VoxelFeatureExtractor

Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.

class VoxelFeatureExtractor(*args, **kwargs)

Bases: Protocol

Turn a subject’s images into per-voxel feature vectors inside the ROI.

Implementations in HABIT cover raw intensity, kinetic curves, local entropy, and voxel-wise radiomics. Because this is a protocol rather than a hard-coded branch, an external group can plug in voxel embeddings from a self-supervised or foundation model without modifying HABIT.

property spec: Spec

Return the algorithm specification, used for provenance and caching.

__call__(subject: Subject) → VoxelFeatureField

Compute per-voxel features for one subject.

Parameters:

subject – Subject providing images and the ROI mask.

Returns:

Feature vectors for every voxel inside the ROI.

Raises:

GeometryError – If the required modalities and the mask do not share a compatible voxel grid.

__init__(*args, **kwargs)