nipreps · oesteban · Mar 8, 2017 · Mar 8, 2017 · Mar 8, 2017 · Mar 8, 2017
diff --git a/README.rst b/README.rst
@@ -1,7 +1,7 @@
 mriqc: image quality metrics for quality assessment of MRI
 ==========================================================
 
-This pipeline is developed by `the Poldrack Lab at Stanford University
+MRIQC is developed by `the Poldrack Lab at Stanford University
 <https://poldracklab.stanford.edu>`_ for use at the `Center for Reproducible
 Neuroscience (CRN) <http://reproducibility.stanford.edu>`_, as well as
 for open-source software distribution.
@@ -16,7 +16,7 @@ for open-source software distribution.
 .. image:: https://api.codacy.com/project/badge/grade/fbb12f660141411a89ba1ae5bf873717
   :target: https://www.codacy.com/app/code_3/mriqc
 
-.. image:: https://coveralls.io/repos/github/poldracklab/mriqc/badge.svg?branch=master 
+.. image:: https://coveralls.io/repos/github/poldracklab/mriqc/badge.svg?branch=master
   :target: https://coveralls.io/github/poldracklab/mriqc?branch=master
 
 .. image:: https://codecov.io/gh/poldracklab/mriqc/branch/master/graph/badge.svg
@@ -42,62 +42,37 @@ for open-source software distribution.
 About
 -----
 
-The package provides a series of image processing workflows to extract and
-compute a series of NR (no-reference), IQMs (image quality metrics) to be 
-used in QAPs (quality assessment protocols) for MRI (magnetic resonance imaging).
-
-This open-source neuroimaging data processing tool is being developed as a
-part of the MRI image analysis and reproducibility platform offered by
+MRIQC extracts no-reference IQMs (image quality metrics) from
+structural (T1w and T2w) and functional MRI (magnetic resonance imaging)
+data.
+
+MRIQC is an open-source project, developed under the following
+software engineering principles:
+
+1. Modularity and integrability: MRIQC implements a
+nipype workflow to integrate modular sub-workflows that rely upon third
+party software toolboxes such as FSL, ANTs and AFNI.
+2. Minimal preprocessing: the workflow described before should be as minimal
+as possible to estimate the IQMs on the original data or their minimally processed
+derivatives.
+3. Interoperability and standards: MRIQC follows the the brain imaging data structure
+(BIDS), and it adopts the BIDS-App standard.
+4. Reliability and robustness: the software undergoes frequent vetting sprints
+by testing its robustness against data variability (acquisition parameters,
+physiological differences, etc.) using images from the OpenfMRI resource.
+Reliability is checked and maintained with the use of a continuous
+integration service.
+
+
+MRIQC is part of the MRI image analysis and reproducibility platform offered by
 the CRN. This pipeline derives from, and is heavily influenced by, the
 `PCP Quality Assessment Protocol <http://preprocessed-connectomes-project.github.io/quality-assessment-protocol>`_.
 
-This tool extracts a series of IQMs from structural and functional MRI data.
-It is also scheduled to add diffusion MRI to the target imaging families.
-
-
-External Dependencies
----------------------
-
-``mriqc`` is implemented using ``nipype``, but it requires some other neuroimaging
-software tools:
-
-- `FSL <http://fsl.fmrib.ox.ac.uk/fsl/fslwiki/>`_.
-- The N4ITK bias correction tool released with `ANTs <http://stnava.github.io/ANTs/>`_.
-- `AFNI <https://afni.nimh.nih.gov/>`_.
-
-These tools must be installed and their binaries available in the 
-system's ``$PATH``.
-
-
-Installation
-------------
-
-The ``mriqc`` is packaged and available through the PyPi repository.
-Therefore, the easiest way to install the tool is: ::
-
-    pip install mriqc
-
-
-
-Execution and the BIDS format
------------------------------
-
-The ``mriqc`` workflow takes as principal input the path of the dataset
-that is to be processed.
-The only requirement to the input dataset is that it has a valid `BIDS (Brain
-Imaging Data Structure) <http://bids.neuroimaging.io/>`_ format.
-This can be easily checked online using the 
-`BIDS Validator <http://incf.github.io/bids-validator/>`_.
-
-Example command line: ::
-
-    mriqc -i ~/Data/bids_dataset -o out/ -w work/
-
 
 Support and communication
 -------------------------
 
-The documentation of this project is found here: http://mriqc.readthedocs.org/en/latest/.
+The documentation of this project is found here: http://mriqc.readthedocs.org/.
 
 If you have a problem or would like to ask a question about how to use ``mriqc``,
 please submit a question to NeuroStars.org with an ``mriqc`` tag.
@@ -106,7 +81,7 @@ NeuroStars.org is a platform similar to StackOverflow but dedicated to neuroinfo
 All previous ``mriqc`` questions are available here:
 http://neurostars.org/t/mriqc/
 
-To participate in the ``mriqc`` development-related discussions please use the 
+To participate in the ``mriqc`` development-related discussions please use the
 following mailing list: http://mail.python.org/mailman/listinfo/neuroimaging
 Please add *[mriqc]* to the subject line when posting on the mailing list.
 
@@ -132,5 +107,5 @@ the ``mriqc`` distribution.
 All trademarks referenced herein are property of their respective
 holders.
 
-Copyright (c) 2015-2016, the mriqc developers and the CRN.
+Copyright (c) 2015-2017, the mriqc developers and the CRN.
 All rights reserved.
diff --git a/circle.yml b/circle.yml
@@ -38,6 +38,7 @@ general:
   branches:
     ignore:
       - gh-pages # ignore gh-pages
+      - doc/* # ignore all doc-related branches
 
 # deployment:
 #   codecov:

diff --git a/docs/source/about.rst b/docs/source/about.rst
@@ -0,0 +1,6 @@
+
+Introduction
+============
+
+.. include:: ../../README.rst
+   :start-line: 44
diff --git a/docs/source/classifier.rst b/docs/source/classifier.rst
@@ -1,42 +1,17 @@
-The MRIQC classifier for T1w images
-===================================
-
-MRIQC is shipped with a random-forests classifier, using the combination of the 
-`ABIDE <http://fcon_1000.projects.nitrc.org/indi/abide/>`_ and 
-`DS030 <https://openfmri.org/dataset/ds000030/>`_ datasets as training sample.
-
-
-To predict the quality labels (0="accept", 1="reject") on a features table
-computed by ``mriqc`` with the default classifier, the command line
-is as follows:
-
-  ::
-
-      mriqc_clf --load-classifier -X aMRIQC.csv -o mypredictions.csv
-
 
-where ``aMRIQC.csv`` is the file generated by the ``group`` level run of
-``mriqc``.
+.. _classifier:
 
-Custom classifiers can be fitted using the same ``mriqc_clf`` tool in fitting
-mode:
-
-  ::
-
-      mriqc_clf --train aMRIQC_train.csv labels.csv --log-file fit_clf.log --save-classifier myclassifier.pklz
-
-where ``aMRIQC_train.csv`` contains the IQMs calculated by ``mriqc`` and ``labels.csv`` contains
-the matching ratings assigned by an expert.
-The labels can be numerical (``-1``= exclude, ``0``= doubtful, ``1`` = accept) or textual ("bad", "fail" can be
-used for exclude; "may be" or "maybe" for doubtful and "ok", "good" for accept).
-
-The trained classifier can be then used for prediction on unseen data with
-the command at the top, indicating now which classifier should be used:
+===================================
+The MRIQC classifier for T1w images
+===================================
 
-  ::
+.. automodule:: mriqc.classifier
+    :members:
+    :undoc-members:
+    :show-inheritance:
 
-      mriqc_clf --load-classifier myclassifier.pklz -X aMRIQC.csv -o mypredictions.csv
 
+Contents
+--------
 
-Predictions are stored as a CSV file, containing the BIDS identifiers as
-indexing columns and the predicted quality label under the ``prediction`` column.
+- py:module:`~mriqc.classifier.cv`
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -46,6 +46,7 @@
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
+    'mriqc.sphinxext.plot_workflow',
     'sphinx.ext.autodoc',
     'sphinx.ext.doctest',
     'sphinx.ext.intersphinx',

diff --git a/docs/source/cv/helpers.rst b/docs/source/cv/helpers.rst
@@ -0,0 +1,8 @@
+
+.. _crossvalidation:
+
+
+.. automodule:: mriqc.classifier.cv
+    :members:
+    :undoc-members:
+    :show-inheritance:
diff --git a/docs/source/cv/sklearn_ext.rst b/docs/source/cv/sklearn_ext.rst
@@ -0,0 +1,9 @@
+
+
+.. _sklearn_ext:
+
+
+.. automodule:: mriqc.classifier.sklearn_extension
+    :members:
+    :undoc-members:
+    :show-inheritance:
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -7,18 +7,23 @@ Welcome to mriqc's documentation!
 =================================
 
 .. include:: ../../README.rst
-
+   :start-line: 3
+   :end-line: 39
 
 Contents
 ========
 
 .. toctree::
-   :maxdepth: 3
+   :maxdepth: 2
 
-   userguide
+   about
+   install
+   running
    measures
    docker
    classifier
+   reports
+   workflows
 
 
 Indices and tables

diff --git a/docs/source/install.rst b/docs/source/install.rst
@@ -0,0 +1,22 @@
+
+Installation
+------------
+
+We have included ``mriqc`` in the PyPi resource ::
+
+  pip install mriqc
+
+
+Execution system dependencies
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If you are using a linux distribution with `neurodebian <http://neuro.debian.net/>`_, installation
+should be as easy as::
+
+  sudo apt-get fsl afni ants
+  sudo ln -sf /usr/lib/ants/N4BiasFieldCorrection /usr/local/bin/
+
+After installation, make sure that all the necessary binaries are added to the ``$PATH`` environment
+variable, for the profile used run ``mriqc``.
+
+Otherwise, you can follow each software installation guide: `FSL <http://fsl.fmrib.ox.ac.uk/fsl/fslwiki/FslInstallation>`_, `AFNI <https://afni.nimh.nih.gov/afni/doc/howto/0>`_, and `ANTs <http://stnava.github.io/ANTs/>`_.
diff --git a/docs/source/iqms/bold.rst b/docs/source/iqms/bold.rst
@@ -0,0 +1,11 @@
+
+.. _bold:
+
+
+IQMs for functional images
+--------------------------
+
+.. automodule:: mriqc.qc.functional
+    :members:
+    :undoc-members:
+    :show-inheritance:
diff --git a/docs/source/iqms/t1w.rst b/docs/source/iqms/t1w.rst
@@ -0,0 +1,11 @@
+
+.. _t1w:
+
+
+IQMs for structural images
+--------------------------
+
+.. automodule:: mriqc.qc.anatomical
+    :members:
+    :undoc-members:
+    :show-inheritance: