Till Bretschneider

CelFDrive automates high-resolution 3D imaging of cells using deep learning for efficient detection of rare events in large populations.

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.

The paper generates synthetic tissue segmentation data using GANs and shows it improves segmentation performance while reducing annotation time.

The paper identifies a multi-tiered mechanical mechanism regulating the shape of the anterior neural plate during zebrafish gastrulation through combined in vivo and in silico approaches.

The paper identifies highly conserved cis-regulatory modules in zebrafish and human endoderm that control vertebrate organogenesis and are enriched for neuro-pancreatic transcription factor binding sites.

This paper introduces a curvature-enhanced random walker method for 3D cell surface segmentation, showing improved performance on Dictyostelium cells compared to existing methods.

QuimP is a software tool for analyzing transmembrane signaling in deformable cells by tracking cell outlines and quantifying fluorescence patterns over time.

This study uses computational methods to show that TOG domains accelerate microtubule growth through electrostatically guided tubulin capture and stabilization.