Spark

Duke Spark, with support from Duke AI Health, invites faculty across Duke to apply for the Fall 2025 Medical Imaging and AI Proposal Studios, a unique opportunity to receive expert feedback and mentorship on grant proposals at the intersection of AI, computer vision, and medical imaging. Designed to support high-impact and competitive research, this initiative is open to clinical and non-clinical faculty from all Duke departments, with special encouragement for early-career investigators. Selected projects will participate in tailored scientific review sessions held from October to December 2025. Applications are due by 10:00 PM ET on Monday, September 8, 2025.

LEARN MORE

This seminar, presented by James S. Duncan, PhD, and hosted by Maciej Mazurowski, PhD, explores advanced neuroimaging analysis in autism spectrum disorders (ASD), with a focus on identifying objective biomarkers and predicting response to behavioral therapies such as Pivotal Response Treatment (PRT). Dr. Duncan presents a range of methodologies, beginning with a Bayesian framework to detect atypical brain connectivity and moving toward machine learning approaches that use convolutional and recurrent neural networks for classification and prediction. The talk also discusses early work involving dynamic causal modeling as a complementary approach to traditional functional connectivity methods. These techniques offer promising tools for individualized diagnosis, treatment planning, and monitoring in ASD. This seminar originally aired on March 7th, 2023. This session was part of the monthly Spark: AI Health Initiative for Medical Imaging seminar series. Spark highlights cutting-edge work in medical imaging research from Duke and beyond, with a mission to develop, validate, and implement AI tools for clinical imaging. The series fostered collaboration between technical and clinical experts. VIEW

Can AI safely automate medical decision-making tasks to improve patient outcomes? In this talk, the presenters will share the challenges in the development and translation of medical AI, and how they are being addressed through a blend of innovation in algorithm development, dataset curation, and implementation design. They will first talk about self-supervised learning methods for medical image classification that leverage large unlabeled datasets to reduce the number of manual annotations required for expert-level performance. Then, they will discuss open benchmarks that can help the community transparently measure advancements in generalizability of algorithms to new geographies, patient populations, and clinical settings. Third, they will share insights from studies that investigate how to optimize human-AI collaboration in the context of clinical workflows and deployment settings. Altogether, this talk will cover key ways in which we can realize the potential of medical AI to make healthcare more accurate, efficient and accessible for patients worldwide.

READ MORE

Duke AI Health welcomes Maciej Mazurowski, PhD, who will join its Faculty Council as Director of Radiology Imaging. At AI Health, Dr. Mazurowski will coordinate the AI Health Initiative for Medical Imaging. This new effort will engage experts in machine learning and clinical medicine from across Duke’s campus to foster and accelerate the development, validation, and clinical implementation of machine learning algorithms for medical imaging. “I’m excited to undertake this new challenge and I’m looking forward to working with experts and leadership across the entire campus to build on existing technical and clinical strengths in medical imaging AI at Duke,” Dr. Mazurowski said.

READ MORE