Merge pull request #48 from reghbali/reghbali_bids_fix

Reghbali bids fix

README.md

@@ -1,6 +1,7 @@
 # PyALFE
 
 Python implementation of Automated Lesion and Feature Extraction (ALFE) pipeline.
+We developed this pipeline for analysis of brain MRIs of patients suffering from conditions that cause brain lesions. It utilizes image processing tools, image registration tools, and deep learning segmentation models to produce a set of features that describe the lesion in the brain.
 
 ## Requirements
 
@@ -9,7 +10,7 @@ PyALFE supports Linux x86-64, Mac x86-64, and Mac arm64 and requires python 3.9+
 ### Image registration and processing
 PyALFE can be configured to use either [Greedy](https://greedy.readthedocs.io/en/latest/) or [AntsPy](https://antspy.readthedocs.io/en/latest/registration.html) registration tools.
 Similarly, PyALFE can can be configured to use [Convert3D](https://sourceforge.net/p/c3d/git/ci/master/tree/doc/c3d.md) or python native library [Nilearn](https://nilearn.github.io/stable/index.html) for image processing tasks.
-To use Greedy and Convert3d, these command line tools should be downloaded using the [download command](#download-models-and-tools).
+To use Greedy and Convert3d, these command line tools should be installed on your system.
 
 ## Installation
 
@@ -49,7 +50,7 @@ pip install --upgrade build
 Run the following commands in the parent pyalfe directory to build the whl file and install pyalfe
 ```bash
 python -m build
-pip install dist/pyalfe-0.0.1-py3-none-any.whl
+pip install dist/pyalfe-0.1.0-py3-none-any.whl
 ```
 
 ### Download models
@@ -76,12 +77,12 @@ pyalfe configure
 ```
 which prompt the you to enter the following required configurations:
 
-#### Classified directory
+#### Input directory
 ```bash
 Enter input image directory: /path/to/my_mri_data
 ```
-The classified directory (`classified_dir`) is the input directory to PyALFE and should be organized by accessions (or session ids). Inside the directory for each accession there should be a directory for each available modality.
-Here is an example that follow ALFE default structure:
+The input directory (`input_dir`) contains the images that will be processed by PyALFE and should be organized by accessions (or session ids). Inside the directory for each accession there should be a directory for each available modality.
+Here is an example that follows ALFE default structure:
 ```
 my_mri_data
 │
@@ -112,34 +113,51 @@ my_mri_data
     └───T2
         └── T2.nii.gz
 ```
-To use this directory the user should provide `path/to/my_mri_data` as the classified directory. This config value can be overwritten when calling `pyalfe run` via `-cd` or `--classified-dir` option.
+To use this directory the user should provide `path/to/my_mri_data` as the input directory. This config value can be overwritten when calling `pyalfe run` via `-id` or `--input-dir` option.
 
 pyALFE also supports BIDS directories. Here is an example of input dir organized in BIDS format:
 
 ```
 my_mri_data
 │
-│───anat
-│   │───sub-123_T1w.nii.gz
-│   │───sub-123_T2w.nii.gz
-│   └───sub-123_FLAIR.nii.gz
-│───dwi
-│    │───sub-123_dwi.nii.gz
-│    └───sub-123_md.nii.gz
-│───swi
-│    └───sub-123_swi.nii.gz
-└───perf
-     └───sub-123_cbf.nii.gz
+│───sub-01
+│   │───anat
+│   │   │───sub-01_T1w.nii.gz
+│   │   │───sub-01_ce-gadolinium_T1w.nii.gz
+│   │   │───sub-01_T2w.nii.gz
+│   │   └───sub-01_FLAIR.nii.gz
+│   │───dwi
+│   │    │───sub-01_dwi.nii.gz
+│   │    └───sub-01_md.nii.gz
+│   │───swi
+│   │    └───sub-01_swi.nii.gz
+│   └───perf
+│       └───sub-01_cbf.nii.gz
+│
+└───sub-02
+.   │───anat
+.   │   │───sub-02_T1w.nii.gz
+.   │   │───sub-02_ce-gadolinium_T1w.nii.gz
+    │   │───sub-02_T2w.nii.gz
+    │   └───sub-02_FLAIR.nii.gz
+    │───dwi
+    │    │───sub-02_dwi.nii.gz
+    │    └───sub-02_md.nii.gz
+    │───swi
+    │    └───sub-02_swi.nii.gz
+    └───perf
+        └───sub-02_cbf.nii.gz
 
 ```
 
-#### Processed directory
+#### Output directory
 ```bash
-Enter input image directory: /path/to/processed_data_dir
+Enter output image directory: /path/to/output_dir
 ```
-The processed image directory (`processed_dir`) is where ALFE writes all its output to.
+The output image directory (`output_dir`) is where pyALFE writes all its output to.
 It can be any valid path in filesystem that user have write access to.
-This config value can be overwritten when calling `pyalfe run` via `-pd` or `--processed-dir` option.
+This config value can be overwritten when calling `pyalfe run` via `-od` or `--output-dir` option.
+
 
 #### Modalities
 ```bash
@@ -173,7 +191,7 @@ image processor to use (c3d, nilearn) [c3d]:
 ```
 Currently, pyalfe can be configures to use either Convert3D (a.k.a. c3d) or Nilearn for image processing tasks.
 The default is Convert3d aka c3d. In other to use c3d,
-you have to download it using the [download command](#download-models-and-tools).
+you have to download it using the [download command](#download-models).
 To use Nilearn, you do not need to run any extra command since it is already installed when you install pyalfe.
 This config value can be overwritten when calling `pyalfe run` via `-ip` or `--image_processing` option.
 
@@ -182,10 +200,18 @@ This config value can be overwritten when calling `pyalfe run` via `-ip` or `--i
 image registration to use (greedy, ants) [greedy]:
 ```
 Currently, pyalfe can be configures to use either greedy or ants for image registration tasks. The default is greedy.
-In other to use greedy, you have to download it using the [download command](#download-models-and-tools). To use ants,
+In other to use greedy, you have to download it using the [download command](#download-models). To use ants,
 install pyalfe with ants support ``pip install pyalfe[ants]``.
 This config value can be overwritten when calling `pyalfe run` via `-ir` or `--image-registration` option.
 
+#### Dierctory Data Structure
+```bash
+data directory structure (press enter for default) (alfe, bids) [alfe]:
+```
+
+The directory structure that pyALFE expects in the input directory and will follow when creating the output. See [Inupt directory](#input-directory) for information on ALFE and BIDS.
+This config value can be overwritten when calling `payalfe run` via `-dds` or `--data-dir-structure` option.
+
 ### Running the pipeline
 To run PyALFE for an accession
 

docs/guides/install.md

@@ -7,9 +7,15 @@ PyALFE can be configured to use either [Greedy](https://greedy.readthedocs.io/en
 Similarly, PyALFE can be configured to use [Convert3D](https://sourceforge.net/p/c3d/git/ci/master/tree/doc/c3d.md) or python native library [Nilearn](https://nilearn.github.io/stable/index.html) for image processing tasks.
 To use Greedy and Convert3d, these command line tools should be downloaded using the [download command](#download-models-and-tools).
 
+### Option 1: Pypi installation
+You can install pyalfe by running:
+```bash
+pip install pyalfe
+```
 
-You can either instal pyalfe in [development mode](#development-mode-installation) or [build and install](#build-and-install).
-### Option 1: Development mode installation
+You can either install pyalfe from source after cloning the repo using [development mode](#development-mode-installation) or [build and install](#build-and-install).
+
+### Option 2: Development mode installation
 
 First update the setuptools
 ```bash
@@ -19,6 +25,7 @@ pip install --upgrade setuptools
 Run the following command in the parent pyalfe directory:
 
 ```bash
+
 pip install -e .
 ```
 
@@ -32,7 +39,7 @@ pip install --upgrade build
 Run the following commands in the parent pyalfe directory to build the whl file and install pyalfe
 ```bash
 python -m build
-pip install dist/pyalfe-0.0.1-py3-none-any.whl
+pip install dist/pyalfe-*-py3-none-any.whl
 ```
 
 ### Download models

docs/guides/tutorial.md

@@ -22,7 +22,7 @@ mkdir -p pyalfe-output
 
 ## Installation
 
-Create a python virtual environment and activate
+Create a python virtual environment and activate it
 ```bash
 python3 -m venv venv
 source venv/bin/activate
@@ -41,5 +41,5 @@ pyalfe download models
 
 ## Run
 ```bash
-pyalfe run UPENNGBM0000511 --input-dir alfe/input  --output-dir alfe/output
+pyalfe run UPENNGBM0000511 --input-dir pyalfe-test-data  --output-dir pyalfe-output
 ```

docs/guides/usage.md

@@ -1,38 +1,21 @@
 ## Usage
 
+We recommend running the configure command first to create a configuration file for the pipeline.
+However, you can skip to [Running the pipeline](#running-the-pipeline) section if you prefer to provide all the required configuration through command line
+options.
 ### Configuration
 To configrue the PyALFE pipeline you should run:
 ```bash
 pyalfe configure
 ```
 which prompt the you to enter the following required configurations:
 
-#### Classified directory
+#### Input directory
 ```bash
 Enter input image directory: /path/to/my_mri_data
 ```
-The classified directory (`classified_dir`) is the input directory to PyALFE and should be organized by accessions (or session ids). Inside the directory for each accession there should be a directory for each available modality.
-Here is an example that follow ALFE default structure:
-
-```
-my_mri_data
-│
-│───anat
-│   │───sub-123_T1w.nii.gz
-│   │───sub-123_T2w.nii.gz
-│   └───sub-123_FLAIR.nii.gz
-│───dwi
-│    │───sub-123_dwi.nii.gz
-│    └───sub-123_md.nii.gz
-│───swi
-│    └───sub-123_swi.nii.gz
-└───perf
-     └───sub-123_cbf.nii.gz
-
-```
-To use this directory the user should provide `path/to/my_mri_data` as the classified directory. This config value can be overwritten when calling `pyalfe run` via `-cd` or `--classified-dir` option.
-
-pyALFE also supports BIDS directories. Here is an example of input dir organized in BIDS format:
+The input directory (`input_dir`) contains the images that will be processed by PyALFE and should be organized by accessions (or session ids). Inside the directory for each accession there should be a directory for each available modality.
+Here is an example that follows ALFE default structure:
 ```
 my_mri_data
 │
@@ -46,9 +29,10 @@ my_mri_data
 │   │   └── FLAIR.nii.gz
 │   │───ADC
 │   │   └── ADC.nii.gz
-│   └───T2
-│       └── T2.nii.gz
-│
+│   │───T2
+│   │   └── T2.nii.gz
+│   └───CBF
+│       └── CBF.nii.gz
 └───12356
 .   │
 .   │───T1
@@ -62,13 +46,51 @@ my_mri_data
     └───T2
         └── T2.nii.gz
 ```
-#### Processed directory
+To use this directory the user should provide `path/to/my_mri_data` as the input directory. This config value can be overwritten when calling `pyalfe run` via `-id` or `--input-dir` option.
+
+pyALFE also supports BIDS directories. Here is an example of input dir organized in BIDS format:
+
+```
+my_mri_data
+│
+│───sub-01
+│   │───anat
+│   │   │───sub-01_T1w.nii.gz
+│   │   │───sub-01_ce-gadolinium_T1w.nii.gz
+│   │   │───sub-01_T2w.nii.gz
+│   │   └───sub-01_FLAIR.nii.gz
+│   │───dwi
+│   │    │───sub-01_dwi.nii.gz
+│   │    └───sub-01_md.nii.gz
+│   │───swi
+│   │    └───sub-01_swi.nii.gz
+│   └───perf
+│       └───sub-01_cbf.nii.gz
+│
+└───sub-02
+.   │───anat
+.   │   │───sub-02_T1w.nii.gz
+.   │   │───sub-02_ce-gadolinium_T1w.nii.gz
+    │   │───sub-02_T2w.nii.gz
+    │   └───sub-02_FLAIR.nii.gz
+    │───dwi
+    │    │───sub-02_dwi.nii.gz
+    │    └───sub-02_md.nii.gz
+    │───swi
+    │    └───sub-02_swi.nii.gz
+    └───perf
+        └───sub-02_cbf.nii.gz
+
+```
+
+#### Output directory
 ```bash
-Enter input image directory: /path/to/processed_data_dir
+Enter output image directory: /path/to/output_dir
 ```
-The processed image directory (`processed_dir`) is where ALFE writes all its output to.
+The output image directory (`output_dir`) is where pyALFE writes all its output to.
 It can be any valid path in filesystem that user have write access to.
-This config value can be overwritten when calling `pyalfe run` via `-pd` or `--processed-dir` option.
+This config value can be overwritten when calling `pyalfe run` via `-od` or `--output-dir` option.
+
 
 #### Modalities
 ```bash
@@ -102,7 +124,7 @@ image processor to use (c3d, nilearn) [c3d]:
 ```
 Currently, pyalfe can be configures to use either Convert3D (a.k.a. c3d) or Nilearn for image processing tasks.
 The default is Convert3d aka c3d. In other to use c3d,
-you have to download it using the [download command](#download-models-and-tools).
+you have to download it using the [download command](#download-models).
 To use Nilearn, you do not need to run any extra command since it is already installed when you install pyalfe.
 This config value can be overwritten when calling `pyalfe run` via `-ip` or `--image_processing` option.
 
@@ -111,10 +133,18 @@ This config value can be overwritten when calling `pyalfe run` via `-ip` or `--i
 image registration to use (greedy, ants) [greedy]:
 ```
 Currently, pyalfe can be configures to use either greedy or ants for image registration tasks. The default is greedy.
-In other to use greedy, you have to download it using the [download command](#download-models-and-tools). To use ants,
+In other to use greedy, you have to download it using the [download command](#download-models). To use ants,
 install pyalfe with ants support ``pip install pyalfe[ants]``.
 This config value can be overwritten when calling `pyalfe run` via `-ir` or `--image-registration` option.
 
+#### Dierctory Data Structure
+```bash
+data directory structure (press enter for default) (alfe, bids) [alfe]:
+```
+
+The directory structure that pyALFE expects in the input directory and will follow when creating the output. See [Inupt directory](#input-directory) for information on ALFE and BIDS.
+This config value can be overwritten when calling `payalfe run` via `-dds` or `--data-dir-structure` option.
+
 ### Running the pipeline
 To run PyALFE for an accession
 

docs/intro.md

@@ -1,7 +1,7 @@
 # PyALFE
 
-PyALFE is an open-source python Automated Lesion and Feature Extraction pipeline.
-It consumes a clinical brain MRI study consisting of various pulse sequences
+PyALFE is an open-source python pipeline for Automated Lesion and Feature Extraction.
+It can process a clinical brain MRI study consisting of various sequences
 such as T1, T1 post contrast, FLAIR, T2, ADC, and CBF. It performs
 pre-processing, inter-seq registration, template registration, segmentation,
 and quantification to generate a set of numerical human-interpretable features

pyalfe/containers.py

@@ -3,7 +3,7 @@
 
 from dependency_injector import containers, providers
 
-from pyalfe.data_structure import DefaultALFEDataDir, Modality
+from pyalfe.data_structure import DefaultALFEDataDir, BIDSDataDir, Modality
 from pyalfe.image_processing import Convert3DProcessor, NilearnProcessor
 from pyalfe.image_registration import GreedyRegistration, AntsRegistration
 from pyalfe.inference import NNUnetV2
@@ -34,10 +34,18 @@ class Container(containers.DeclarativeContainer):
     logger = logging.getLogger('Container')
     config = providers.Configuration()
 
-    pipeline_dir = providers.Singleton(
-        DefaultALFEDataDir,
-        output_dir=config.options.output_dir,
-        input_dir=config.options.input_dir,
+    pipeline_dir = providers.Selector(
+        config.options.data_dir_structure,
+        alfe=providers.Singleton(
+            DefaultALFEDataDir,
+            output_dir=config.options.output_dir,
+            input_dir=config.options.input_dir,
+        ),
+        bids=providers.Singleton(
+            BIDSDataDir,
+            output_dir=config.options.output_dir,
+            input_dir=config.options.input_dir,
+        ),
     )
 
     image_processor = providers.Selector(

pyalfe/data_structure.py

@@ -475,7 +475,7 @@ def get_output_image(
             'sub-{subject}[/ses-{session}]/{datatype}/sub-{subject}'
             '[_ce-{ceagent}][_space-{space}][_desc-{desc}]'
             '_{suffix<T1w|T2w|FLAIR|swi|asl|cbf|md|mask|dseg|probseg>}'
-            '{extension<.nii|.nii.gz>|.nii.gz}'
+            '{extension<.nii|.nii.gz|.mat>|.nii.gz}'
         ]
         entities = {
             'subject': accession,