A. Kreshuk

A deep learning-based toolkit for 3D nuclei segmentation and quantitative analysis in cellular and tissue context

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

Deep intravital brain tumor imaging enabled by tailored three-photon microscopy and analysis

This paper introduces Deep3P, a three-photon microscopy and AI analysis method that enables deep intravital imaging of glioblastoma in mouse brains, revealing new insights into tumor invasion routes and white matter disruption.

CebraEM: A practical workflow to segmentcellular organelles in volume SEM datasetsusing a transferable CNN-based membraneprediction

CebraEM provides a workflow for segmenting cellular organelles in volume SEM datasets using a transferable CNN-based membrane prediction, achieving state-of-the-art results with minimal post-processing.

Sensing their plasma membrane curvature allows migrating cells to circumvent obstacles

The paper identifies a curvature-sensing mechanism in immune-like cells that enables obstacle avoidance through actin and membrane dynamics.

Microscopy-based assay for semi-quantitative detection of SARS-CoV-2 specific antibodies in human sera

The paper develops a semi-quantitative microscopy-based assay to detect SARS-CoV-2 specific antibodies in human sera, providing a sensitive and specific method for serological analysis.

Integration of Cell Growth and Asymmetric Division During Lateral Root Initiation In Arabidopsis thaliana

The paper analyzes the geometric features of cell divisions during lateral root initiation in Arabidopsis thaliana, showing asymmetric periclinal divisions and volume integration during growth.

Deep learning enables fast and dense single-molecule localization with high accuracy

This paper introduces DECODE, a deep learning tool that improves single-molecule localization speed and density in SMLM with high accuracy across various imaging conditions.

A digital 3D reference atlas reveals cellular growth patterns shaping the Arabidopsis ovule

The paper creates a 3D digital atlas of Arabidopsis ovule development, revealing cellular growth patterns and new functions in morphogenesis.

Deep learning-enhanced light-field imaging with continuous validation

This paper introduces a deep learning framework for light-field microscopy that uses continuous validation during image reconstruction, achieving high-quality video-rate reconstructions of medaka heart dynamics and zebrafish neural activity.

Whole-body integration of gene expression and single-cell morphology

The paper integrates gene expression and single-cell morphology in Platynereis dumerilii to identify spatially coherent cell groups defined by transcription factors.

Accurate And Versatile 3D Segmentation Of Plant Tissues At Cellular Resolution

PlantSeg provides a deep learning-based pipeline for accurate 3D segmentation of plant tissues into individual cells across various developmental contexts.