Search

Abstract Background Magnetic resonance imaging (MRI) offers superb non-invasive, soft tissue imaging of the human body. However, extensive data sampling requirements severely restrict the spatiotemporal resolution achievable with MRI. This limits the modality’s utility in real-time guidance applications, particularly for the rapidly growing MRI-guided radiation therapy approach to cancer treatment. Recent advances in artificial intelligence (AI) could reduce the trade-off between the spatial and the temporal resolution of MRI, thus increasing the clinical utility of the imaging modality. Methods We trained deep learning-based super-resolution neural networks to increase the spatial resolution of real-time MRI. We developed a framework to integrate neural networks directly onto a 1.0 T MRI-linac enabling real-time super-resolution imaging. We integrated this framework with the targeting system of the MRI-linac to demonstrate real-time beam adaptation with super-resolution-based imaging. We tested the integrated system using large publicly available datasets, healthy volunteer imaging, phantom imaging, and beam tracking experiments using bicubic interpolation as a baseline comparison. Results Deep learning-based super-resolution increases the spatial resolution of real-time MRI across a variety of experiments, offering measured performance benefits compared to bicubic interpolation. The temporal resolution is not compromised as measured by a real-time adaptation latency experiment. These two effects, an increase in the spatial resolution with a negligible decrease in the temporal resolution, leads to a net increase in the spatiotemporal resolution. Conclusions Deployed super-resolution neural networks can increase the spatiotemporal resolution of real-time MRI. This has applications to domains such as MRI-guided radiation therapy and interventional procedures.

Background and purpose: Magnetic resonance imaging (MRI)-Linac systems combine simultaneous MRI with radiation delivery, allowing treatments to be guided by anatomically detailed, real-time images. However, MRI can be degraded by geometric distortions that cause uncertainty between imaged and actual anatomy. In this work, we develop and integrate a real-time distortion correction method that enables accurate real-time adaptive radiotherapy. Materials and methods: The method was based on the pre-treatment calculation of distortion and the rapid correction of intrafraction images. A motion phantom was set up in an MRI-Linac at isocentre (P0), the edge (P1) and just outside (P2) the imaging volume. The target was irradiated and tracked during real-time adaptive radiotherapy with and without the distortion correction. The geometric tracking error and latency were derived from the measurements of the beam and target positions in the EPID images. Results: Without distortion correction, the mean geometric tracking error was 1.3 mm at P1 and 3.1 mm at P2. When distortion correction was applied, the error was reduced to 1.0 mm at P1 and 1.1 mm at P2. The corrected error was similar to an error of 0.9 mm at P0 where the target was unaffected by distortion indicating that this method has accurately accounted for distortion during tracking. The latency was 319 ± 12 ms without distortion correction and 335 ± 34 ms with distortion correction. Conclusions: We have demonstrated a real-time distortion correction method that maintains accurate radiation delivery to the target, even at treatment locations with large distortion.

Purpose: While disparities in the inclusion and advancement of women and minorities in science, technology, engineering, mathematics, and medical fields have been well documented, less work has focused on medical physics specifically. In this study, we evaluate historical and current diversity within the medical physics workforce, in cohorts representative of professional advancement (PA) in the field, and within National Institutes of Health (NIH)–funded medical physics research activities. Methods and Materials: The 2020 American Association of Physicists in Medicine (AAPM) membership was queried as surrogate for the medical physics workforce. Select subsets of the AAPM membership were queried as surrogate for PA and early career professional advancement (ECPA) in medical physics. Self-reported AAPM-member demographics data representative of study analysis groups were identified and analyzed. Demographic characteristics of the 2020 AAPM membership were compared with those of the PA and ECPA cohorts and United States (US) population. The AAPM-NIH Research Database was appended with principal investigator (PI) demographics data and analyzed to evaluate trends in grant allocation by PI demographic characteristics. Results: Women, Hispanic/Latinx/Spanish individuals, and individuals reporting a race other than White or Asian alone comprised 50.8%, 18.7%, and 32.4% of the US population, respectively, but only 23.9%, 9.1%, and 7.9% of the 2020 AAPM membership, respectively. In general, representation of women and minorities was further decreased in the PA cohort; however, significantly higher proportions of women (P < .001) and Hispanic/Latinx/Spanish members (P < .05) were observed in the ECPA cohort than the 2020 AAPM membership. Analysis of historical data revealed modest increases in diversity within the AAPM membership since 2002. Across NIH grants awarded to AAPM members between 1985 and 2020, only 9.4%, 5.3%, and 1.7% were awarded to women, Hispanic/Latinx/Spanish, and non-White, non-Asian PIs, respectively. Conclusions: Diversity within medical physics is limited. Proactive policy should be implemented to ensure diverse, equitable, and inclusive representation within research activities, roles representative of PA, and the profession at large.