Anna Kreshuk

The paper discusses AI4Life's Open Calls and Public Challenges, highlighting the state of bioimage analysis, tool availability, and the need for better data and infrastructure.

This paper introduces an automated workflow for cryo-volume EM that improves resolution and enables structural analysis of vitrified cells and tissues.

This paper introduces a modular cryogenic light microscope for single-molecule localization microscopy, improving stability and reducing ice contamination in cryo-CLEM.

The paper identifies a pressure-sensitive aboral valve in cnidarians that regulates hydraulic pressure during morphogenesis through mesogleal basement membrane dynamics.

This paper introduces a framework for high-plex spectral imaging using DNA-barcoded labeling and programmable signal amplification to improve panel design and unmixing accuracy.

CryoSiam is a self-supervised framework for cryo-ET data analysis that learns hierarchical representations and transfers to experimental data for denoising, segmentation, and macromolecular detection.

The paper maps a whole-body single-cell transcriptome into an electron microscopy volume of an annelid worm to study cellular morphology and gene regulation.

FeatureForest uses foundation model embeddings with random forests to enable fast, accurate segmentation of complex biological images with minimal labeling.

Spotiflow improves spot detection in microscopy images using deep learning, achieving subpixel accuracy and efficiency across diverse datasets.

This paper introduces a method to quantify intensity distribution in 3D and 2D microscopy data using spherical harmonics, demonstrating its application across various biological systems.

This study creates a spatiotemporal atlas of mouse gastrulation and early organogenesis using spatial transcriptomics and scRNA-seq, revealing gene expression dynamics and mesodermal fate decisions.

The paper shows that stochastic division timing and cell mechanics contribute to robust embryo patterning and morphogenesis in mammals.

The paper introduces computational tools for 3D nuclei segmentation and analysis, showing variations in nuclear-to-cell volume ratios across tissues.

This study develops an engineered uterus-like microenvironment to study mouse embryo implantation, revealing coordination between trophoblast migration and embryo growth.

MoBIE is a Fiji plugin that enables visualization, sharing, and management of large, multi-modal image data across platforms.

DeePiCt is a deep-learning framework for segmenting and localizing macromolecular complexes in cryo-electron tomograms, showing effectiveness in identifying low-abundance structures across species.

The paper introduces an unsupervised method to extract morphological features from 3D EM data, enabling cell type and tissue organization analysis in a segmented worm.

The BioImage Model Zoo provides a community standard, infrastructure, and open repository for sharing, testing, and deploying pre-trained deep learning microscopy models across multiple bioimage analysis tools.

This paper combines CNNs and Random Forests for domain adaptation in image segmentation, using pseudo-labels from a few annotations to improve performance across domains.

This paper develops an ex vivo culture system to study mouse peri-implantation development, revealing a mechano-chemical interplay between extra-embryonic and embryonic tissues.

The paper identifies 18 cell types in sponges, including neuroid cells with synaptic gene expression, suggesting early neuro-immune system evolution.

The paper shows that mechanical competition influences cell behavior during Drosophila gastrulation, with stretching cells exhibiting non-linear mechanical properties despite sharing the same genetic program as constricting neighbors.

The paper improves microscopy video segmentation by retraining a CNN with a Siamese network setup using unlabelled video frames.