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
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
Christoph Sadée, Serena Zhang, Alex Dils, et al.
Microplastic Identification Using AI-Driven Image Segmentation and GAN-Generated Ecological Context
Alex Dils, David Raymond, Christoph Sadée, et al.
Integrating Mechanistic Knowledge into Deep Learning for Improved Cancer Detection
Christoph Sadée, Katherine Hartmann, Alex Dils, et al.
Eye For An Eye: A Deep-Learning and Analytical Method to Spatializing Stereoscopic Images
Alex Dils*, Jake Yoshinaka, Leo McDonnell (*equal contribution)
Full list and citations on Google Scholar.