Image processing articles from across Nature Portfolio

A new deep learning approach enables motion correction across sequential acquisitions, even if each image in the sequence was acquired differently.

A groundbreaking biomedical AI foundation model, called BiomedParse, unifies detection, segmentation and recognition of organs, setting the stage for enhanced efficiency and accuracy in biomedical research and diagnostics.

This study presents a non-invasive method to track eye movements and reconstruct the retinal view of free-swimming fish in 3D. Validated through ground truth comparisons and behavioral analyses, this method advances eye-tracking studies in natural settings.

A foundation model for the motion correction, resolution enhancement, denoising and harmonization of magnetic resonance images improves the performance of machine-learning models across a wide range of tasks.

Algorithms help to capture macromolecular motion and structural heterogeneity in native cellular environments.

A new deep learning approach enables motion correction across sequential acquisitions, even if each image in the sequence was acquired differently.

A groundbreaking biomedical AI foundation model, called BiomedParse, unifies detection, segmentation and recognition of organs, setting the stage for enhanced efficiency and accuracy in biomedical research and diagnostics.

A computational mesoscale microscope offers large-scale volumetric imaging of intravital dynamics with cellular resolution.

The identification of senescent cells is a long-standing unresolved challenge, owing to their intrinsic heterogeneity and the lack of universal markers. In this Comment, we discuss the recent advent of machine-learning-based approaches to identifying senescent cells by using unbiased, multiparameter morphological assessments, and how these tools can assist future senescence research.