# BOA::Contrast
Package to compute contrast information from a CT image, part of the [BOA](https://github.com/UMEssen/Body-and-Organ-Analyzer) (soon online!). The package uses the open-source software [TotalSegmentator](https://github.com/wasserth/TotalSegmentator) to compute segmentations of important anatomical landmarks, which are then used to create features for a machine learning model to predict the contrast information.
## Install
```bash
pip install boa-contrast
```
will install only the basic package (without the TotalSegmentator), if you also want to install the TotalSegmentator you can
```bash
pip install "boa-contrast[totalsegmentator]"
```
However, the TotalSegmentator can also be used together with docker, and in such case it is not needed to install it.
## Command Line
```
constrast-recognition --help
```
Once a CT and a folder where to store the TotalSegmentator segmentations is given, you can run it using the following command
```
contrast-recognition [-h] --ct-path CT_PATH --segmentation-folder SEGMENTATION_FOLDER [--docker] [--user-id USER_ID] [--device-id DEVICE_ID] [-v]
```
You can run it using docker by using the `--docker` flag. If you are using docker, you need to specify your user ID using the `--user-id` flag, otherwise you will have to change the ownership of the segmentations afterwards.
If you are using a GPU, you can specify the device ID using the `--device-id` flag.
You can enable verbosity with the `-v` flag.
To not download the TotalSegmentator weights all the time, you can specify their location using the `TOTALSEG_WEIGHTS_PATH` environment variable.
A sample output looks as follows:
```
IV Phase: NON_CONTRAST
Contrast in GIT: NO_CONTRAST_IN_GI_TRACT
```
## From Python
Compute the segmentation with the TotalSegmentator with docker
```python
from boa_contrast import compute_segmentation
compute_segmentation(
ct_path=..., # The path to the CT
segmentation_folder=..., # The root where the segmentation should be stored
device_id=..., # The ID of the GPU device or -1
user_id=..., # Your user ID for docker to run in user mode
compute_with_docker=False, # Whether to use docker or not
)
```
Once the segmentation is computed
```python
from boa_contrast import predict
predict(
ct_path=..., # path to the CT
segmentation_folder=..., # path to this CT's segmentation
)
```
Output:
```
{
"phase_ensemble_prediction": 0,
"phase_ensemble_predicted_class": "NON_CONTRAST",
"phase_ensemble_probas": array(
[
9.89733540e-01,
3.60637282e-04,
4.79974664e-04,
5.55973168e-04,
8.86987492e-03,
]
),
"git_ensemble_prediction": 0,
"git_ensemble_predicted_class": "NO_CONTRAST_IN_GI_TRACT",
"git_ensemble_probas": array(
[
9.99951577e-01,
4.84187825e-05,
]
),
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/UMEssen/BOA-Contrast",
"name": "boa-contrast",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8,<3.11",
"maintainer_email": "",
"keywords": "python,contrast,intravenous,gastrointestinal tract,CT,machine learning",
"author": "Giulia Baldini",
"author_email": "Giulia.Baldini@uk-essen.de",
"download_url": "https://files.pythonhosted.org/packages/0c/f2/5e176422a8ea891eb315e0de0fccf3320bae9483e41666f62c3c87956a93/boa_contrast-0.1.3.tar.gz",
"platform": null,
"description": " # BOA::Contrast\n\nPackage to compute contrast information from a CT image, part of the [BOA](https://github.com/UMEssen/Body-and-Organ-Analyzer) (soon online!). The package uses the open-source software [TotalSegmentator](https://github.com/wasserth/TotalSegmentator) to compute segmentations of important anatomical landmarks, which are then used to create features for a machine learning model to predict the contrast information.\n\n## Install\n\n```bash\npip install boa-contrast\n```\n\nwill install only the basic package (without the TotalSegmentator), if you also want to install the TotalSegmentator you can\n\n```bash\npip install \"boa-contrast[totalsegmentator]\"\n```\n\nHowever, the TotalSegmentator can also be used together with docker, and in such case it is not needed to install it.\n\n## Command Line\n```\nconstrast-recognition --help\n```\nOnce a CT and a folder where to store the TotalSegmentator segmentations is given, you can run it using the following command\n```\ncontrast-recognition [-h] --ct-path CT_PATH --segmentation-folder SEGMENTATION_FOLDER [--docker] [--user-id USER_ID] [--device-id DEVICE_ID] [-v]\n```\n\nYou can run it using docker by using the `--docker` flag. If you are using docker, you need to specify your user ID using the `--user-id` flag, otherwise you will have to change the ownership of the segmentations afterwards.\n\nIf you are using a GPU, you can specify the device ID using the `--device-id` flag.\n\nYou can enable verbosity with the `-v` flag.\n\nTo not download the TotalSegmentator weights all the time, you can specify their location using the `TOTALSEG_WEIGHTS_PATH` environment variable.\n\nA sample output looks as follows:\n```\nIV Phase: NON_CONTRAST\nContrast in GIT: NO_CONTRAST_IN_GI_TRACT\n```\n\n## From Python\nCompute the segmentation with the TotalSegmentator with docker\n\n```python\nfrom boa_contrast import compute_segmentation\n\ncompute_segmentation(\n ct_path=..., # The path to the CT\n segmentation_folder=..., # The root where the segmentation should be stored\n device_id=..., # The ID of the GPU device or -1\n user_id=..., # Your user ID for docker to run in user mode\n compute_with_docker=False, # Whether to use docker or not\n)\n```\n\nOnce the segmentation is computed\n\n```python\nfrom boa_contrast import predict\n\npredict(\n ct_path=..., # path to the CT\n segmentation_folder=..., # path to this CT's segmentation\n)\n```\n\nOutput:\n```\n{\n \"phase_ensemble_prediction\": 0,\n \"phase_ensemble_predicted_class\": \"NON_CONTRAST\",\n \"phase_ensemble_probas\": array(\n [\n 9.89733540e-01,\n 3.60637282e-04,\n 4.79974664e-04,\n 5.55973168e-04,\n 8.86987492e-03,\n ]\n ),\n \"git_ensemble_prediction\": 0,\n \"git_ensemble_predicted_class\": \"NO_CONTRAST_IN_GI_TRACT\",\n \"git_ensemble_probas\": array(\n [\n 9.99951577e-01,\n 4.84187825e-05,\n ]\n ),\n}\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://github.com/UMEssen/BOA-Contrast",
"Repository": "https://github.com/UMEssen/BOA-Contrast"
},
"split_keywords": [
"python",
"contrast",
"intravenous",
"gastrointestinal tract",
"ct",
"machine learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "d036f17ac762a09a0fc4e1b67d0eca8fe15383325f70a43e66e8e2cf3cd7120f",
"md5": "68b9c99d59fa566b3783666ff9336ed6",
"sha256": "82f8973dfd64ac49dc0fd752d27d4f88ab85e13f5b11fa272fc8abe92deb9fb5"
},
"downloads": -1,
"filename": "boa_contrast-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "68b9c99d59fa566b3783666ff9336ed6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8,<3.11",
"size": 78440901,
"upload_time": "2023-08-04T11:45:09",
"upload_time_iso_8601": "2023-08-04T11:45:09.739474Z",
"url": "https://files.pythonhosted.org/packages/d0/36/f17ac762a09a0fc4e1b67d0eca8fe15383325f70a43e66e8e2cf3cd7120f/boa_contrast-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "0cf25e176422a8ea891eb315e0de0fccf3320bae9483e41666f62c3c87956a93",
"md5": "afd6ddd2d2023cb99f1be8f04e966665",
"sha256": "77010a8f2ee2319a13bb7e317890ec49875301ceb2ef0fb809859627da423326"
},
"downloads": -1,
"filename": "boa_contrast-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "afd6ddd2d2023cb99f1be8f04e966665",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8,<3.11",
"size": 78437884,
"upload_time": "2023-08-04T11:45:15",
"upload_time_iso_8601": "2023-08-04T11:45:15.621442Z",
"url": "https://files.pythonhosted.org/packages/0c/f2/5e176422a8ea891eb315e0de0fccf3320bae9483e41666f62c3c87956a93/boa_contrast-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-08-04 11:45:15",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "UMEssen",
"github_project": "BOA-Contrast",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "boa-contrast"
}
JSON
