ITH Score
Output
ith_scores.csv
Definition
Topological intra-tumor heterogeneity (ITH) score computed on the habitat label map. Each habitat label contributes connected-component statistics; the score increases when labels are fragmented into many small regions.
Formula
\(S_{\mathrm{total}}\) = tumor voxel count; \(S_{i,\max}\) = largest connected component of label i; \(n_i\) = number of connected components of label i.
Connected components use SimpleITK ConnectedComponent (default 6-connectivity in 3D, same as non_radiomics).
Output columns
Default (Spec("ith_score") / IthHabitatFeatures()) writes only
ith_score. Pass include_auxiliary=True to add the summaries below
(CSV export then remaps ith_num_habitats → num_habitats and
ith_total_area → total_area).
Column |
Description |
|---|---|
|
ITH score (higher = more fragmented; not clamped to [0, 1]) |
|
Auxiliary. Number of distinct habitat labels (> 0) in the map |
|
Auxiliary. \(n_i\) (component count for label i; i = actual label value) |
|
Auxiliary. \(S_{i,\max}\) |
|
Auxiliary. \(S_{i,\max} / n_i\) |
|
Auxiliary. \(S_{\mathrm{total}}\) |
Notes
HABIT applies the ITHscore topology step to an existing habitat map (*_habitats.nrrd). It does not repeat the pixel-level radiomics clustering from the original ITHscore pipeline.
Implementation
habit/compat/engines/habitat_extraction/habitat_features/ith_features.py