{
    "info": {
        "author": "Wouter Kouw",
        "author_email": "wmkouw@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "License :: OSI Approved :: MIT License",
            "Operating System :: POSIX :: Linux",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3.6",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Scientific/Engineering :: Image Recognition"
        ],
        "description": "[![Coverage](https://scrutinizer-ci.com/g/wmkouw/mrai-net/badges/coverage.png?b=master)](https://scrutinizer-ci.com/g/wmkouw/mrai-net/statistics/)\n[![BuildStatus](https://travis-ci.org/wmkouw/mrai-net.svg?branch=master)](https://travis-ci.org/wmkouw/mrai-net) [![Docs](https://media.readthedocs.org/static/projects/badges/passing-flat.svg)](https://mrai-net.readthedocs.io/en/latest/index.html) ![Python version](https://img.shields.io/badge/python-3.5%2C%203.6-blue.svg) [![DOI](https://zenodo.org/badge/95411302.svg)](https://zenodo.org/badge/latestdoi/95411302)\n\n# MR Acquisition-Invariant Neural Network\n\nThis repository contains experiments and code accompanying the paper:\n\n\"MR Acquisition-Invariant Representation Learning\"\n\nwhich is currently under review. The preprint is on [ArXiv](https://arxiv.org/abs/1709.07944).\n\n## Installation\n\nmrainet can be installed through:\n```shell\npip install mrainet\n```\n\nPyPI takes care of all dependencies. However, to ensure that these don't mess up your current python environment, you should set up a virtual one. If you're familiar with [conda](https://conda.io/docs/), you can do this through:\n```\nconda env create -f environment.yml\nsource activate mrainet\n```\n\n## Usage\n\nPlease visit the [examples](https://mrai-net.readthedocs.io/en/latest/examples.html) section in the documentation to get started.\n\nTo give you an impression of how the module is used, here's an example call:\n```python\nfrom mrainet.mraicnn import MRAIConvolutionalNeuralNetwork\n\nM = MRAIConvolutionalNeuralNetwork()\nM.train(X,Y,Z,U)\n\nH = M.feedforward(X)\n```\nwhere X are MRI-scans from the source scanner, Y are their corresponding segmentations, Z are MRI-scans from the target scanner, and U is its corresponding incomplete segmentations (nearly all are NaN). H represents the patches fed through the network and embedded in MRAI-net's penultimate layer (MRAI representation).\n\nFor more information on individual classes, methods and functions, visit the [docs](https://mrai-net.readthedocs.io/en/latest/).\n\n## Data\n\nIn order to isolate MRI-scanner acquisition-based variation in medical images, we simulated datasets of varying scan protocol parameters using [SIMRI](https://www.ncbi.nlm.nih.gov/pubmed/15705518). High-quality human brain phantoms were used, which can be found here:\n- [Brainweb](http://brainweb.bic.mni.mcgill.ca/)\n\n\nThe original code for SIMRI can be downloaded from [here](https://sourceforge.net/projects/simri/). Our repo contains a modified version of SIMRI that includes the additional NMR relaxation times, as described in the paper's appendix. For more information on how to run your own simulations, see the example shell script named `run_simulation.sh` in the folder `data/brainweb/simulator`.\n\nReal data consisted of the MRBrainS data set, known from the brain tissue segmentation challenge at MICCAI 2013.\n- [MRBrainS](http://mrbrains13.isi.uu.nl/)\n\nWe used only the 5 training scans provided, as the labels for the remaining 15 scans have not been released.\n\n## Experiments\n\nExperimental scripts from the paper are included in this repository:\n- `exp-mrai-cnn_b1b3`: simulated data from MRI-scanners with different acquisition protocols.\n- `exp_mrai-cnn_b1mb`: simulated data as souce and real data as target, for different field strengths.\n- `exp_mrai-cnn_b3mb`: simulated data as souce and real data as target, for equivalent field strengths.\n\nFor more information on experiment parameters and setup, see the [README](https://github.com/wmkouw/mrai-net/tree/master/experiments) in the experiments folder.\n\n## Contact\nBugs, comments and questions can be submitted to the [issues tracker](https://github.com/wmkouw/mrai-net/issues).\n\n\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/wmkouw/mrai-net",
        "keywords": "",
        "license": "Apache 2.0",
        "maintainer": "",
        "maintainer_email": "",
        "name": "mrainet",
        "package_url": "https://pypi.org/project/mrainet/",
        "platform": "",
        "project_url": "https://pypi.org/project/mrainet/",
        "project_urls": {
            "Homepage": "https://github.com/wmkouw/mrai-net"
        },
        "release_url": "https://pypi.org/project/mrainet/0.1.0/",
        "requires_dist": [
            "numpy (>=1.12.1)",
            "numpydoc (>=0.7.0)",
            "scipy (>=0.11)",
            "matplotlib (>=2.0.2)",
            "ipython (>=5.5.0)",
            "Sphinx (>=1.6.6)",
            "nibabel (>=2.2.1)",
            "scikit-learn (>=0.15.0)",
            "tensorflow (>=0.12.1)",
            "Keras (>=2.0.0)"
        ],
        "requires_python": "",
        "summary": "MR acquisition-invariant network.",
        "version": "0.1.0"
    },
    "last_serial": 4079698,
    "releases": {
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a24474506877e906363b58e15398e0ac",
                    "sha256": "cad2a2c934a856d8ca552e843411003a9ed84760627afa698be0454e717ec3c3"
                },
                "downloads": -1,
                "filename": "mrainet-0.1.0-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "a24474506877e906363b58e15398e0ac",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 25438,
                "upload_time": "2018-07-18T20:07:40",
                "url": "https://files.pythonhosted.org/packages/e9/01/d6334ace1608b83a3daa5c88cf2c4329e88d2d32f5b749cc3e719e473035/mrainet-0.1.0-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "2cc83ac16e06e4101fc97e13c5ebcece",
                    "sha256": "c5ff3711bec5328f4a548f1ed7d3b87069f39075b29032fa65535d9d55cd95ad"
                },
                "downloads": -1,
                "filename": "mrainet-0.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "2cc83ac16e06e4101fc97e13c5ebcece",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 20336,
                "upload_time": "2018-07-18T20:07:41",
                "url": "https://files.pythonhosted.org/packages/6c/36/3fa55c96a1db7f702278580f8b3a1de2bee012ba6834d9d0c1539e995d8a/mrainet-0.1.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "a24474506877e906363b58e15398e0ac",
                "sha256": "cad2a2c934a856d8ca552e843411003a9ed84760627afa698be0454e717ec3c3"
            },
            "downloads": -1,
            "filename": "mrainet-0.1.0-py2.py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "a24474506877e906363b58e15398e0ac",
            "packagetype": "bdist_wheel",
            "python_version": "py2.py3",
            "requires_python": null,
            "size": 25438,
            "upload_time": "2018-07-18T20:07:40",
            "url": "https://files.pythonhosted.org/packages/e9/01/d6334ace1608b83a3daa5c88cf2c4329e88d2d32f5b749cc3e719e473035/mrainet-0.1.0-py2.py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "2cc83ac16e06e4101fc97e13c5ebcece",
                "sha256": "c5ff3711bec5328f4a548f1ed7d3b87069f39075b29032fa65535d9d55cd95ad"
            },
            "downloads": -1,
            "filename": "mrainet-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "2cc83ac16e06e4101fc97e13c5ebcece",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 20336,
            "upload_time": "2018-07-18T20:07:41",
            "url": "https://files.pythonhosted.org/packages/6c/36/3fa55c96a1db7f702278580f8b3a1de2bee012ba6834d9d0c1539e995d8a/mrainet-0.1.0.tar.gz"
        }
    ]
}