Reducing MRI scan times could add thousands of exam slots, generating up to $22M in new revenue per practice
Techniques to reduce MRI scan times could potentially add thousands of additional appointment slots while generating upward of $22 million in new annual revenue, all while helping protect the environment.
That’s according to a new retrospective study led by the University of California, San Francisco, and Siemens Healthineers, published Tuesday in Radiology. Previous studies have explored how powering down scanners during downtimes could save electricity and reduce carbon emissions. Researchers recently took a new approach, examining how methods to speed-up scans could preserve the planet and precious imaging resources.
They tested three potential acceleration techniques via a phantom study. Accelerating sequences by 25%–75% was found to lower per-exam greenhouse gasses and energy consumption by 21%–65%, with deep-learning-based reconstruction producing the greatest impact. For a practice operating seven days a week and handling 24 MRIs, projected annual energy savings ranged from over $26,000 to nearly $113,000. This also would enable 8,424 to 57,564 additional appointments, generating between $3.26 million to $22.28 million in additional revenue.
“These findings highlight the value of sustainable operations and energy-saving strategies,” Sean A. Woolen, MD, MS, a UCSF radiologist and researcher, and co-authors advised. “Optimizing MRI protocols with acceleration methods such as [deep learning] offers substantial environmental and operational benefits, reducing [greenhouse gasses], energy use, and costs while improving patient access and revenue,” they added later.
The deep learning method in question is Deep Resolve from Siemens Healthineers, with the study also performed using three models of the company’s scanners. DR deploys multiple techniques, taking advantage of convolutional neural networks to enable accelerated scans, such as 70% faster brain MRIs.
To conduct their study, Woolen and colleagues used power meters to record electricity use from the three machines. They then deployed various acceleration methods, calculating reductions in output. Cost savings were determined using the U.S. average commercial energy rate ($0.13 per kilowatt hour), with additional revenue from increased slots estimated via Medicare reimbursement rates. Greenhouse gas savings, meanwhile, were calculated using the 2021 U.S. average emission rate.
“Study limitations include reliance on three MRI scanners from one vendor, modeling from clinical and phantom data, variability in energy estimates across institutions, exclusion of chilled water energy, and use of U.S. national averages for energy costs, reimbursement, and carbon savings,” the authors cautioned. “DL model training energy and image quality impacts were not evaluated.”
Read much more in the flagship journal of the Radiological Society of North America here (sign in required).
Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic.