I am a Postdoctoral Scholar working with Prof. Akshay Chaudhari and Prof. David Larson in the Department of Radiology at Stanford University focusing on evaluating the performance and robustness of large-scale AI models for medicine and identifying early disease biomarkers. I am part of the Machine Intelligence in Medical Imaging Research Group (MIMI) and AI Development and Evaluation Lab (AIDE).
Until August 2023, I was a Postdoctoral Scholar in the Computational Neuroimage Science Laboratory (CNS Lab) with Prof. Kilian M. Pohl working on multi-modal machine learning models that can improve the understanding, diagnosis, and treatment of neuropsychiatric disorders.
In 2021, I earned my Ph.D. Summa Cum Laude in Computer Science at the Chair for Computer Aided Medical Procedures & Augmented Reality at TUM advised by Prof. Nassir Navab. My dissertation was about Learning Robust Representations for Medical Diagnosis.
My husband, Walter Simson is a Senior AI Engineer at NVIDIA.
What if AI could learn from millions of unlabeled radiology images and reports—and then flexibly adapt to new clinical tasks? In a new comprehensive review in Radiology, we dive into how foundation models (FMs) are set to revolutionize radiology!
Our review provides a structured framework for understanding FMs in radiology: Core technical principles, training methodologies, clinical applications, evaluation strategies and implementation challenges
I have developed methods to evaluate and enhance the robustness of neural networks in medical imaging. My work introduced adversarial examples to the medical community, demonstrating the vulnerability of classification and segmentation models for cancer diagnosis in breast imaging and dermatoscopy.
Investigation of medical imaging networks using adversarial examples for model evaluation and benchmarking.
Novel geometric transformation techniques for improved model robustness and performance.
Contributing to the development and evaluation of foundation models for radiology, focusing on models that can interpret both textual and imaging data.
Development of an instruction-tuned foundation model for chest X-ray interpretation and report generation.
Evaluation of a comprehensive model for CT scan analysis with EHR codes and reports.
Development of approaches bridging data-driven deep learning with hypothesis-driven testing, focusing on biomarker identification using combined imaging and non-imaging data.
Novel permutation-based framework for predicting depressive symptoms in adolescents.
Machine learning approaches for identifying disease biomarkers and risk factors.
Advancements in surgical phase recognition focusing on improving patient safety and supporting intra-operative decision-making through automatic workflow analysis.
Multi-Stage Temporal Convolutional Network for surgical phase recognition.
Transformer-based model for surgical phase prediction from video sequences.
