Evidence grade: WEAK — Supported only by weak or preliminary evidence.
The hand-crafted radiomics enterprise rests on reproducibility that is largely retrospective; if signal cannot survive prospective standardization it will not translate.
IBSI/ComBat make features poolable, but harmonization can remove real biological variance along with batch effect.
Prospective standardized-acquisition study comparing pre-specified radiomic signatures with and without harmonization against outcome; quantify biology-vs-batch tradeoff.
This is an educational research resource from Resonant Labs, not clinical advice. Evidence grades and controversies are summarized from the literature and may change as the field evolves.