Metadata-Version: 2.1
Name: afids-cnn
Version: 0.2.1
Summary: 
Author: Your Name
Author-email: you@example.com
Requires-Python: >=3.8,<3.12
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: keras (>=2.12.0,<3.0.0)
Requires-Dist: numpy (>=1.22,<1.24)
Requires-Dist: pandas (>=1.3,<2)
Requires-Dist: scikit-image (>=0.19.3,<0.20.0)
Requires-Dist: snakebids (>=0.9.0,<0.10.0)
Requires-Dist: tensorflow (>=2.12.0,<3.0.0)
Requires-Dist: torch (>=1.13.1,<3.0.0)
Description-Content-Type: text/markdown

# afids-NN
Utilizing the anatomical fiducals framework to identify other salient brain regions and automatic localization of anatomical fiducials using neural networks


# Processing data for training 

Convert3D

## Anatomical landmark data (AFIDs)

Convert3D:
1) .fcsv -> threshold image -> landmark distance map (could be considered probability map) 
2) distance map used for training 

## Structural T1w imaging 

Convert3D: 
1) brainmask.nii -> 3D patches sampled at x voxels 
2) matching of distance maps and anatomical imaging patches is crucial for proper training 



