Ensembling U-Nets for Rare Chromosomal Aberration Detection in Metaphase Images, Uncertainty Quantification, and Ionizing Radiation Dose Estimation

Abstract

We present an ensembling U-Net approach for automated detection of rare chromosomal aberrations in metaphase images, combined with uncertainty quantification and dose-response modelling using quasi-Poisson regression, supporting reliable biodosimetry for ionizing radiation exposure assessment.