Visitors Talk: Lilla Zollei, Harvard Medical School

Abstract

InfantFreeSurfer is an automated image analysis pipeline originally designed for processing T1-weighted MRI scans of children aged 0-3 years. It extends the FreeSurfer framework with infant-specific image processing solutions to accommodate the rapid anatomical changes and low tissue contrast characteristic of early postnatal brain development. This pipeline will provide a framework for my talk to introduce novel deep-learning based solutions on skullstriping, whole brain segmentation and surface reconstruction for the target perinatal population.

About the speaker

Dr. Lilla Zöllei is an Associate Professor of Radiology at Massachusetts General Hospital / Harvard Medical School. She earned her PhD in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology, and her research focuses on developing advanced computational tools for neuroimaging, particularly in pediatric and perinatal brain studies where conventional adult-focused methods fall short. Dr. Zöllei has made significant contributions to infant brain segmentation, surface reconstruction pipelines, automated tractography, and high-resolution ex vivo imaging using MRI and optical coherence tomography, often in close collaboration with clinical teams. She is currently funded by a variety of NIH and private foundation grants.