Dr. Fiona Kolbinger

Areas of Research 

Computational Medicine, Artificial Intelligence Applications in Healthcare, Medical Image Analysis, Decentralized Learning, Minimally-Invasive and Robot-Assisted Surgery

Projects

The Kolbinger Lab conducts translational research at the intersection of data science and clinical medicine. Our primary goal is to develop computational tools with a direct clinical impact and to facilitate their clinical implementation. Our focus is on advancing technological innovations within the field of surgery and interventional medicine. To achieve this, our lab leverages robust clinical and computational expertise, engaging in national and international collaborations.

Our ongoing projects encompass various domains, including but not limited to:

(1)Prediction of disease progression and outcomes using multimodal clinical datasets (imaging, numerical, categorical, and monitoring data)
(2)Artificial Intelligence-based intraoperative decision support, based on analysis of surgical video data
(3)Decentralized Artificial Intelligence solutions for privacy-preserving collaboration in healthcare
(4)Curation of relevant medical datasets as tools for the scientific community.

We welcome applications from students with diverse academic and training backgrounds including electrical, biomedical or mechanical engineering, computer science, (bio-)medicine, and related fields. We particularly encourage students from underrepresented backgrounds to apply. Dr. Kolbinger strives to create an inclusive and equitable work environment and to ensure that all its members are provided with the training and support they need to pursue and accomplish their personal and professional goals. 

Recruitment Needs

  • We will be hiring 1-2 highly motivated graduate students with a strong background in deep learning-based image analysis to join the team in Fall 2024. 

Please feel free to contact Dr. Fiona Kolbinger directly.

Email: fkolbing@purdue.edu

Website: https://engineering.purdue.edu/BME/People/ptProfile?resource_id=286131