Immunotherapy outcome prediction
In the last decade, cancer immunotherapy has been revolutionizing cancer care. Immunotherapy is a systemic cancer treatment that exploits the power of the body’s immune system to fight cancer cells by boosting the immune response. Despite the success of immunotherapy in treating specific cancer types, the overall response rate is low. Because of potential side effects and the high cost of immunotherapy, it is crucial to identify which patients would benefit from this therapy. In the AI for Oncology lab, we develop AI algorithms to help predict immunotherapy treatment outcomes and improve patient selection.
As a patient's response to immunotherapy is governed by a complex interplay between genes, tumor microenvironment, and host, we employ all types of data obtained from each patient. This includes data sources such as resected tumor tissue stained with hematoxylin and eosin (H&E), immunohistochemistry (IHC), or multiplex immunofluorescence assays, RNA or DNA sequencing data, and radiological imaging such as CT and MRI scans.
- A. Panteli, J. Teuwen, H. Horlings, E. Gavves, "Sparse-shot Learning with Exclusive Cross-Entropy for Extremely Many Localisations", 2021
- Y. Schirris, E. Gavves, I. Nederlof, H. M. Horlings, J. Teuwen, "DeepSMILE: Self-supervised heterogeneity-aware multiple instance learning for DNA damage response defect classification directly from H&E whole-slide images", 2021
- B. P. Y. Kwee, M. Messemaker, E. Marcus, G. Oliveira, W. Scheper, C. J. Wu, J. Teuwen, T. N. Schumacher, "STAPLER: Efficient learning of TCR-peptide specificity prediction from full-length TCR-peptide data", 2023