Package to calculate and classify ICAs using MEGNET deep learning architecture
Project description
MEGNET
This repository is a fork of the code listed below in the original code reference. This repository adds an automated processing wrapper and python package installation around the original codebase. The current codebase utilizes mne python to preprocess the data, generate the infomax ICA components (n=20), circular topography maps, and timeseries outputs. The architecture of neural net has been preserved, however, the weights have been reset to uniform distribution and retrained using repository data from MEGIN, CTF, 4D, and KIT systems.
Install
conda create -n megnet 'mne>=1.6' 'python<3.12'
conda activate megnet
pip install git+https://github.com/nih-megcore/MegNet.git
Post install initalization (downloading huggingface model weights)
megnet_init
Original Code Repository
https://github.com/DeepLearningForPrecisionHealthLab/MegNET_2020
Manuscript available: https://pubmed.ncbi.nlm.nih.gov/34274419/
DOI: https://doi.org/10.1016/j.neuroimage.2021.118402
PMID: 34274419
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file megnet_neuro-0.3.1.tar.gz.
File metadata
- Download URL: megnet_neuro-0.3.1.tar.gz
- Upload date:
- Size: 49.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9b5599537291c3baac612f79e18096653855a53de6dfa26ea915bb9953fc5a0c
|
|
| MD5 |
93423be0257b8205ee5eac3470f83d29
|
|
| BLAKE2b-256 |
3fd6e2f821974b71706fde0c376c784afce7e9f23fa19ee64f8e1113746bf2b0
|
File details
Details for the file megnet_neuro-0.3.1-py3-none-any.whl.
File metadata
- Download URL: megnet_neuro-0.3.1-py3-none-any.whl
- Upload date:
- Size: 70.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
db5ff3b9cc43d1aa1e816ef0110ed561517b54b8e2bbf3accb4e81ec3425e7b4
|
|
| MD5 |
7f24f8a7a0aa90e0a038b3feec8a7bc7
|
|
| BLAKE2b-256 |
374f8f4a318d8ab77a5835d3980ac56778365832cc13c00bff8fd3d168b0dcba
|
