Radiological Society of North America

Large language models (LLMs) are being increasingly explored in radiology for education, report support, guideline retrieval and clinical decision support. However, a recently published study in Radiology: Artificial Intelligence demonstrated that LLMs are susceptible to cognitively biased inputs and the authors say safeguards must be put in place to mitigate their influence. In the study conducted at the University of Toronto, lead author Nicholas T.

For more than a decade, RSNA’s AI Challenges have drawn thousands of participants from around the world to tackle some of medical imaging’s most difficult problems. Along the way, the competitions have generated uniquely valuable datasets, open-source algorithms and collaborations that continue to advance radiology AI long after the winners are announced. Those lasting benefits stem in part from the diversity of both the sources of data and the competitors themselves.

Berat Bersu Ozcan, MD, is a diagnostic radiology resident at the University of Texas (UT) Southwestern Medical Center in Dallas. Dr. Ozcan earned her medical degree from Hacettepe University in Ankara, Turkey, and subsequently completed a research fellowship in the Department of Radiology at UT Southwestern. She has served on the RadioGraphics Trainee Editorial Board and maintains an active role in academic radiology.

Superresolution US may offer a new way to detect diabetic peripheral neuropathy (DPN) by revealing subtle microvascular changes in the tibial nerve. In a study published in Radiology, lead author Fang Liu, MD, of Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, and colleagues reported increased nerve blood flow and vascularity in patients with neuropathy and ulcers, challenging the long-held assumption that the condition is driven mainly by reduced blood flow.

Quantifying myocardial infarction on cardiac MR is accurate but time-consuming and subject to inter-reader variability. A new deep learning (DL)-based model shows promise in assisting radiologists with the segmentation and quantification of cardiac MR (CMR) images following myocardial infarction. Research published in Radiology Advances compared the DL-model and human-based measurements, demonstrating the model’s strengths and limitations.

For people living with temporal lobe epilepsy (TLE), the challenges extend beyond seizures. Long-term memory impairment is among the most common concerns, along with a wide spectrum of cognitive defects. Stereotactic laser amygdalohippocampotomy (SLAH) is an emerging minimally invasive treatment option for TLE patients, potentially offering seizure control comparable to open anterior temporal lobectomy, while also showing more favorable memory outcomes.

Advancing Research Across a Range of Diseases Among this year’s recipients is Yashbir Singh, PhD, of Mayo Clinic in Rochester, New York. Dr. Singh was awarded a Research Scholar Grant for his work to improve early detection and tailored treatment for perihilar cholangiocarcinoma (pCCA), a cancer that forms in the bile ducts outside the liver.

Impact Factors on LCS Adherence and Patient Experience In the analyses of patients following LDCT, there were surprising physical and emotional effects reported by patients overall. “Participants generally reported minimal short-term burden associated with low-dose CT screening. Most individuals described little to no discomfort and only mild emotional effects, such as low levels of anxiety or concern,” Dr. Porembka said.

Abbreviated MRI can serve as a time-efficient alternative for assessing the response to neoadjuvant chemotherapy (NAC), demonstrating diagnostic performance comparable to full protocol MRI. NAC is a standard approach for treating locally advanced breast cancer and is increasingly used for treating smaller tumors. Following NAC, full-protocol MRI is used to assess treatment response and inform surgical planning.

Three RSNA members joined the Society for different reasons: access to journals, educational opportunities and professional development. What they found was much more: mentorship, leadership experience, publishing opportunities and connections that helped shape their careers. A Rising Star Finds New Opportunities Kevin Fung, MBBS, a consultant radiologist in the Department of Radiology at Hong Kong Children’s hospital, first joined RSNA around 2014, drawn by the coveted access to its journals.