We believe that a key aspect of making breast MRI more widely available is to be able to perform the exam with the patient lying on their back (supine), rather than the conventional face-down (prone) position.

We introduce a practical technique to measure voxel-wise noise variance in AI-based MRI reconstructions, addressing a long-standing gap in accelerated MRI.

In this work we present an ensemble of methods for quantifying spatial variations in MR image quality and demonstrate its utility for benchmarking imaging performance near metallic implants.

While breast MRI offers a more accurate detection approach than standard mammography, two challenges are (1) the uncomfortable prone position (patient lying on her stomach) and (2) the use of a contrast injection.

In this work a novel diffusion-weighted method, DW-DESS-Cones, is developed and characterized in vivo for the MRI of breast cancer without a contrast injection.

This manuscript presents a clinical breast MRI study that investigates the performance of single-shot DWI and multi-shot DWI reconstructed by two different techniques (MUSE and Shot-LLR).

Recent years have seen large advances in new artificial intelligence (AI) techniques for improving the current status of medical imaging, and specifically, magnetic resonance imaging (MRI).