python3.10/site-packages conda
contourpy 1.3.1 /venv/lib/python3.10/site-packages conda
cycler 0.12.1 /venv/lib/python3.10/site-packages conda
Deprecated 1.2.18 /venv/lib/python3.10/site-packages pip
filelock 3.17.0 /venv/lib/python3.10/site-packages pip
fonttools 4.56.0 /venv/lib/python3.10/site-packages conda
fsspec 2025.2.0 /venv/lib/python3.10/site-packages pip
grpcio 1.67.1 /venv/lib/python3.10/site-packages conda
h2 4.2.0 /venv/lib/python3.10/site-packages conda
h5py 3.12.1 /venv/lib/python3.10/site-packages conda
hpack 4.1.0 /venv/lib/python3.10/site-packages conda
humanize 4.11.0 /venv/lib/python3.10/site-packages pip
hyperframe 6.1.0 /venv/lib/python3.10/site-packages conda
idna 3.10 /venv/lib/python3.10/site-packages conda
imagecodecs 2024.12.30 /venv/lib/python3.10/site-packages conda
imageio 2.37.0 /venv/lib/python3.10/site-packages conda
importlib_metadata 8.6.1 /venv/lib/python3.10/site-packages conda
importlib_resources 6.5.2 /venv/lib/python3.10/site-packages conda
Jinja2 3.1.5 /venv/lib/python3.10/site-packages pip
joblib 1.4.2 /venv/lib/python3.10/site-packages conda
kiwisolver 1.4.7 /venv/lib/python3.10/site-packages conda
lapy 1.2.0 /venv/lib/python3.10/site-packages conda
lazy_loader 0.4 /venv/lib/python3.10/site-packages conda
Markdown 3.6 /venv/lib/python3.10/site-packages conda
markdown-it-py 3.0.0 /venv/lib/python3.10/site-packages pip
MarkupSafe 3.0.2 /venv/lib/python3.10/site-packages conda
matplotlib 3.10.0 /venv/lib/python3.10/site-packages conda
mdurl 0.1.2 /venv/lib/python3.10/site-packages pip
mpmath 1.3.0 /venv/lib/python3.10/site-packages pip
munkres 1.1.4 /venv/lib/python3.10/site-packages
narwhals 1.25.2 /venv/lib/python3.10/site-packages conda
networkx 3.4.2 /venv/lib/python3.10/site-packages conda
nibabel 5.3.2 /venv/lib/python3.10/site-packages conda
numpy 1.26.4 /venv/lib/python3.10/site-packages conda
nvidia-cublas-cu12 12.6.4.1 /venv/lib/python3.10/site-packages pip
nvidia-cuda-cupti-cu12 12.6.80 /venv/lib/python3.10/site-packages pip
nvidia-cuda-nvrtc-cu12 12.6.77 /venv/lib/python3.10/site-packages pip
nvidia-cuda-runtime-cu12 12.6.77 /venv/lib/python3.10/site-packages pip
nvidia-cudnn-cu12 9.5.1.17 /venv/lib/python3.10/site-packages pip
nvidia-cufft-cu12 11.3.0.4 /venv/lib/python3.10/site-packages pip
nvidia-curand-cu12 10.3.7.77 /venv/lib/python3.10/site-packages pip
nvidia-cusolver-cu12 11.7.1.2 /venv/lib/python3.10/site-packages pip
nvidia-cusparse-cu12 12.5.4.2 /venv/lib/python3.10/site-packages pip
nvidia-cusparselt-cu12 0.6.3 /venv/lib/python3.10/site-packages pip
nvidia-nccl-cu12 2.21.5 /venv/lib/python3.10/site-packages pip
nvidia-nvjitlink-cu12 12.6.85 /venv/lib/python3.10/site-packages pip
nvidia-nvtx-cu12 12.6.77 /venv/lib/python3.10/site-packages pip
packaging 24.2 /venv/lib/python3.10/site-packages conda
pandas 2.2.3 /venv/lib/python3.10/site-packages conda
pillow 11.1.0 /venv/lib/python3.10/site-packages conda
pip 25.0.1 /venv/lib/python3.10/site-packages conda
plotly 6.0.0 /venv/lib/python3.10/site-packages conda
protobuf 5.28.3 /venv/lib/python3.10/site-packages conda
psutil 6.1.1 /venv/lib/python3.10/site-packages conda
pycparser 2.22 /venv/lib/python3.10/site-packages conda
Pygments 2.19.1 /venv/lib/python3.10/site-packages pip
pyparsing 3.2.1 /venv/lib/python3.10/site-packages conda
PySide6 6.8.2 /venv/lib/python3.10/site-packages
PySocks 1.7.1 /venv/lib/python3.10/site-packages conda
python-dateutil 2.9.0.post0 /venv/lib/python3.10/site-packages conda
pytz 2024.1 /venv/lib/python3.10/site-packages conda
PyWavelets 1.8.0 /venv/lib/python3.10/site-packages conda
PyYAML 6.0.2 /venv/lib/python3.10/site-packages conda
requests 2.32.3 /venv/lib/python3.10/site-packages conda
rich 13.9.4 /venv/lib/python3.10/site-packages pip
scikit-image 0.25.1 /venv/lib/python3.10/site-packages conda
scikit-learn 1.6.1 /venv/lib/python3.10/site-packages conda
scikit-sparse 0.4.14 /venv/lib/python3.10/site-packages conda
scipy 1.15.1 /venv/lib/python3.10/site-packages conda
setuptools 75.8.0 /venv/lib/python3.10/site-packages
shellingham 1.5.4 /venv/lib/python3.10/site-packages pip
shiboken6 6.8.2 /venv/lib/python3.10/site-packages
SimpleITK 2.4.1 /venv/lib/python3.10/site-packages pip
six 1.17.0 /venv/lib/python3.10/site-packages conda
sympy 1.13.1 /venv/lib/python3.10/site-packages pip
tensorboard 2.18.0 /venv/lib/python3.10/site-packages conda
tensorboard_data_server 0.7.0 /venv/lib/python3.10/site-packages conda
threadpoolctl 3.5.0 /venv/lib/python3.10/site-packages conda
tifffile 2025.1.10 /venv/lib/python3.10/site-packages conda
torch 2.6.0+cu126 /venv/lib/python3.10/site-packages pip
torchio 0.20.4 /venv/lib/python3.10/site-packages pip
torchvision 0.21.0+cu126 /venv/lib/python3.10/site-packages pip
tornado 6.4.2 /venv/lib/python3.10/site-packages conda
tqdm 4.67.1 /venv/lib/python3.10/site-packages conda
triton 3.2.0 /venv/lib/python3.10/site-packages pip
typer 0.15.1 /venv/lib/python3.10/site-packages pip
typing_extensions 4.12.2 /venv/lib/python3.10/site-packages conda
tzdata 2025.1 /venv/lib/python3.10/site-packages conda
unicodedata2 16.0.0 /venv/lib/python3.10/site-packages conda
urllib3 2.3.0 /venv/lib/python3.10/site-packages conda
Werkzeug 3.1.3 /venv/lib/python3.10/site-packages conda
wheel 0.45.1 /venv/lib/python3.10/site-packages
wrapt 1.17.2 /venv/lib/python3.10/site-packages pip
yacs 0.1.8 /venv/lib/python3.10/site-packages conda
zipp 3.21.0 /venv/lib/python3.10/site-packages conda
zstandard 0.23.0 /venv/lib/python3.10/site-packages
...
Execution
Include the command you used to run FastSurfer that cause the problem, e.g.
./run_fastsurfer.sh --sid test --sd /path/to/dir --t1 /path/to/file.nii.
I ran fastsurfer cerebNet on the../mri/orig/001.mgz images from an existing FreeSurfer 7.4.1 analysis.
Fastsurfer call:
#!/bin/bash
#SBATCH -J fastsurf_gpu
#SBATCH --cpus-per-task=2
#SBATCH --mem-per-cpu=2GB
#SBATCH --output=/mnt/scratch/projects/VIA_BIDS/logs/slurm-%j.txt
#SBATCH --partition=HPC
#SBATCH --gres=gpu:1
module load singularity/4.0.0
# =========================
# Project utilities
# =========================
UTILS_DIR="/mnt/projects/VIA_BIDS/scripts/freesurfer/utils"
export UTILS_DIR
for utils in catch_error validate_email validate_xnatid logging set_debug_mode; do
# shellcheck source=/dev/null
source "${UTILS_DIR}/${utils}.sh"
done
######## These must be provided via the command line.
[ "$1" == "" ] && echo "Please specify FS_DIR" && exit
[ "$2" == "" ] && echo "Please specify data_file" && exit
[ "$3" == "" ] && echo "Please specify LOG_DIR" && exit
[ "$4" == "" ] && echo "Please specify FS_OUt dir" && exit
FS_DIR="${1}"
data_file="${2}"
LOG_DIR="${3}"
FS_OUT="${4}"
slurmid=${SLURM_ARRAY_TASK_ID}
subid=$(awk "NR==${slurmid}" ${data_file})
log="${LOG_DIR}/slurm.fastsurfer.cerebnet.${subid}.log"
catch_error mv ${LOG_DIR}/slurm-${SLURM_JOBID}.txt ${log}
LICENSE_DIR="/mnt/projects/VIA_BIDS/scripts" # set path to valid license file
## fastsurfer file
fastsurfer="/mrhome/wimb/singularity/fastsurfer-sandbox-v2.4.2" # change path to latest fastsurfer v2.2.0
IN_DIR="${FS_DIR}/${subid}/mri/orig"
T1="001.mgz"
OUT_DIR="${FS_OUT}/${subid}/fastsurfer"
for dir in ${OUT_DIR}
do
if [ ! -d ${dir} ]; then
mkdir -p ${dir}
fi
done
# # run all modules. Segmentations plus surfaces. Delete or comment out using # if not applicable
# catch_error singularity exec --cleanenv --contain --nv \
# -B ${IN_DIR}:/data \
# -B ${OUT_DIR}:/output \
# -B ${LICENSE_DIR}:/fs_license \
# ${fastsurfer} \
# /fastsurfer/run_fastsurfer.sh \
# --fs_license /fs_license/license.txt \
# --t1 /data/${T1} \
# --sid ${subid} \
# --sd /output \
# --parallel \
# --threads ${SLURM_CPUS_PER_TASK}
# only run cerebellum. Delete or comment out using # if not applicable
catch_error singularity exec --cleanenv --contain --nv \
-B ${IN_DIR}:/data \
-B ${OUT_DIR}:/output \
-B ${LICENSE_DIR}:/fs_license \
${fastsurfer} \
/fastsurfer/run_fastsurfer.sh \
--fs_license /fs_license/license.txt \
--t1 /data/${T1} \
--sid ${subid} \
--sd /output \
--seg_only \
--parallel \
--threads ${SLURM_CPUS_PER_TASK}