Domain-specific cues improve robustness of deep learning-based segmentation of CT volumes.

Machine learning has considerably improved medical image analysis in the past years. Although data-driven approaches are intrinsically adaptive and thus, generic, they often do not perform the same way on data from different imaging modalities. In particular computed tomography (CT) data poses many challenges to medical image segmentation based on convolutional neural networks (CNNs), mostly due to the broad dynamic range of intensities and the varying number of recorded slices of CT volumes.

Multi-scale imaging and analysis identify pan-embryo cell dynamics of germlayer formation in zebrafish.

The coordination of cell movements across spatio-temporal scales ensures precise positioning of organs during vertebrate gastrulation. Mechanisms governing such morphogenetic movements have been studied only within a local region, a single germlayer or in whole embryos without cell identity. Scale-bridging imaging and automated analysis of cell dynamics are needed for a deeper understanding of tissue formation during gastrulation.

Imaging, quantification and visualization of spatio-temporal patterning in mESC colonies under different culture conditions.

Motivation: Mouse embryonic stem cells (mESCs) have developed into a prime system to study the regulation of pluripotency in stable cell lines. It is well recognized that different, established protocols for the maintenance of mESC pluripotency support morphologically and functionally different cell cultures. However, it is unclear how characteristic properties of cell colonies develop over time and how they are re-established after cell passage depending on the culture conditions.