Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add datasets D4, D5 and models M4, M5 #23

Merged
merged 11 commits into from
Dec 13, 2023
Merged

Add datasets D4, D5 and models M4, M5 #23

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
b23e720
Add D4 and M4
valosekj Nov 22, 2023
b478ad1
Update README.md
valosekj Nov 22, 2023
ade167f
Add install info how to install nnunet on GPU
valosekj Nov 22, 2023
67daac6
Add info about M5 and D5
valosekj Dec 1, 2023
de89493
Add check_voxels.py to check voxels with values `1` and min and max v…
valosekj Dec 1, 2023
231ca0b
Update README for M5
valosekj Dec 6, 2023
d9c1601
Add parse_nnunet_training_log.py to read nnUNet training log file, ex…
valosekj Dec 6, 2023
4b34dbc
Fix input arg
valosekj Dec 6, 2023
44e973d
Show interactive figure using plotly
valosekj Dec 6, 2023
cd9df10
Print the latest Dice for each class
valosekj Dec 6, 2023
6d597eb
Print mean Dice across all classes
valosekj Dec 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
64 changes: 60 additions & 4 deletions training/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,9 @@
# Spinal Nerve Rootlets Segmentation on T2w Images

## 0) Dependencies

- nnUNetV2 - GPU installation for model training: [here](https://github.com/ivadomed/utilities/blob/main/quick_start_guides/nnU-Net_quick_start_guide.md#installation)

## 1) Project Overview

The goal of this project is to develop a deep learning (DL)-based method to segment and locate the spinal nerve
Expand Down Expand Up @@ -63,6 +67,8 @@ will be numbered as D1, D2, etc., and the models as M1, M2, etc.
| D1b (nnUNet 006) | 18 | 22.9 | 1.21 | Binary | Prediction + Manual review | 0.52~0.6 | [D1b.tsv](dataset_creation/D1b.tsv) |
| D2 (nnUNet 007) | 36 (20 from D0b + D1b) + 2 test images | 26.2 | 5.2 | Binary | Prediction + Manual review | 0.65~0.75 | [D2.tsv](dataset_creation/D2.tsv) |
| D3 (nnUNet 008-9) | 31 + 2 test images | 26.5 | 5.5 | Level specific | Value modification | 0.4~0.6 | [D3.tsv](dataset_creation/D3.tsv) |
| D4 (nnUNet 011) | 33 + 5 test images | | | Level specific | Prediction + Manual review | | [D4.tsv](dataset_creation/D4.tsv) |
| D5 (nnUNet 012) | 31 + 5 test images | | | Level specific | Prediction + Manual review | | [D5.tsv](dataset_creation/D5.tsv) |

<details>
<summary>Details</summary>
Expand Down Expand Up @@ -128,6 +134,25 @@ exceeding 0.5 compared to the first training conducted with 1000 epochs.

> Refer to [issue#8 part 3)](https://github.com/ivadomed/model-spinal-rootlets/issues/8).

#### D4)

Five images used for [inter-rater variability](https://github.com/ivadomed/model-spinal-rootlets/issues/17)
(`sub-007_ses-headNormal_T2w.nii.gz`, `sub-010_ses-headUp_T2w.nii.gz`, `sub-amu02_T2w.nii.gz`, `sub-barcelona01_T2w.nii.gz`,
`sub-brnoUhb03_T2w.nii.gz`) were moved from the training dataset to the test dataset.
The D3 model was applied to five new randomly chosen images from the spine-generic dataset (`sub-mgh01_T2w.nii.gz`, `sub-mgh02_T2w.nii.gz`,
`sub-stanford02_T2w.nii.gz`, `sub-stanford05_T2w.nii.gz`, `sub-ucdavis03_T2w.nii.gz`), the images were QCed, manually
corrected and added to the training dataset.
The D4 training dataset comprises 33 images, and the test dataset comprises 5 images. For details, see [D4.tsv](dataset_creation/D4.tsv).

#### D5)

During M4 training using D4 dataset, I noticed `0` and `nan` dice for some levels --> I checked all the D4 labels and
found that some labels were wrong (some labels contained values `1` (probably legacy from binary levels) and some levels
were mislabeled) --> I corrected the labels. Also, I made sure that the labels contains only levels 2 to 8 (we do not
have enough subjects with levels >9). Also, I removed `sub-004_ses-headUp` (difficult to label) and `sub-008_ses-headUp`
(wrong FOV covering only C1-C4). The final dataset is called D5.
The D5 training dataset comprises 31 images, and the test dataset comprises 5 images. For details, see [D5.tsv](dataset_creation/D5.tsv).

</details>

### C) Reproduce
Expand Down Expand Up @@ -330,13 +355,44 @@ sub-011_ses-headUp_T2w.nii.gz

</details>

This dataset D3 composed of 33 images with 31 for train .
I have trained 4 folds of a nnUNet 3d_fullres model for 2000
epochs `CUDA_VISIBLE_DEVICES=XXX nnUNetv2_train DATASETID -tr nnUNetTrainer_2000epochs -f 0`
The dataset D3 composed of 33 images with 31 for train.
I have trained 5 folds of a nnUNet 3d_fullres model for 2000 epochs:

```
CUDA_VISIBLE_DEVICES=XXX nnUNetv2_train DATASETID -tr nnUNetTrainer_2000epochs -f 0
```

nnUNet Dice score from `progress.png` was between 0.4 and 0.6.

#### iv) Get our dataset
#### iv) Reproduce D4, M4

The dataset D4 composed of 38 images with 33 for train.
I have trained 5 folds of a nnUNet 3d_fullres model for 2000 epochs:

```
nnUNetv2_plan_and_preprocess -d 011 --verify_dataset_integrity -c 3d_fullres
CUDA_VISIBLE_DEVICES=1 nnUNetv2_train 011 3d_fullres 0 -tr nnUNetTrainer_2000epochs
CUDA_VISIBLE_DEVICES=2 nnUNetv2_train 011 3d_fullres 1 -tr nnUNetTrainer_2000epochs
CUDA_VISIBLE_DEVICES=3 nnUNetv2_train 011 3d_fullres 2 -tr nnUNetTrainer_2000epochs
CUDA_VISIBLE_DEVICES=1 nnUNetv2_train 011 3d_fullres 3 -tr nnUNetTrainer_2000epochs
CUDA_VISIBLE_DEVICES=2 nnUNetv2_train 011 3d_fullres 4 -tr nnUNetTrainer_2000epochs
```

#### v) Reproduce D5, M5

The dataset D5 composed of 36 images with 31 for train.
I have trained 5 folds of a nnUNet 3d_fullres model for 2000 epochs:

```
nnUNetv2_plan_and_preprocess -d 012 --verify_dataset_integrity -c 3d_fullres
CUDA_VISIBLE_DEVICES=1 nnUNetv2_train 012 3d_fullres 0 -tr nnUNetTrainer_2000epochs
CUDA_VISIBLE_DEVICES=2 nnUNetv2_train 012 3d_fullres 1 -tr nnUNetTrainer_2000epochs
CUDA_VISIBLE_DEVICES=3 nnUNetv2_train 012 3d_fullres 2 -tr nnUNetTrainer_2000epochs
CUDA_VISIBLE_DEVICES=1 nnUNetv2_train 012 3d_fullres 3 -tr nnUNetTrainer_2000epochs
CUDA_VISIBLE_DEVICES=2 nnUNetv2_train 012 3d_fullres 4 -tr nnUNetTrainer_2000epochs
```

For resulting Dice, see https://github.com/ivadomed/model-spinal-rootlets/pull/23#issuecomment-1843240432

#Link to dataset D1b, D2, D3 already done, make one release per dataset ?

Expand Down
47 changes: 47 additions & 0 deletions training/check_voxels.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
"""
This script opens a NIfTI image, finds the coordinates of voxels with a specified value,
and prints the voxel coordinates along with the maximum and minimum values in the image.

Usage:
python script.py <nii_image_path>

Jan Valosek
"""

import nibabel as nib
import numpy as np

def find_coordinates_with_value(image_path, target_value=1):
# Load NIfTI image
img = nib.load(image_path)

# Get image data as a NumPy array
data = img.get_fdata()

# Find voxel coordinates with the specified value
coordinates = np.argwhere(data == target_value)

# Get max and min values in the image
max_value = np.max(data)
min_value = np.min(data)

return coordinates, max_value, min_value

if __name__ == "__main__":
import sys

# Check if the input argument is provided
if len(sys.argv) != 2:
print("Usage: python script.py <nii_image_path>")
sys.exit(1)

# Get the NIfTI image path from the command line arguments
nii_image_path = sys.argv[1]

# Find coordinates with value 1 and max/min values in the NIfTI image
voxel_coordinates, max_value, min_value = find_coordinates_with_value(nii_image_path)

# Print the result
print(f"Voxel coordinates with value 1 in {nii_image_path}:\n{voxel_coordinates}")
print(f"Max value in the image: {max_value}")
print(f"Min value in the image: {min_value}")
39 changes: 39 additions & 0 deletions training/dataset_creation/D4.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
file_name folder sex age resolution (mm) neck_flexion height weight date_of_scan institution_id institution manufacturer manufacturers_model_name receive_coil_name software_versions researcher pathology notes
sub-amu01_T2w.nii.gz train M 28 0.8 N 176.0 70.0 12/02/2019 amu AMU - CEMEREM Siemens Verio NeckMatrix syngo_MR_B17 Virginie Callot HC
sub-amu05_T2w.nii.gz train F 39 0.8 N 175.0 66.0 01/03/2019 amu AMU - CEMEREM Siemens Verio NeckMatrix syngo_MR_B17 Virginie Callot HC disc protrusion C4/5/6 and mild kyphosis
sub-balgrist01_T2w.nii.gz train F 31 0.8 N 158.0 60.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC Mild kyphosis
sub-balgrist02_T2w.nii.gz train F 22 0.8 N 170.0 72.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC Mild kyphosis
sub-balgrist03_T2w.nii.gz train F 23 0.8 N 175.0 85.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC disc protrusion C3/4 and mild kyphosis
sub-balgrist04_T2w.nii.gz train M 28 0.8 N 195.0 90.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC
sub-balgrist06_T2w.nii.gz train M 23 0.8 N 170.0 64.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC visualised spinal canal C5-Th1
sub-barcelona02_T2w.nii.gz train M 38 0.8 N 190.0 95.0 23/11/2018 barcelona Advanced Imaging in Neuroimmunological Diseases (ImaginEM) group Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 Martinez-Heras E, Solana E, Llufriu S MildCompression mild spinal cord compression due to C4-6 disc protrusions
sub-barcelona03_T2w.nii.gz train M 39 0.8 N 185.0 85.0 23/11/2018 barcelona Advanced Imaging in Neuroimmunological Diseases (ImaginEM) group Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 Martinez-Heras E, Solana E, Llufriu S MildCompression mild spinal cord compression due to C4/5 disc hernia
sub-barcelona06_T2w.nii.gz train F 25 0.8 N 170.0 55.0 30/11/2018 barcelona Advanced Imaging in Neuroimmunological Diseases (ImaginEM) group Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 Martinez-Heras E, Solana E, Llufriu S HC disc protrusions C4-7 and Th4-6
sub-brnoUhb01_T2w.nii.gz train M 21 0.8 N 180.0 90.0 13/02/2019 brnoUhb The University Hospital Brno, Department of Radiology and Nuclear Medicine, Czech Republic GE Signa-PETMR MP24 Marek Dostal, Milo Kekovsk HC disc protrusions C4-7
sub-cardiff02_T2w.nii.gz train F 34 0.8 N 172.0 54.0 05/03/2019 cardiff CUBRIC, Cardiff University, Wales, UK Siemens Prisma HeadNeck_64 VE11C G. Tackley, S. Kusmia, R. Wise HC disc protrusion Th2/3
sub-cardiff04_T2w.nii.gz train F 31 0.8 N 170.0 58.0 12/03/2019 cardiff CUBRIC, Cardiff University, Wales, UK Siemens Prisma HeadNeck_64 VE11C G. Tackley, S. Kusmia, R. Wise HC disc protrusion C3-7 and Th2-4
sub-cmrra02_T2w.nii.gz train M 27 0.8 N 188.0 91.0 01/03/2019 cmrra University of Minnesota Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 R. Labounek, J. Joers, C. Nguyen, I. Nestrasil, C. Lenglet, P-G. Henry HC disc protrusions C4-7
sub-cmrra04_T2w.nii.gz train F 22 0.8 N 163.0 54.0 18/03/2019 cmrra University of Minnesota Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 R. Labounek, J. Joers, C. Nguyen, I. Nestrasil, C. Lenglet, P-G. Henry HC disc protrusion and kyphosis at C3/4
sub-geneva01_T2w.nii.gz train M 29 0.8 N 189.0 69.0 21/02/2019 geneva Campus Biotech Geneva Siemens Prisma 64ch+spine VE11C K. Kinany, L. Mattera HC Chondrosis and disc protrusions C3-7
sub-mgh01_T2w.nii.gz train F 28 0.8 N 173 73 2019-01-01 mgh Massachusetts General Hospital Siemens Skyra 64ch+spine VE11C R. L. Barry HC disc protrusions C3-6
sub-mgh02_T2w.nii.gz train F 33 0.8 N 155 41 2019-01-01 mgh Massachusetts General Hospital Siemens Skyra 64ch+spine VE11C R. L. Barry HC disc protrusion C5/6
sub-stanford02_T2w.nii.gz train F 39 0.8 N 163 54 2018-02-22 stanford Stanford University GE MR750 16ch neurovascular DV26.0_R01 C. S. Law, K. A. Weber II, S. Mackey, K. R. Epperson, K. S Epperson HC n/a
sub-stanford05_T2w.nii.gz train M 19 0.8 N 178 59 2018-02-24 stanford Stanford University GE MR750 16ch neurovascular DV26.0_R01 C. S. Law, K. A. Weber II, S. Mackey, K. R. Epperson, K. S Epperson HC Disc protrusion C3/4
sub-ucdavis03_T2w.nii.gz train M 41 0.8 N 179 82 n/a ucdavis UC Davis Health, California, US Siemens Vida HeadNeck_64 syngo MR XA20 Allan R. Martin HC Mild disc protrusions C3-7
sub-brnoUhb03_T2w.nii.gz test F 26 0.8 N 163.0 56.0 13/02/2019 brnoUhb The University Hospital Brno, Department of Radiology and Nuclear Medicine, Czech Republic GE Signa-PETMR MP24 Marek Dostal, Milo Kekovsk HC disc protrusions C4-7
sub-amu02_T2w.nii.gz test M 28 0.8 N 183.0 67.0 13/02/2019 amu AMU - CEMEREM Siemens Verio NeckMatrix syngo_MR_B17 Virginie Callot HC disc protrusion Th2/3, visualised central canal
sub-barcelona01_T2w.nii.gz test M 36 0.8 N 170.0 70.0 16/10/2018 barcelona Advanced Imaging in Neuroimmunological Diseases (ImaginEM) group Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 Martinez-Heras E, Solana E, Llufriu S MildCompression mild spinal cord compression due to C4/5 disc protrusion
sub-002_ses-headNormal_T2w.nii.gz train F 22 0.6 N
sub-003_ses-headNormal_T2w.nii.gz train M 22 0.6 N
sub-003_ses-headUp_T2w.nii.gz train M 22 0.6 U
sub-004_ses-headNormal_T2w.nii.gz train F 23 0.6 N
sub-004_ses-headUp_T2w.nii.gz train F 23 0.6 U
sub-005_ses-headNormal_T2w.nii.gz train M 22 0.6 N
sub-005_ses-headUp_T2w.nii.gz train M 22 0.6 U
sub-007_ses-headUp_T2w.nii.gz train M 23 0.6 U
sub-008_ses-headUp_T2w.nii.gz train M 26 0.6 U
sub-010_ses-headNormal_T2w.nii.gz train M 23 0.6 N
sub-011_ses-headNormal_T2w.nii.gz train M 23 0.6 N
sub-011_ses-headUp_T2w.nii.gz train M 23 0.6 U
sub-007_ses-headNormal_T2w.nii.gz test M 23 0.6 N
sub-010_ses-headUp_T2w.nii.gz test M 23 0.6 U
37 changes: 37 additions & 0 deletions training/dataset_creation/D5.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
file_name folder sex age resolution (mm) neck_flexion height weight date_of_scan institution_id institution manufacturer manufacturers_model_name receive_coil_name software_versions researcher pathology notes
sub-amu01_T2w.nii.gz train M 28 0.8 N 176.0 70.0 12/02/2019 amu AMU - CEMEREM Siemens Verio NeckMatrix syngo_MR_B17 Virginie Callot HC
sub-amu05_T2w.nii.gz train F 39 0.8 N 175.0 66.0 01/03/2019 amu AMU - CEMEREM Siemens Verio NeckMatrix syngo_MR_B17 Virginie Callot HC disc protrusion C4/5/6 and mild kyphosis
sub-balgrist01_T2w.nii.gz train F 31 0.8 N 158.0 60.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC Mild kyphosis
sub-balgrist02_T2w.nii.gz train F 22 0.8 N 170.0 72.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC Mild kyphosis
sub-balgrist03_T2w.nii.gz train F 23 0.8 N 175.0 85.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC disc protrusion C3/4 and mild kyphosis
sub-balgrist04_T2w.nii.gz train M 28 0.8 N 195.0 90.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC
sub-balgrist06_T2w.nii.gz train M 23 0.8 N 170.0 64.0 balgrist Spinal Cord Injury Center University Balgrist Clinic Siemens Prisma HeadNeck_64 VE11C M. Seif, P. Freund HC visualised spinal canal C5-Th1
sub-barcelona02_T2w.nii.gz train M 38 0.8 N 190.0 95.0 23/11/2018 barcelona Advanced Imaging in Neuroimmunological Diseases (ImaginEM) group Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 Martinez-Heras E, Solana E, Llufriu S MildCompression mild spinal cord compression due to C4-6 disc protrusions
sub-barcelona03_T2w.nii.gz train M 39 0.8 N 185.0 85.0 23/11/2018 barcelona Advanced Imaging in Neuroimmunological Diseases (ImaginEM) group Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 Martinez-Heras E, Solana E, Llufriu S MildCompression mild spinal cord compression due to C4/5 disc hernia
sub-barcelona06_T2w.nii.gz train F 25 0.8 N 170.0 55.0 30/11/2018 barcelona Advanced Imaging in Neuroimmunological Diseases (ImaginEM) group Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 Martinez-Heras E, Solana E, Llufriu S HC disc protrusions C4-7 and Th4-6
sub-brnoUhb01_T2w.nii.gz train M 21 0.8 N 180.0 90.0 13/02/2019 brnoUhb The University Hospital Brno, Department of Radiology and Nuclear Medicine, Czech Republic GE Signa-PETMR MP24 Marek Dostal, Milo Kekovsk HC disc protrusions C4-7
sub-cardiff02_T2w.nii.gz train F 34 0.8 N 172.0 54.0 05/03/2019 cardiff CUBRIC, Cardiff University, Wales, UK Siemens Prisma HeadNeck_64 VE11C G. Tackley, S. Kusmia, R. Wise HC disc protrusion Th2/3
sub-cardiff04_T2w.nii.gz train F 31 0.8 N 170.0 58.0 12/03/2019 cardiff CUBRIC, Cardiff University, Wales, UK Siemens Prisma HeadNeck_64 VE11C G. Tackley, S. Kusmia, R. Wise HC disc protrusion C3-7 and Th2-4
sub-cmrra02_T2w.nii.gz train M 27 0.8 N 188.0 91.0 01/03/2019 cmrra University of Minnesota Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 R. Labounek, J. Joers, C. Nguyen, I. Nestrasil, C. Lenglet, P-G. Henry HC disc protrusions C4-7
sub-cmrra04_T2w.nii.gz train F 22 0.8 N 163.0 54.0 18/03/2019 cmrra University of Minnesota Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 R. Labounek, J. Joers, C. Nguyen, I. Nestrasil, C. Lenglet, P-G. Henry HC disc protrusion and kyphosis at C3/4
sub-geneva01_T2w.nii.gz train M 29 0.8 N 189.0 69.0 21/02/2019 geneva Campus Biotech Geneva Siemens Prisma 64ch+spine VE11C K. Kinany, L. Mattera HC Chondrosis and disc protrusions C3-7
sub-mgh01_T2w.nii.gz train F 28 0.8 N 173 73 2019-01-01 mgh Massachusetts General Hospital Siemens Skyra 64ch+spine VE11C R. L. Barry HC disc protrusions C3-6
sub-mgh02_T2w.nii.gz train F 33 0.8 N 155 41 2019-01-01 mgh Massachusetts General Hospital Siemens Skyra 64ch+spine VE11C R. L. Barry HC disc protrusion C5/6
sub-stanford02_T2w.nii.gz train F 39 0.8 N 163 54 2018-02-22 stanford Stanford University GE MR750 16ch neurovascular DV26.0_R01 C. S. Law, K. A. Weber II, S. Mackey, K. R. Epperson, K. S Epperson HC n/a
sub-stanford05_T2w.nii.gz train M 19 0.8 N 178 59 2018-02-24 stanford Stanford University GE MR750 16ch neurovascular DV26.0_R01 C. S. Law, K. A. Weber II, S. Mackey, K. R. Epperson, K. S Epperson HC Disc protrusion C3/4
sub-ucdavis03_T2w.nii.gz train M 41 0.8 N 179 82 n/a ucdavis UC Davis Health, California, US Siemens Vida HeadNeck_64 syngo MR XA20 Allan R. Martin HC Mild disc protrusions C3-7
sub-brnoUhb03_T2w.nii.gz test F 26 0.8 N 163.0 56.0 13/02/2019 brnoUhb The University Hospital Brno, Department of Radiology and Nuclear Medicine, Czech Republic GE Signa-PETMR MP24 Marek Dostal, Milo Kekovsk HC disc protrusions C4-7
sub-amu02_T2w.nii.gz test M 28 0.8 N 183.0 67.0 13/02/2019 amu AMU - CEMEREM Siemens Verio NeckMatrix syngo_MR_B17 Virginie Callot HC disc protrusion Th2/3, visualised central canal
sub-barcelona01_T2w.nii.gz test M 36 0.8 N 170.0 70.0 16/10/2018 barcelona Advanced Imaging in Neuroimmunological Diseases (ImaginEM) group Siemens Prisma-fit HeadNeck_64 syngo_MR_E11 Martinez-Heras E, Solana E, Llufriu S MildCompression mild spinal cord compression due to C4/5 disc protrusion
sub-002_ses-headNormal_T2w.nii.gz train F 22 0.6 N
sub-003_ses-headNormal_T2w.nii.gz train M 22 0.6 N
sub-003_ses-headUp_T2w.nii.gz train M 22 0.6 U
sub-004_ses-headNormal_T2w.nii.gz train F 23 0.6 N
sub-005_ses-headNormal_T2w.nii.gz train M 22 0.6 N
sub-005_ses-headUp_T2w.nii.gz train M 22 0.6 U
sub-007_ses-headUp_T2w.nii.gz train M 23 0.6 U
sub-010_ses-headNormal_T2w.nii.gz train M 23 0.6 N
sub-011_ses-headNormal_T2w.nii.gz train M 23 0.6 N
sub-011_ses-headUp_T2w.nii.gz train M 23 0.6 U
sub-007_ses-headNormal_T2w.nii.gz test M 23 0.6 N
sub-010_ses-headUp_T2w.nii.gz test M 23 0.6 U
Loading