How technology is breathing new life into cardiac MRI
Cardiac magnetic resonance imaging has been in use since the 1980s and has become an important clinical tool, valued for its ability to visualize and quantify the blood flow in the heart, aorta and large vessels. Its capabilities are critical in diagnosing heart disease and heart failure.
While cardiac MRI is considered the gold standard in diagnostics because of the quality of images possible and the non-invasive nature of the test, it is frequently a last resort in imaging modalities because of the difficulty of acquisition. The patient must remain very still and be able to hold their breath multiple times. Some patients may need anesthesia to endure the test, increasing the risk. It takes longer to perform than other diagnostics, requires a highly skilled technologist and radiologist, and the results may not be immediately available. These challenges may also reduce the usability of cardiac MRIs in emergency situations.
Currently, limitations to routine clinical application include availability of the hardware, cost and perhaps most important, physician and technologist education. While some institutions already using cardiac MRI are inundated with increasing demand, other institutions are unable to adopt the technology because of lack of educated professionals to administer the test and evaluate the results.
Advances in imaging technology have not only provided better quality studies, but have also relieved many of the difficulties with administering it. 4D flow MRI—3D flow imaging over time—has been available in research centers for decades and is finally making its way into clinical practice.
The 4D flow sequence enables comprehensive haemodynamic flow assessments, providing valuable assessment of the three-dimensional and multi-directional nature of intra-cardiac blood flow.
With 2D-based systems, it was necessary for the physician to determine ahead of time every measurement that was needed, and each one was taken in a separate sequence. Every flow measurement was a separate breath hold, and the physician frequently had to work closely with the technologist while being present during acquisition. This is no longer necessary. Our practice images from the top of the arch through the apex of the heart, obtaining coverage through the entire heart and great vessels. A detailed conversation with the technologist about where to take flow measurements is no longer necessary.
Use of 4D flow has enabled simplified protocols. While not everything can be obtained in 4D flow, the information from the 4D sequence has enabled us to decrease some of the other sequences we were acquiring. In addition, the ease with which the 4D flow sequence is acquired enables other technologists with less cardiac training to run the sequence. The simplified protocols mean any MRI technologist can successfully capture the data necessary.
4D flow also presents numerous benefits to the patient. Velocity measurements derived by 4D flow correlate to those obtained via transesophageal echocardiography, but do not require anesthesia and intubation. First, 4D flow is a free breathing sequence. This opens up the possibilities of imaging younger and sicker patients who are typically unable to meet the breath-holding demands, and it reduces the need to use anesthesia. We are now able to image patients as young as 6 years old without anesthesia. For patients with congenital diseases who need to be imaged frequently, reducing the number of times they receive anesthesia is a significant benefit to their long-term health.
Perhaps most significant is the decreased amount of time necessary to scan a patient and analyze the images. Time slots for cardiac MRI scans in our practice were 90 minutes; we are now able to perform these studies in 45-minute time slots. I can now do all of my post-processing after the patient has left, with no concern that I didn’t capture the necessary images.
Cardiac MRI isn’t just time consuming to capture, but also to analyze. The labor-intensive nature makes it an ideal job replaced by technology. Artificial intelligence has only been used in healthcare in very limited applications. Medical imaging is a core part of patient care, and embedding it with AI can have a huge impact.
With cardiac MRI specifically, use of 4D flow generates exponentially more data. Arterys MICA is a cloud-based AI platform for medical image analytics that is cleared by the Food and Drug Administration. The massive amounts of data that are required for real-time, interactive AI insights to medical images would require a supercomputer to be installed at every workstation to be able to process the 4D Flow images. MICA is a web-based system that runs on a scalable, distributed GPU architecture.
The Arterys platform also uses an AI algorithm to process 2D function images which are preprocessed before opening the study. It used to take me 20 to 40 minutes to draw all of the circles and analyze the 2D images. Now, I spend five minutes looking at the contours and making a few adjustments. It has made a significant difference in my workload.
While there are some growing pains involved, 4D flow is easier for patients, it is more efficient for health care providers, and provides the best diagnostic information to treat the patient.