Gastro-Esophageal cancer (GEC) has a dismal prognosis.
Novel immunotherapy treatment (IMT) shows promising therapeutic results in a subset of all cancer patients but is highly costly.
To select patients that will benefit, medical specialists like pathologist need to quantify biomarkers that are predictive for IMT outcome. Various cancer types require either PD-L1, or tumor infiltrating lymphocytes (TIL) or tumor-foreignness biomarker testing. These biomarker assessments are however complex, expensive and suffer from interobserver variability. Current limited testing methods result in unwanted variation in patient outcome and high healthcare costs.
An evident clinical need exists for objective, integrated and easy to use decision support tools, to optimize personalized treatment and identify GEC patients that will respond to IMT. We will address these needs using Artificial Intelligence (AI) at multiple levels, as simultaneous biomarker assessment is currently not standard operational procedure and integrated assessment is too complex for individual medical specialists. In the first part of the project, we intend to alleviate this problem, by using medical imaging and computer vision algorithms to accurately quantify the multimodal morphological and genomic biomarker parameters PD-L1, TIL and tumor foreignness directly on standard histopathology H&E slides without the need of performing additional test. Secondly, as the primary goal of all these analyses is to predict response to immunotherapy and disease outcome, we will also consider the problem from a knowledge discovery perspective which biomarkers or combinations are responsible for this specific outcome and response prediction?
In this project we will need to develop state of the art deep learning techniques for determination, integration of spatial quantification of individual biomarkers from histopathology slides, and outcome prediction in multidisciplinary clinical data. Additionally, we will design novel self-supervised geometric deep learning techniques and combine these with model interpretability techniques to discover new knowledge about gastro-esophageal cancer and outcome to immunotherapy treatment.
Our goal is to bring these models into the daily clinical practice of pathologists and oncologists to identify patients who may benefit most from immunotherapy or could be spared unnecessary treatment.
About your roleAs a PhD-candidate, you will be responsible for developing and evaluating state-of-the-art deep learning techniques in multidisciplinary medical data. You will be involved in preparing histopathology datasets of GEC patients for cancer-immune interaction and clinical outcome data. Finally, you will validate the algorithms you developed with immunotherapy treatment outcome in independent patient cohorts to ensure the devised AI-algorithms' applicability in clinical practice.
- You will collaborate with other researchers within the research labs of the SELECT-AI consortium (Amsterdam UMC departments of Pathology and Medical Oncology, University of Amsterdam the Institute of Informatics, and the department of Pathology from NKI-AvL).
- Regularly present internally on your progress
- Regularly present intermediate research at international conferences and workshops, publish them in proceedings and journals, help with submitting applications
- Assist in relevant teaching activities
- Complete and defend a PhD thesis
For this project two PhD students are recruited, one student with more focus on fundamental AI-algorithm development and one on clinical applicable AI methods.