If you walk into the Epidemiology Research Team on any given day, you’ll likely find Danielle Durham, data scientist and resident problem-solver, immersed in what she affectionately describes as “puzzles.” While her work focuses on lung cancer screening, large datasets, and statistical modeling, Danielle sees the job through a more playful—and deeply human—lens. “I think people hear data and math and assume it’s boring,” she laughs. “But to me, it’s like a game. How do you get to the end screen? How do you beat the boss? It’s all strategy.” From the Lab Bench to Population Health Danielle grew up in Charlotte, NC, and made her way to Chapel Hill for both undergrad and graduate school. Her early career was hands-on: she worked overnight and weekend shifts as a general hematologist in the McLendon Labs, seeing countless cancer cases up close. Those experiences sparked an interest in understanding patients’ stories before they appeared under a microscope. “I started Googling public health,” she recalls. “I wanted to know what happens before someone shows up in the lab.” That curiosity eventually led her back to UNC-Greensboro to study community-based public health and later to research at a healthcare quality improvement organization in RTP.

UNC Radiology was proud to bring together faculty, trainees, alumni, and friends at this year’s RSNA for our annual Alumni Society Reception, hosted at Cindy’s. The evening offered a warm and welcoming space for our community to reconnect, share updates, and celebrate the ongoing achievements of Tar Heels across the field of radiology. In addition to our reception, UNC Radiology had the opportunity to connect with partners and supporters at Siemens Healthineers during RSNA. These conversations highlighted our shared commitment to advancing imaging science, strengthening clinical excellence, and fostering innovation that supports patients and providers alike. Events like these underscore the strength of the UNC Radiology network—spanning generations of graduates, current trainees, dedicated faculty, and industry collaborators. We’re grateful for everyone who joined us in Chicago and helped make this year’s RSNA such a meaningful experience. We look forward to continuing these connections throughout the year and seeing our community grow even stronger. Until next time, Go Heels!

Chapel Hill, N.C. — A research team led by the University of North Carolina at Chapel Hill has unveiled a transformative new approach to mapping the brain’s white matter pathways—one that eliminates the need for diffusion MRI (dMRI), long considered essential for tractography. Published in Nature Communications, the study introduces Anatomy-to-Tract Mapping (ATM), a deep learning framework capable of reconstructing full white matter bundles using only standard T1-weighted structural MRI. This innovation could greatly expand access to high-quality brain connectivity mapping in both research and clinical settings, where diffusion imaging is often limited or unavailable. Traditionally, dMRI tractography relies on the propagation of streamlines guided by local fiber orientation estimates—an approach that struggles in regions where multiple fiber populations cross, bend, or converge. High-quality diffusion data is also difficult to acquire, making robust tractography inaccessible for many clinical environments. ATM bypasses these challenges by learning the relationship between anatomical MRI features and known white matter pathways, generating anatomically plausible, subject-specific streamlines conditioned directly on a patient’s structural MRI. The result: accurate reconstructions of 30 major white matter bundles—without using any diffusion data. Notably, ATM performed well even on low-field and low-resolution clinical MRI scans, highlighting potential for real-world deployment in settings with limited