ANTsPyT1w
reference processing for t1-weighted neuroimages (human)
the outputs of these processes can be used for data inspection/cleaning/triage as well for interrogating neuroscientific hypotheses.
this package also keeps track of the latest preferred algorithm variations for production environments.
install by calling (within the source directory):
python setup.py install
or install via pip install antspyt1w
what this will do
-
provide example data
-
brain extraction
-
denoising
-
n4 bias correction
-
brain parcellation into tissues, hemispheres, lobes and regions
-
hippocampus specific segmentation
-
t1 hypointensity segmentation and classification exploratory
-
deformable registration with robust and repeatable parameters
-
registration-based labeling of major white matter tracts
-
helpers that organize and annotate segmentation variables into data frames
-
hypothalamus segmentation FIXME/TODO
the two most time-consuming processes are hippocampus-specific segentation (because it uses augmentation) and registration. both take 10-20 minutes depending on your available computational resources and the data. both could be made computationally cheaper at the cost of accuracy/reliability.
first time setup
import antspyt1w
antspyt1w.get_data()
NOTE: get_data has a force_download option to make sure the latest
package data is installed.
example processing
import os
os.environ["TF_NUM_INTEROP_THREADS"] = "8"
os.environ["TF_NUM_INTRAOP_THREADS"] = "8"
os.environ["ITK_GLOBAL_DEFAULT_NUMBER_OF_THREADS"] = "8"
import antspyt1w
import antspynet
import ants
##### get example data + reference templates
# NOTE: PPMI-3803-20120814-MRI_T1-I340756 is a good example of our naming style
# Study-SubjectID-Date-Modality-UniqueID
# where Modality could also be measurement or something else
fn = antspyt1w.get_data('PPMI-3803-20120814-MRI_T1-I340756', target_extension='.nii.gz' )
img = ants.image_read( fn )
# generalized default processing
myresults = antspyt1w.hierarchical( img, output_prefix = '/tmp/XXX' )
##### organize summary data into data frames - user should pivot these to columns
# and attach to unique IDs when accumulating for large-scale studies
# see below for how to easily pivot into wide format
# https://stackoverflow.com/questions/28337117/how-to-pivot-a-dataframe-in-pandas
An example "full study" (at small scale) is illustrated in ~/.antspyt1w/run_dlbs.py
which demonstrates/comments on:
- how to aggregate dataframes
- how to pivot to wide format
- how to join with a demographic/metadata file
- visualizing basic outcomes.
ssl error
if you get an odd certificate error when calling force_download, try:
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
to publish a release
before doing this - make sure you have a recent run of pip-compile pyproject.toml
rm -r -f build/ antspyt1w.egg-info/ dist/
python3 -m build .
python3 -m pip install --upgrade twine
python3 -m twine upload --repository antspyt1w dist/*
Metadata
Release files for antspyt1w 1.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| antspyt1w-1.1.3.tar.gz | 48.5 kB | Without provenance | Details for antspyt1w-1.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| antspyt1w-1.1.3-py3-none-any.whl | Python 3 | none | any | Details for antspyt1w-1.1.3-py3-none-any.whl |
Total release size: 89.8 kB
Release files / antspyt1w-1.1.3.tar.gz
| Download URL | antspyt1w-1.1.3.tar.gz |
|---|---|
| Size | 48.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e6c8cd83682fc09161ccffb23d3ab9bac020e769e4d1f5ee57690aea601eb0d1
|
|
BLAKE2b-256 checksum How to use checksums |
3fb26affdbac4ca7cb39f9664483093515a645c9fd37f2ff283cd127b45093a0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.9
|
Release files / antspyt1w-1.1.3-py3-none-any.whl
| Download URL | antspyt1w-1.1.3-py3-none-any.whl |
|---|---|
| Size | 41.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fc36829b8e6fc62aa443669567ffe0ce6891e17ec39a46667fbcb9130c616a4c
|
|
BLAKE2b-256 checksum How to use checksums |
55965b9fc7be46edfac10c8d67307ad6f8a29e1859e22a2a6ea28c9ccb339fb2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.9
|
Security for antspyt1w 1.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.