Duke Spark News

Tuesday, July 19, 2022

In this talk, Alberto Bartesaghi, Associate Professor of Computer Science, Duke University, will describe his efforts to employ AI-based techniques for feature recognition to drive the development of strategies to accelerate structure determination using cryo-EM. For example, finding the conditions to stabilize a macromolecular target for imaging remains the most critical barrier to determining its structure. SmartScope is the first framework to streamline, standardize, and automate specimen evaluation using deep-learning-based object detection, allowing it to perform specimen screening in a fully automated manner. During the downstream data analysis, randomly distributed copies of the protein of interest need to be identified, extracted, and averaged in 3D to obtain a high-resolution structure. Existing neural-network-based detection algorithms require extensive labeling and are very slow to train. Leveraging positive unlabeled learning and consistency regularization, we propose a novel framework that can identify particles much faster than previously possible while still using very few labels. Altogether, these advances in AI-driven cryo-EM greatly facilitate and accelerate the structural analysis of important biomedical targets, thus lowering the barrier of adoption of this powerful technique for protein structure determination. 

Wednesday, April 20, 2022

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.

Monday, February 28, 2022

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.