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.

Deep neural network modeling of auditory processing identifies distorted cross-frequency interactions as the key problem for the processing of speech in noise after hearing loss.

Advances in quantitative phase and polarized light microscopy, combined with deep learning, reveal the architecture of human brain tissue.

Rapid, label-free, volumetric, and automated assessment of the immunological synapse dynamics is demonstrated by combining optical diffraction tomography and deep-learning-based segmentation, providing a new option for immunological research.

Deep learning combined with induced pluripotent stem cell technology is an effective method to interrogate cellular phenotypes and predict patterns of cardiotoxicity in vitro.

A multi-compartment spiking neural network model demonstrates that biologically feasible deep learning can be achieved if sensory inputs and higher-order feedback are received by different dendritic compartments.

Scratch-AID, a deep learning-based system for automatic quantification of mouse scratching behavior, could replace labor-intensive manual quantification and facilitate high through-put anti-itch drug screening.

Integration of language model and geometric deep learning enables accurate and efficient genome-scale annotation of comprehensive protein-ligand binding sites.

Collaborative hunting, characterized by the division of roles among predators, has emerged within a group of artificial agents through deep reinforcement learning.

Incremental deep learning enables accurate tracking of cell lineages in 3D with a modest investment in time and effort.