Talks, Posters, and Tutorials

Talks

The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning (October 2022)

For The Pacific Northwest Seminar on Topology, Algebra, and Geometry in Data Science (TAG-DS), a hybrid seminar at the University of Washington Math Department. Slides are here.

• My related paper from MICCAI 2022: open access preprint here and published paper here.

What actually is Artificial Intelligence, and how does it relate to astronomy? (June 2024, August 2022)

See the talk here. For ERIRA 2022 and 2024 Astro X.

Posters

2024

• Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Models (MICCAI 2024).
• Rethinking Perceptual Metrics for Medical Image Translation (MIDL 2024).
• The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images (ICLR 2024).

2023

• Attributing Learned Concepts in Neural Networks to Training Data (NeurIPS 2023 Workshop on Attributing Model Behavior at Scale [Oral]).
• Reverse Engineering Breast MRIs: Predicting Acquisition Parameters Directly from Images (MIDL 2023).

2022 and earlier

• The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning (MICCAI 2022). Poster won Judges’ Choice Award at the Duke University Pratt School of Engineering Fall 2022 Poster Session.
• Bayesian Model Fitting to Data With Both Intrinsic and Extrinsic Uncertainties in Two Dimensions (UNC Celebration of Undergraduate Research, Spring 2019).

Tutorials

Train a Neural Network to Detect Breast MRI Tumors with PyTorch

• Part 1
• Part 2 (Featured on the Editors’ Picks of Towards Data Science)

Differential Geometry Cheatsheet

See here.