Quantifying Energy Consumption in MRI, CT, and PET/CT

Dr. Ashwin Parihar speaks with Dr. Olayinka A. Abiodun-Ojo and Dr. David M. Schuster about findings from the EMPIRE 2 trial, exploring how fluciclovine PET and PSMA PET influence salvage radiotherapy planning for men with recurrent prostate cancer after prostatectomy. The discussion examines the strengths and limitations of each tracer, the importance of prostate bed detection, and where fluciclovine may still have a role in the evolving era of PSMA-targeted imaging. 18F-Fluciclovine or 68Ga-PSMA-11 PET/CT–guided SalvageRadiotherapy Changes in Postprostatectomy BiochemicalRecurrence: Secondary Analysis of the EMPIRE-2 Trial. Abiodun-Ojo and Jani et al. Radiology 2026; 319(3):e251874. 

In this episode of the Radiology Podcast, Dr. Siddhant Dogra speaks with Dr. Albert Jiao about Radiology Reimagined and the critical role interoperability plays in integrating AI into everyday radiology workflows. Together, they explore lessons learned from large-scale AI demonstrations, practical considerations for evaluating imaging AI tools, and what the future of radiology innovation may look like. Radiology Reimagined: Interoperability and Lessons Learned from the Imaging AI in Practice Demonstration. Jiao et al. Radiology 2026; 319(3):e252225.

Dr. Lauren Kim speaks with first author Dr. Andrew Hernandez about his study which comprehensively quantified energy consumption in MRI, CT, and PET/CT imaging suites by measuring the energy utilization of main power, HVAC, and chilled water subsystems. The study showed that HVAC and chilled water subsystems contribute substantially to total energy consumption, that energy efficiency increases with increasing daily scanning volume, and that a substantial portion of energy consumption occurs during non-operating hours.   Quantification of Imaging Suite–Level Energy Patterns in MRI, CT, and PET/CT to Guide Energy Efficiency. Hernandez et al. Radiology 2026; 319(1):e253128.

Host Dr. Reni Butler sits down with Dr. Connie Lehman to discuss groundbreaking research on how AI-generated breast cancer risk scores change over time and what those changes may reveal about a woman's future cancer risk. Together, they explore the promise of longitudinal imaging biomarkers, personalized screening strategies, and how artificial intelligence could transform breast cancer detection and prevention. Longitudinal Analysis of Changes in Deep Learning Image-based Breast Cancer Risk Scores over Time. Lehman et al. Radiology 2026; 319(3):e253023.

Dr. Refky Nicola welcomes back Dr. Kate Hanneman to discuss new research examining the link between long-term air pollution exposure and coronary atherosclerosis detected on cardiac CT. Together, they explore key findings on plaque burden, sex-specific differences, cumulative exposure risks, and the growing cardiovascular implications of wildfire smoke.   Sex-Specific Associations between Long-term Air Pollution Exposure and Coronary Atherosclerosis at Cardiac CT. Castillo et al. Radiology 2026; 319(3):e252086.

Dr. Lauren Kim and first author Dr. Daniel Marinescu discuss this study comprised of approximately 1,500 patients which determines the relative importance of specific CT imaging features used to distinguish radiologic patterns in fibrotic interstitial lung disease. This study identifies areas of substantial incongruence between radiologist-assigned ILD patterns and current clinical diagnostic guideline definitions, incongruencies which in turn may help refine and standardize future diagnostic criteria. Association of CT Features with Radiologic Patterns in Interstitial Lung Disease: Multinomial Analysis in CARE-PF.  Marinescu et al. Radiology 2026; 318(3):e251944. From CT Features and Patterns to Clinical Pathways: Focusing a Multinomial Lens on Fibrotic ILD. Czum and Brown. Radiology 2026; 318(3):e260494.

Host Dr. Celina Nahyun Jo sits down with Dr. Perry Pickhardt to explore how opportunistic CT screening is transforming routine imaging into a powerful tool for cardiometabolic risk assessment, bone health evaluation, liver disease detection, and body composition analysis. Together, they discuss the role of explainable AI, the future of CT-based biologic age, and why value-added imaging has the potential to reshape preventive care.   CT-based Opportunistic Screening for Adding Clinical Value:How I Do It. Pickhardt et al. Radiology 2026; 319(1):e252106.

Dr. Linda Chu speaks with Dr. Eddy Zandee and Dr. Kirk Davis about multidisciplinary expert consensus recommendations aimed at reducing the use of low yield radiographs and improving imaging appropriateness across healthcare settings. They explore which common radiographic exams may offer limited clinical value, when CT or MRI may be more appropriate, and how education and workflow changes can help optimize imaging utilization. Optimizing Radiography Utilization: Multidisciplinary Expert Consensus Recommendations Endorsed by the Society of Academic Bone Radiologists, Society of Skeletal Radiology, American Societyof Emergency Radiology, Orthopaedic Trauma Association, American Academy of Emergency Medicine, and American Rhinologic Society. Zandee van Rilland et al. Radiology 2026; 319(2):e252309.

Dr. Ashwin Singh Parihar sits down with Dr. Louise Emmett to discuss how post-therapy Lutetium-177 PSMA SPECT/CT may help predict overall survival in patients with metastatic castration resistant prostate cancer and shape future treatment decisions. Drawing from the ENZA-p trial run by ANZUP cancer trials group, they explore quantitative imaging, treatment response assessment, adaptive dosing strategies, and the growing role of theranostics in precision oncology.   177Lu-PSMA-617 SPECT/CT for Early Prediction of Overall Survival in Participants with Metastatic Castration-Resistant Prostate Cancer. Ayati et al. Radiology 2026; 319(1):e252672.

Dr. Siddhant Dogra sits down with Dr. Su Hwan Kim to discuss how reader experience influences the performance and real world utility of large language models for brain MRI differential diagnosis. Together they explore AI assisted decision making, automation bias, radiology training, and why strong AI performance does not always translate into meaningful clinical benefit. Performing Best When Needed Least: Reader Experience ShapesAccuracy Gains in Large Language Model–assisted Brain MRIDifferential Diagnosis. Schramm et al. Radiology 2026; 319(2):e253477.