HONOLULU - Sustainability in medical imaging is of deep concern, and there are a number of ways to tackle the problem of negative environmental impacts caused by MRI, according to a presentation delivered on 11 May at the International Society for Magnetic Resonance in Medicine (ISMRM)/International Society for MR Radiographers & Technologists (ISMRT) conference.
The "greening" of MR imaging is part of a much bigger picture of sustainability in medical imaging, Dr. Saif Afat, managing senior physician at University Hospital Tübingen, Germany, told session attendees, noting that this effort requires discernment and perseverance.
Saif Afat, MD
"In each one of these steps, there are [a variety of] approaches for ways to reduce waste," he said.
There are two main categories of imaging waste, Afat noted: contrast agents and energy and workforce patterns. He outlined the path contrast takes after it's been used for imaging.
Gadolinium-based contrast agent (GBCA) waste from both inpatients and outpatients goes into the sewage system; conventional sewage treatment puts it into surface water and groundwater; it then goes into the drinking water production cycle. Water treatment does initiate degradation of GBCA, but still, the agent ends up in consumer drinking water.
Afat offered six tips for making MRI more sustainable and less toxic to the environment:
1. Use high-relaxivity GBCAs, which are "not only sustainable, but also safer for patients with kidney problems," he said.
2. Reduce GBCA waste by using a multi-patient injection system, which can cut contrast waste by 73% to 100%; reduce plastic waste by 85% to 93%; and decrease exam time by 41 seconds.
3. Consider collecting patient urine via toilet water filtration (for example, the Dutch-based Zereau's system), Afat said, noting that almost 15% of the GBCA injected into the patient can be recovered in the urine, and 40% of iodine contrast.
4. Reduce energy consumption by more than 50% by switching MRI systems off when not in use and by more than 45% by setting workstations in "short standby."
5. Use AI to reduce energy consumption by incorporating an energy-saving mode and/or "eco power" mode -- which can also shorten workflows. Afat noted that AI can have a significant impact in the radiology department, from image acquisition processing and clinical decision support to opportunistic screening and patient scheduling.
6. Use faster protocols to reduce scan time.
These suggestions are all part of the ongoing effort to make MRI greener, according to Afat.
"Every small step [towards sustainability] counts," he concluded.
Check out AuntMinnie.com’s full coverage of ISMRM 2025 here.




![Overview of the study design. (A) The fully automated deep learning framework was developed to estimate body composition (BC) (defined as subcutaneous adipose tissue [SAT] in liters; visceral adipose tissue [VAT] in liters; skeletal muscle [SM] in liters; SM fat fraction [SMFF] as a percentage; and intramuscular adipose tissue [IMAT] in deciliters) from MRI. The fully automated framework comprised one model (model 1) to quantify different BC measures (SAT, VAT, SM, SMFF, and IMAT) as three-dimensional (3D) measures from whole-body MRI scans. The second model (model 2) was trained to identify standardized anatomic landmarks along the craniocaudal body axis (z coordinate field), which allowed for subdividing the whole-body measures into different subregions typically examined on clinical routine MRI scans (chest, abdomen, and pelvis). (B) BC was quantified from whole-body MRI in over 66,000 individuals from two large population-based cohort studies, the UK Biobank (UKB) (36,317 individuals) and the German National Cohort (NAKO) (30,291 individuals). Bar graphs show age distribution by sex and cohort. BMI = body mass index. (C) After the performance assessment of the fully automated framework, the change in BC measures, distributions, and profiles across age decades were investigated. Age-, sex-, and height-adjusted body composition reference curves were calculated and made publicly available in a web-based z-score calculator (https://circ-ml.github.io).](https://img.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/05/body-comp.XgAjTfPj1W.jpg?auto=format%2Ccompress&fit=crop&h=100&q=70&w=100)







![Overview of the study design. (A) The fully automated deep learning framework was developed to estimate body composition (BC) (defined as subcutaneous adipose tissue [SAT] in liters; visceral adipose tissue [VAT] in liters; skeletal muscle [SM] in liters; SM fat fraction [SMFF] as a percentage; and intramuscular adipose tissue [IMAT] in deciliters) from MRI. The fully automated framework comprised one model (model 1) to quantify different BC measures (SAT, VAT, SM, SMFF, and IMAT) as three-dimensional (3D) measures from whole-body MRI scans. The second model (model 2) was trained to identify standardized anatomic landmarks along the craniocaudal body axis (z coordinate field), which allowed for subdividing the whole-body measures into different subregions typically examined on clinical routine MRI scans (chest, abdomen, and pelvis). (B) BC was quantified from whole-body MRI in over 66,000 individuals from two large population-based cohort studies, the UK Biobank (UKB) (36,317 individuals) and the German National Cohort (NAKO) (30,291 individuals). Bar graphs show age distribution by sex and cohort. BMI = body mass index. (C) After the performance assessment of the fully automated framework, the change in BC measures, distributions, and profiles across age decades were investigated. Age-, sex-, and height-adjusted body composition reference curves were calculated and made publicly available in a web-based z-score calculator (https://circ-ml.github.io).](https://img.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/05/body-comp.XgAjTfPj1W.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)








