Data

Tools

Indexes

Applications

Experiments

Open Source Science

neurite

Neural networks toolbox focused on medical image analysis

https://github.com/adalca/neurite

Science Score: 64.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ✓
    Committers with academic emails
    20 of 27 committers (74.1%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.3%) to scientific vocabulary

Keywords

brain convolutional-neural-networks keras medical-image-computing medical-imaging python tensorflow

Keywords from Contributors

diffeomorphism image-alignment image-registration optical-flow probabilistic unsupervised-learning
Last synced: 6 months ago · JSON representation ·

Repository

Neural networks toolbox focused on medical image analysis

Basic Info
  • Host: GitHub
  • Owner: adalca
  • License: apache-2.0
  • Language: Python
  • Default Branch: dev
  • Homepage:
  • Size: 2.28 MB
Statistics
  • Stars: 362
  • Watchers: 20
  • Forks: 71
  • Open Issues: 20
  • Releases: 0
Topics
brain convolutional-neural-networks keras medical-image-computing medical-imaging python tensorflow
Created almost 9 years ago · Last pushed 6 months ago
Metadata Files
Readme License Citation

README.md

Neurite

A neural networks toolbox with a focus on medical image analysis in tensorflow/keras for now.

⚠️ Warning: neurite is under active development. We are in the process of finalizing the structure for PyTorch -- interfaces may change.

Install

To use the Neurite library, either clone this repository and install the requirements listed in setup.py or install directly with pip.

pip install neurite

Main tools

  • layers: various network layers, sparse operations (e.g. SpatiallySparse_Dense), and LocallyConnected3D currently not included in keras
  • utils: various utilities, including interpn: N-D gridded interpolation, and several nonlinearities
    • model: stack_models: keras model stacking
    • vae: tools for analyzing (V)AE style models
    • seg: segmentation tools
  • models: flexible models (many parameters to play with) particularly useful in medical image analysis, such as UNet/hourglass model, convolutional encoders and decoders
  • generators: generators for medical image volumes and various combinations of volumes, segmentation, categorical and other output
  • callbacks: a set of callbacks for keras training to help with understanding your fit, such as Dice measurements and volume-segmentation overlaps
  • dataproc: a set of tools for processing medical imaging data for preparation for training/testing
  • metrics: metrics (most of which can be used as loss functions), such as Dice or weighted categorical crossentropy
  • plot: plotting tools, mostly for debugging models

Papers:

If you use this code, please cite:

Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation
Adrian V. Dalca, John Guttag, Mert R. Sabuncu
CVPR 2018.
[ PDF | arxiv | bibtex ]

If you are using any of the sparse/imputation functions, please cite:

Unsupervised Data Imputation via Variational Inference of Deep Subspaces
Adrian V. Dalca, John Guttag, Mert R. Sabuncu
Arxiv preprint 2019
[ arxiv | bibtex ]

Development:

We welcome contributions; please make sure your code respects pep8, except for E731,W291,W503,W504, by running:
pycodestyle --ignore E731,W291,W503,W504 --max-line-length 100 /path/to/neurite
Please open an issue [preferred] or contact Adrian Dalca at adalca@csail.mit.edu for question related to neurite.

Use/demos:

Parts of neurite were used in VoxelMorph and brainstorm, which we encourage you to check out!

Owner

  • Name: Adrian Dalca
  • Login: adalca
  • Kind: user
  • Location: Cambridge, MA
  • Company: MIT

Professor at Harvard Medical School, Researcher at MIT. Machine Learning in Medical Image Analysis, computer vision.

Citation (citations.bib) 

@inproceedings{dalca2018anatomical,
  title={Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation},
  author={Dalca, Adrian V and Guttag, John and Sabuncu, Mert R},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={9290--9299},
  year={2018}
}

@article{dalca2019imputation,
  title={Unsupervised Data Imputation via Variational Inference of Deep Subspaces},
  author={Dalca, Adrian V and Guttag, John and Sabuncu, Mert R},
  journal={arXiv preprint arXiv:1903.03503},
  year={2019}
}

@article{hoffmann2021learning,
  title={Learning MRI Contrast-Agnostic Registration},
  author={Hoffmann, Malte and Billot, Benjamin and Eugenio Iglesias, Juan and Fischl, Bruce and Dalca, Adrian V},
  journal={ISBI: IEEE International Symposium on Biomedical Imaging},
  pages={899--903},
  year={2021}
}

@article{hoffmann2022synthmorph,
  title={SynthMorph: learning contrast-invariant registration without acquired images},
  author={Hoffmann, Malte and Billot, Benjamin and Greve, Douglas N and Iglesias, Juan Eugenio and Fischl, Bruce and Dalca, Adrian V},
  journal={IEEE Transactions on Medical Imaging},
  volume={41},
  number={3},
  pages={543--558},
  year={2022},
  publisher={IEEE}
}

GitHub Events

Total
  • Issues event: 2
  • Watch event: 22
  • Delete event: 1
  • Member event: 1
  • Issue comment event: 5
  • Push event: 58
  • Pull request event: 11
  • Fork event: 6
  • Create event: 1
Last Year
  • Issues event: 2
  • Watch event: 22
  • Delete event: 1
  • Member event: 1
  • Issue comment event: 5
  • Push event: 58
  • Pull request event: 11
  • Fork event: 6
  • Create event: 1

Committers

Last synced: about 2 years ago

All Time
  • Total Commits: 670
  • Total Committers: 27
  • Avg Commits per committer: 24.815
  • Development Distribution Score (DDS): 0.399
Past Year
  • Commits: 15
  • Committers: 5
  • Avg Commits per committer: 3.0
  • Development Distribution Score (DDS): 0.467
Top Committers
Name Email Commits
adalca a****a@m****u 403
Adrian Dalca a****a@s****u 68
Malte Hoffmann m****n@m****u 47
Andrew Hoopes a****1@g****m 42
Adrian Dalca a****a@t****u 21
Adrian Dalca g****v@e****u 20
Adrian Dalca a****a@a****u 12
Bruce Fischl f****l@n****u 8
Danielle Pace d****e@m****u 8
Sean Doyle s****e@p****g 6
Adrian Dalca a****a@m****u 6
Adrian Dalca g****v@e****u 5
Adrian Dalca a****a@s****u 3
Andrew Hoopes a****s 2
Neel Dey 4****y 2
Adrian Dalca a****a@a****u 2
Adrian Dalca a****a@s****u 2
Hallee Wong h****1@w****u 2
adalca a****2@t****u 2
ahoopes h****s@m****u 2
Adrian Dalca a****a@h****u 1
Andrew Hoopes a****s@m****u 1
Hallee Wong h****e@m****u 1
kinshuk1207 9****7 1
Avnish Kumar a****s 1
Robert Pollak r****k@p****t 1
Zhilu Zhang z****2@c****u 1
Committer Domains (Top 20 + Academic)
mit.edu: 3 mgh.harvard.edu: 3 sumac.csail.mit.edu: 1 turmeric.csail.mit.edu: 1 en-ec-sablab-gpu01.coecis.cornell.edu: 1 advieh.csail.mit.edu: 1 nmr.mgh.harvard.edu: 1 partners.org: 1 mars.csail.mit.edu: 1 en-ec-sablab-gpu06.coecis.cornell.edu: 1 sesame.csail.mit.edu: 1 athelas.csail.mit.edu: 1 salep.csail.mit.edu: 1 williams.edu: 1 tebo.nmr.mgh.harvard.edu: 1 hops.csail.mit.edu: 1 posteo.net: 1 cornell.edu: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 18
  • Total pull requests: 82
  • Average time to close issues: 23 days
  • Average time to close pull requests: 13 days
  • Total issue authors: 18
  • Total pull request authors: 17
  • Average comments per issue: 1.33
  • Average comments per pull request: 0.17
  • Merged pull requests: 70
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 2
  • Pull requests: 12
  • Average time to close issues: 3 days
  • Average time to close pull requests: 21 days
  • Issue authors: 2
  • Pull request authors: 2
  • Average comments per issue: 3.5
  • Average comments per pull request: 0.17
  • Merged pull requests: 12
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • jackyko1991 (1)
  • ywyz233 (1)
  • dwang6524 (1)
  • jondo (1)
  • haoyayuzzz (1)
  • sergiumocanu (1)
  • Kanyq (1)
  • FishJyz (1)
  • vasl12 (1)
  • huangmozhilv (1)
  • patleitao (1)
  • zozo19999 (1)
  • adalca (1)
  • timroelofs123 (1)
  • joshuacwnewton (1)
Pull Request Authors
  • mu40 (66)
  • Catherine0505 (6)
  • EtienneChollet (4)
  • adalca (4)
  • ahoopes (2)
  • aviziskind (2)
  • halleewong (2)
  • ajinkya-kulkarni (2)
  • neel-dey (2)
  • kousu (1)
  • jondo (1)
  • avnishks (1)
  • DLPerf (1)
  • junyuchen245 (1)
  • tosemml (1)
Top Labels
Issue Labels
enhancement (1) tf-version-bug (1) bug (1)
Pull Request Labels
bug (1) enhancement (1)

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 7,201 last-month
  • Total docker downloads: 923
  • Total dependent packages: 1
  • Total dependent repositories: 17
  • Total versions: 2
  • Total maintainers: 1
pypi.org: neurite

Neural Networks Toolbox for Medical Imaging

  • Versions: 2
  • Dependent Packages: 1
  • Dependent Repositories: 17
  • Downloads: 7,201 Last month
  • Docker Downloads: 923
Rankings
Docker downloads count: 1.7%
Dependent repos count: 3.5%
Stargazers count: 3.6%
Average: 3.9%
Downloads: 4.2%
Dependent packages count: 4.8%
Forks count: 5.3%
Maintainers (1)
adalca
Last synced: 6 months ago

Dependencies

setup.py pypi
  • matplotlib *
  • nibabel *
  • numpy >=1.17
  • packaging *
  • pystrum >=0.2
  • scikit-learn *
  • scipy *
  • six *
  • tqdm *