Deep learning denoising reconstruction enables faster T2-weighted FLAIR sequence acquisition with satisfactory image quality.

Introduction: Deep learning reconstruction (DLR) technologies are the latest methods attempting to solve the enduring problem of reducing MRI acquisition times without compromising image quality. The clinical utility of this reconstruction technique is yet to be fully established. This study aims to assess whether a commercially available DLR technique applied to 2D T2-weighted FLAIR brain images allows a reduction in scan time, without compromising image quality and thus diagnostic accuracy.

Dynamic Susceptibility Contrast Perfusion, Part 2: Deployment With and Without Contrast Leakage Present.

A thorough description of perfusion analysis and basic DSC MR acquisition concepts has been described in the companion article to this article, which the interested reader may also find useful. DSC MR imaging requires an MR imaging pulse sequence that is sensitive to magnetic susceptibility changes to register the contrast concentration changes when GBCA passes through the capillary bed. Any pulse sequence that has T∗-weighting can be used to pick up these changes, provided that the sequence is fast enough to acquire an image of that slice of tissue at least every 1 to 2 second.

Dynamic Susceptibility Contrast Perfusion, Part 1: The Fundamentals.

Measuring blood flow has been of long-standing interest in medicine and physiology. Initially conceived to measure blood flow to the whole organ, attention turned quickly to measure capillary blood flow as a measure of local delivery of nutrients to a small region of tissue. Originally proposed with gases and microspheres, early on, the method of indicator dilution has become the most prevalent approach because of the impracticality of using microspheres.