The spatial autocorrelation method Local Moran’s I was used for image segmentation to delineate pixel clusters representing congruous objects with fuzzy borders, in this case potassium ion channel clusters.

Convolutional neural networks and graph partitioning algorithms can be combined into an easy-to-use tool for segmentation of cells in dense plant tissue volumes imaged with light microscopy.

A dual-channel image registration pipeline combined with deep-learning inference achieves accurate-and-flexible registration/segmentation/mapping of mouse brain.

'Cellular Electron Microscopy 500,000 images' (CEM500K) is a highly heterogeneous, information-rich, non-redundant, unlabeled EM dataset curated to pre-train DL algorithms for better model generalization on EM segmentation tasks.

Easy-to-use image analysis software enables single cell quantitation of cell types and division rates in complex 3D tissues including living Drosophila brains, mouse embryos and Zebrafish organoids.

Automated computational unfolding of the hippocampus allows analyses at its mesoscale and facilitates novel discoveries in the study of cognition and disease.

The software package Ais simplifies automated segmentation in cryo-electron tomography, enabling users to segment, detect particles, and visualize data in a streamlined and accessible workflow.

Experimental results in Drosophila support a model in which gene expression is fundamentally controlled by morphogens tuning the same transcription parameter for genes that are expressed in highly diverse patterns.

A comparison of different bioimage analysis pipelines reveals how deep learning can be used for automatized and reliable analysis of fluorescent features in biological datasets.

New reconstruction methods are used to create a publicly available dense reconstruction of the neurons and chemical synapses of central brain of Drosophila, with analysis of its graph properties.