Background
Invasive breast cancer is increasingly treated with neoadjuvant (i.e., pre-operative) chemotherapy. However, it is effective only for some patients.
Project goal
Develop biomarkers based on the joint analysis of multiple digital pathology whole-slide images of pre-operative breast cancer biopsies stained with hematoxylin and eosin (H&E) and a panel of immunohistochemical (IHC) markers to predict treatment response.
Tasks
- Develop deep learning systems to quantify biomarkers in IHC slides
- Apply existing deep learning models for the extraction of some biomarkers
- Align extracted features via registration across multiple slides
- Use extracted features to build a prediction model of treatment response
Requirements
- Students with a major in computer science, biomedical engineering, artificial intelligence, physics, or a related area in the final stage of master level studies are invited to apply.
- Affinity with programming in Python
- Interest in deep learning and medical image analysis
Information
- Project duration: 6 months
- Location: Radboud University Nijmegen Medical Center
- For more information please contact Francesco Ciompi
