Invited Talks


click this art to regenerate it
I whipped up this little piece of art that changes every time you click on it. You’ll stumble upon mesmerizing patterns that bring to mind the stunning intricacies of stained glass and the enchanting aura of ancient doors and catholic church windows.

Acronyms Explained

MGH Massachusetts General Hospital
MIT Massachusetts Institute of Technology
CISS Annual Conference on Information Sciences and Systems
Martinos Athinoula A. Martinos Center for Biomedical Imaging
JHU Johns Hopkins University


Title Date Host Records Info
Machine Learning Tools in Computational Neuroimaging: From Connectomes to FIT Nov, 2024 Susan Gabrieli Coming soon
An overview of machine learning tools in computational neuroimaging, covering connectomes and functional imaging techniques.

Machine Learning Tools in Computational Neuroimaging: From Connectomes to FIT Oct, 2024 Julie Price slides, video
Automated fetal brain extraction from MRI is a challenging task due to variable head sizes, orientations, complex anatomy, and prevalent artifacts. While deep learning (DL) models trained on synthetic images have been successful in adult brain extraction, adapting these networks for fetal MRI is difficult due to the scarcity of labeled data, leading to increased false-positive predictions. To address this, we propose a test-time strategy that reduces false positives in networks trained on sparse, synthetic labels. The approach uses a breadth-first scan (BFS) to identify a subvolume likely to contain the fetal brain, followed by a depth-focused sliding window (DFS) search to refine the extraction, pooling predictions to minimize false positives. We train models at different window sizes using synthetic images derived from a small number of fetal brain label maps, augmented with geometric shapes. Each model is trained on diverse head positions and scales, including cases with partial or no brain tissue. On clinical HASTE scans of third-trimester fetuses, our framework matches state-of-the-art brain extraction methods and exceeds them by up to three Dice points in the second trimester and for EPI scans. These results demonstrate the utility of a sliding-window approach, which improves brain-extraction accuracy by progressively refining the regions of interest, minimizing the risk of missing brain mask slices, or incorrectly identifying other tissues as brain.

Data-driven Methods for Functional Connectomes using Optimal Transport July, 2023 PhD Defense slides
under construction ..

Stacking multiple optimal transport policies to map functional connectomes March, 2023 JHU slides
under construction ..

Cross Atlas Remapping via Optimal Transport (CAROT) Feb, 2023 Ev Fedorenko slides
under construction ..

Cross Atlas Remapping via Optimal Transport (CAROT) March, 2023 Bruce Fischl slides
under construction ..