Interactive Feature Selection for Kidney Radiomics

Compare LASSO, Ridge, Elastic Net and stability selection on correlated size and shape features, and watch the selected subset move.

  • feature selection
  • LASSO
  • regularization
  • stability selection
  • radiomics
Features selected
2.000
Size-group selected
2.000
of 4
Shape-group selected
0.000
of 2

Coefficient magnitudes

01234500.10.20.30.40.50.6Feature|coefficient|

Selected features

Feature groups are highlighted separately because size and shape features respond very differently to penalization.
FeatureGroupCoefficient / probabilitySelected
tumor_volume_cm3Size0.074yes
tumor_surface_cm2Size0.000no
max_bbox_extent_mmSize0.000no
max_axial_area_mm2Size0.524yes
tumor_sphericityShape0.000no
bbox_elongationShape0.000no
Selection is itself a random variable
Ridge shrinks every coefficient but selects nothing; LASSO and Elastic Net threshold weak features to exactly zero, and the identity of the zeroed set changes with lambda. Stability selection reports how often a bootstrap replicate would have kept each feature — a single LASSO fit can be a coin flip away from a different subset.