BioinformaticsIEEE International Symposium on Biomedical Imaging (ISBI)Peer-reviewed
SAMPLE-BASED TRAINING DATA FOR EFFECTIVE 3D CELL SEGMENTATION
Adam Smith, Till Bretschneider
The paper proposes a method to generate synthetic 3D cell segmentation data to reduce reliance on scarce hand-annotated samples, showing that a standard UNet trained on synthetic data can accurately segment single motile cells with branching filopodia.
DOI 10.1109/isbi61048.2026.11515764