CAN-FLOW, a two-step conditional normalizing flow generator trained on LDDMM momenta from 2,208 UK Biobank hearts, produces sex-, age-, and BMI-conditioned biventricular anatomies whose variability matches the real cohort more closely than cVAE baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Flow-based conditional cardiac anatomy generation for virtual cohorts
CAN-FLOW, a two-step conditional normalizing flow generator trained on LDDMM momenta from 2,208 UK Biobank hearts, produces sex-, age-, and BMI-conditioned biventricular anatomies whose variability matches the real cohort more closely than cVAE baselines.