# **FastSurfer** #
## Overview
* This GEAR wraps FastSurferCNN part of FastSurfer.
### Summary
* FastSurferCNN is an advanced deep learning architecture capable of whole brain segmentation into 95 classes in under 1 minute, mimicking FreeSurfer anatomical segmentation and cortical parcellation (DKTatlas).
### Cite
*Henschel L, Conjeti S, Estrada S, Diers K, Fischl B, Reuter M, FastSurfer - A fast and accurate deep learning based neuroimaging pipeline, NeuroImage 219 (2020), 117012*
License: *MIT*
### Classification
*Category:* *Analysis Gear*
*Gear Level:*
- [ ] Project
- [ ] Subject
- [x] Session
- [x] Acquisition
- [ ] Analysis
----
[[_TOC_]]
----
### Inputs
- *3DT1-Weighted Volume*
- __Name__: *T1w*
- __Type__: *file*
- __Optional__: *false*
- __Classification__: *file*
- __Description__: *Input 3D-T1w nifti in zipped format*
- __Notes__: *{Gear accepts one zipped nifti file}*
### Config
- *{Config-Option}*
- __Name__: *use-gpu*
- __Type__: *boolean*
- __Description__: *Use GPU for computing the FastSurfer segmentation. Gear will default to CPU if no GPU is available.*
- __Default__: *true*
### Outputs
#### Files
- *{Output-File}*
- __Name__: *aparc+aseg.nii.gz*
- __Type__: *file*
- __Optional__: *false*
- __Classification__: *file*
- __Description__: *Segmentation output with 95 labels*
- __Notes__: *The segmentation is based on the DKT atlas*
- *{Output-File}*
- __Name__: *deep-seg.log*
- __Type__: *file*
- __Optional__: *false*
- __Classification__: *file*
- __Description__: *Log file containing all processing details*
- *{Output-File}*
- __Name__: *001.mgz*
- __Type__: *file*
- __Optional__: *false*
- __Classification__: *file*
- __Description__: *intermediate file generated during inference*
- *{Output-File}*
- __Name__: *orig.mgz*
- __Type__: *file*
- __Optional__: *false*
- __Classification__: *file*
- __Description__: *intermediate file generated during inference*
## Usage
### Description
* This gears operates by using the [Eval script](https://github.com/Deep-MI/FastSurfer/blob/stable/FastSurferCNN/eval.py) from [FastSurferCNN](https://github.com/Deep-MI/FastSurfer/tree/stable/FastSurferCNN).
* The input is a 3D-T1w MRI exam in zipped nifti format.
* The output is saved to the Analysis section in the Flywheel platform.
#### File Specifications
This Gear has only 1 required input file. The details are below:
##### *{Input-File}*
A 3D-T1w brain MRI exam is required for this gear. Ideal acquistions are 1mm isotropic. The Gear can handle non-isotropic data such as 0.9mmx0.9mmx1.0mm.
### Workflow
```mermaid
graph LR;
A[Input-File]:::input --> C;
C[Upload] --> D[Parent Container <br> Project, Subject, etc];
D:::container --> E((Gear));
E:::gear --> F[Analysis]:::container;
classDef container fill:#57d,color:#fff
classDef input fill:#7a9,color:#fff
classDef gear fill:#659,color:#fff
```
Description of workflow
1. Upload file to container
2. Select file as input to gear
3. Gear places output in Analysis. All output files can be downloaded from Analysis.
4. The output files are available under "Outputs" section in job log. The aparc+aseg.nii.gz can be seen with OHIF viewer.
### Use Cases
#### Use Case 1
__*Conditions__*:
[x] Collection of 3D-T1w brain MRI exams for which a fast Freesurfer-style segmentation is needed.
[x] For each timepoint, the data is available as a zipped nifti file.
**Steps**
1. Upload the zipped nifti files to your Flywheel instance
a. Follow [these steps](https://docs.flywheel.io/hc/en-us/articles/360008162434) to upload <u>de-identified data to Flywheel </u>
2. Select the subjects' sessions that are to be analyzed
a. 
3. Navigate to "Run Gear", select "Analysis Gear", and select Fast Surfer under the "Image Processing - Segmentation" section.
a. 
4. Select the zipped nifti file to be segmented.
5. Run gear and review the results under Analysis or in the job log output section.
### Logging
* Logging will indicate if the processing was run on a GPU or CPU.
* Three models are run to generate the final output.
* The processing time for each model will be displayed in the log.
## FAQ
[FAQ.md](FAQ.md)
## Contributing
[For more information about how to get started contributing to that gear,
checkout [CONTRIBUTING.md](CONTRIBUTING.md).]
<!-- markdownlint-disable-file -->
Raw data
{
"_id": null,
"home_page": "https://gitlab.com/flywheel-io/flywheel-apps/templates/skeleton",
"name": "fw-gear-fast-surfer",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "Flywheel, Gears",
"author": "Flywheel",
"author_email": "support@flywheel.io",
"download_url": null,
"platform": null,
"description": "# **FastSurfer** #\n\n## Overview\n\n* This GEAR wraps FastSurferCNN part of FastSurfer.\n\n### Summary\n\n* FastSurferCNN is an advanced deep learning architecture capable of whole brain segmentation into 95 classes in under 1 minute, mimicking FreeSurfer anatomical segmentation and cortical parcellation (DKTatlas).\n\n### Cite\n\n*Henschel L, Conjeti S, Estrada S, Diers K, Fischl B, Reuter M, FastSurfer - A fast and accurate deep learning based neuroimaging pipeline, NeuroImage 219 (2020), 117012*\n\nLicense: *MIT*\n\n### Classification\n\n*Category:* *Analysis Gear*\n\n*Gear Level:*\n\n- [ ] Project\n- [ ] Subject\n- [x] Session\n- [x] Acquisition\n- [ ] Analysis\n\n\n----\n\n[[_TOC_]]\n\n----\n\n### Inputs\n\n- *3DT1-Weighted Volume*\n - __Name__: *T1w*\n - __Type__: *file*\n - __Optional__: *false*\n - __Classification__: *file*\n - __Description__: *Input 3D-T1w nifti in zipped format*\n - __Notes__: *{Gear accepts one zipped nifti file}*\n\n### Config\n\n- *{Config-Option}*\n - __Name__: *use-gpu*\n - __Type__: *boolean*\n - __Description__: *Use GPU for computing the FastSurfer segmentation. Gear will default to CPU if no GPU is available.*\n - __Default__: *true*\n\n### Outputs\n\n#### Files\n\n\n- *{Output-File}*\n - __Name__: *aparc+aseg.nii.gz*\n - __Type__: *file*\n - __Optional__: *false*\n - __Classification__: *file*\n - __Description__: *Segmentation output with 95 labels*\n - __Notes__: *The segmentation is based on the DKT atlas*\n\n- *{Output-File}*\n - __Name__: *deep-seg.log*\n - __Type__: *file*\n - __Optional__: *false*\n - __Classification__: *file*\n - __Description__: *Log file containing all processing details*\n\n- *{Output-File}*\n - __Name__: *001.mgz*\n - __Type__: *file*\n - __Optional__: *false*\n - __Classification__: *file*\n - __Description__: *intermediate file generated during inference*\n\n- *{Output-File}*\n - __Name__: *orig.mgz*\n - __Type__: *file*\n - __Optional__: *false*\n - __Classification__: *file*\n - __Description__: *intermediate file generated during inference*\n\n## Usage\n\n### Description\n* This gears operates by using the [Eval script](https://github.com/Deep-MI/FastSurfer/blob/stable/FastSurferCNN/eval.py) from [FastSurferCNN](https://github.com/Deep-MI/FastSurfer/tree/stable/FastSurferCNN).\n* The input is a 3D-T1w MRI exam in zipped nifti format. \n* The output is saved to the Analysis section in the Flywheel platform.\n\n\n#### File Specifications\n\nThis Gear has only 1 required input file. The details are below:\n\n##### *{Input-File}*\n\nA 3D-T1w brain MRI exam is required for this gear. Ideal acquistions are 1mm isotropic. The Gear can handle non-isotropic data such as 0.9mmx0.9mmx1.0mm.\n\n### Workflow\n\n```mermaid\ngraph LR;\n A[Input-File]:::input --> C;\n C[Upload] --> D[Parent Container <br> Project, Subject, etc];\n D:::container --> E((Gear));\n E:::gear --> F[Analysis]:::container;\n \n classDef container fill:#57d,color:#fff\n classDef input fill:#7a9,color:#fff\n classDef gear fill:#659,color:#fff\n\n```\n\nDescription of workflow\n\n1. Upload file to container\n2. Select file as input to gear\n3. Gear places output in Analysis. All output files can be downloaded from Analysis.\n4. The output files are available under \"Outputs\" section in job log. The aparc+aseg.nii.gz can be seen with OHIF viewer.\n\n### Use Cases\n\n#### Use Case 1\n\n__*Conditions__*:\n\n[x] Collection of 3D-T1w brain MRI exams for which a fast Freesurfer-style segmentation is needed. \n[x] For each timepoint, the data is available as a zipped nifti file.\n\n**Steps**\n1. Upload the zipped nifti files to your Flywheel instance\n a. Follow [these steps](https://docs.flywheel.io/hc/en-us/articles/360008162434) to upload <u>de-identified data to Flywheel </u>\n\n2. Select the subjects' sessions that are to be analyzed\n\n a. ![Session Selection](/images/select_subject.png \"Session Selection\")\n\n3. Navigate to \"Run Gear\", select \"Analysis Gear\", and select Fast Surfer under the \"Image Processing - Segmentation\" section. \n a. ![Run Gear](/images/run_gear.png \"Run Gear\")\n4. Select the zipped nifti file to be segmented.\n\n5. Run gear and review the results under Analysis or in the job log output section. \n\n### Logging\n\n* Logging will indicate if the processing was run on a GPU or CPU.\n* Three models are run to generate the final output. \n* The processing time for each model will be displayed in the log. \n\n## FAQ\n\n[FAQ.md](FAQ.md)\n\n## Contributing\n\n[For more information about how to get started contributing to that gear,\ncheckout [CONTRIBUTING.md](CONTRIBUTING.md).]\n<!-- markdownlint-disable-file -->\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Wrapper for Fast Surfer",
"version": "1.0.6",
"project_urls": {
"Homepage": "https://gitlab.com/flywheel-io/flywheel-apps/templates/skeleton",
"Repository": "https://gitlab.com/flywheel-io/flywheel-apps/templates/skeleton"
},
"split_keywords": [
"flywheel",
" gears"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2d6016ce75cf3ec39a239bbc07afd34b0a96b796cc867f8cf7bf44fac32a4b2b",
"md5": "a87d59f7fb9a0906d58085c5c69cbac9",
"sha256": "c4ff546a805b4adb1b15066fc3d120cffb2e864eac1327403cf432f9a73e2fc0"
},
"downloads": -1,
"filename": "fw_gear_fast_surfer-1.0.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a87d59f7fb9a0906d58085c5c69cbac9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 4723,
"upload_time": "2025-01-21T02:09:26",
"upload_time_iso_8601": "2025-01-21T02:09:26.178387Z",
"url": "https://files.pythonhosted.org/packages/2d/60/16ce75cf3ec39a239bbc07afd34b0a96b796cc867f8cf7bf44fac32a4b2b/fw_gear_fast_surfer-1.0.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-21 02:09:26",
"github": false,
"gitlab": true,
"bitbucket": false,
"codeberg": false,
"gitlab_user": "flywheel-io",
"gitlab_project": "flywheel-apps",
"lcname": "fw-gear-fast-surfer"
}
JSON