Using artificial intelligence to support the adoption of quantitative MRI into clinical practice

With over 43 million imaging studies performed across the NHS in 2018 there is an ever-increasing pressure on radiological departments to perform fast, high throughput assessment of medical images. In a recent census report by The Royal College of Radiologists, key findings reported that consultant clinical radiologists are showing increased signs of stress and burnout, and that this is subsequently having a negative impact on patient healthcare. They emphasise that this is in part due to a significant increase in the volume and complexity of MRI studies – accelerated imaging techniques enabled by new scanner hardware results in multiple imaging contrasts in a single radiological study. In addition to this, quantitative MRI (qMRI) also provides a non-invasive assessment of tissue physiology, which is revolutionising the way in which images are used to diagnose disease and monitor changes as a result of treatment. The development of cutting-edge computational techniques such as AI are therefore welcomed in order to make the best use of high volume imaging data and improve patient diagnostics. In this article, we will focus on the fundamentals of qMRI and AI and how they are currently being integrated in order to improve the clinical management of patients with cancer.

The content on this page is provided by the individuals concerned and does not represent the views or opinions of RAD Magazine.