MR News & Stories

Ineffective utilization affects patient wait-times, revenue, as well as referral and patient satisfaction. We are moving the needle in MRI productivity to increase patient volumes and overcome economic pressure.

Our new column “Point of View” picks up trends and developments in healthcare. In this first edition, Greg Freiherr comments on the advent of AI in the medical world – and how he learned to embrace it.

In recent years, the link between tumor therapies and cardiac disease has gained substantial attention. With improving survival rates of patients with various malignancies, potential detrimental effects on cardiac function and outcome including increased morbidity and mortality has become the center of such investigations.

MRF¹ uses quantitative information to generate a more precise understanding of a patient’s condition. Based on reliable, absolute numbers, MRF data could increase objective comparisons in follow-up studies. Ultimately, aided by AI, quantitative measurements could lead to more personalized treatments.

The developments in computational hardware and algorithms, in particular the advent of methods suitable for training complex neural networks (Deep Learning), have opened up new possibilities for machine learning [1] and automation in many applications. MRI, postprocessing and interpretation, in fact radiology in general, are no exception.

CMR will play an integral role in the evaluation of patients with cardiovascular disease. Compressed Sensing will shorten and simplify the CMR protocol increasing its utilization. AI strategies will improve workflow and will also help us extract previously invisible radiomic features that will better characterize cardiovascular disease.