Magnetic resonance imaging articles from across Nature Portfolio

A video-based deep-learning system was trained to understand the spectrum of human cardiovascular disease by the self-supervised method of contrastive learning, using pairs of cardiac MRI scans and their corresponding text reports that are generated as part of routine clinical practice.

A single-breath-hold 3D abdominal MRI technique (SSE-CEST) enables label-free mapping of glucose, glycogen and mobile protein in human liver, offering motion-robust, high-resolution imaging for cancer detection and metabolic monitoring.

Pravdivtseva et al. use 3D-printed models of brain aneurysms to test whether black-blood MRI can show the effects of flow-modulation devices. The black-blood signal increases where blood flow is reduced after device placement, suggesting it could indicate treatment success, even with metal implants.

Next generation ultra-high-gradient diffusion MRI reveals cortical laminar architecture in vivo, providing microstructural contrast that bridges histological cyto- and myeloarchitecture with noninvasive human brain imaging.

Using a 3-T MRI-compatible deep brain stimulation (DBS) system, Ren at al. densely sampled longitudinal, multimodal neuroimaging data from patients with Parkinson’s disease across multiple stimulation conditions spanning a year, mapping circuit-specific DBS-induced responses.

A video-based deep-learning system was trained to understand the spectrum of human cardiovascular disease by the self-supervised method of contrastive learning, using pairs of cardiac MRI scans and their corresponding text reports that are generated as part of routine clinical practice.

A technique called SASS increases temporal signal-to-noise ratio for functional MRI by taking advantage of the time it takes to reach steady state when collecting functional images.