Research

I work on computer vision for medical imaging, with an emphasis on robustness and reliability. My recent work focuses on (1) reducing shortcut learning and confounding, and (2) creating physiologically grounded data augmentation for segmentation.
I have been a research intern with the Stanford Center for Biomedical Informatics Research since 2022.

Research themes

Bias and confounders in diagnosis: methods to reduce spurious correlations in image-based diagnosis and segmentation, and evaluation setups that surface failure modes beyond average performance.
Physiologically informed augmentation: simulation-driven perturbations that preserve anatomy/physics while expanding training support in clinically realistic ways.
Segmentation and uncertainty: practical approaches to improve segmentation robustness under shift, including augmentation design and careful metric/visual validation.

Publications & manuscripts

Enhancing Medical AI with Physiologically-Informed Data Augmentation
ICML 2026 submission (pending) · Expected Jan 2026
Christoph Sadée, Alex Dils, Cally Lin, Audrey Chun, Francisco Carrillo-Perez, Preya Shah, et al.
Addressing Bias and Confounders in AI-based Image Diagnosis - A Study of 117,610 Skin Lesions
Cell (in revision) · Jan 2, 2025
Christoph Sadée, Serena Zhang, Alex Dils, et al.
Microplastic Identification Using AI-Driven Image Segmentation and GAN-Generated Ecological Context
arXiv preprint · Oct 27, 2024
Alex Dils, David Raymond, Christoph Sadée, et al.
Integrating Mechanistic Knowledge into Deep Learning for Improved Cancer Detection
FEniCS Conference 2024 Proceedings · Jun 16, 2024
Christoph Sadée, Katherine Hartmann, Alex Dils, et al.
Eye For An Eye: A Deep-Learning and Analytical Method to Spatializing Stereoscopic Images
National High School Journal of Science · Apr 17, 2025
Alex Dils*, Jake Yoshinaka, Leo McDonnell (*equal contribution)
Full list and citations on Google Scholar.