The Hanarth Fonds will finance the research projects of Iris Nagtegaal, theme Tumours of the digestive tract and Johannes Textor, theme Cancer development and immune defence. The fund aims to promote and enhance the use of artificial intelligence and machine learning to improve the diagnosis, treatment and outcome of patients with cancer.
Iris Nagtegaal: “CUP fight: detecting the origin of metastatic disease”
'Cancer of unknown primary sites (CUP) refer to all metastatic cancers where no primary location has been determined. This patient group accounts for 2.5% of all newly diagnosed cancer patients. The outcomes in this patient group are poor, because treatment is usually based on the primary location of the cancer. Even with the current improved diagnostic methods, ever year approximately 1,300 patients are diagnosed with CUP in the Netherlands. Their survival is less than 6 months. With artificial intelligence, we will explore big data in order to determine metastatic patterns of patients with a known primary location and develop a probability model based on metastatic location. We will subsequently incorporate routinely used biomarkers to optimize decision making, which we will test in a proof-of-concept study. As a result of our study we will deliver a prediction model that can be used in a prospective clinical trial to improve outcomes of patients with CUP.' read more
Johannes Textor: ''Transfer learning for immune cell landscape analysis in salivary gland cancer''
'Salivary gland cancer is a rare type of head-and-neck cancer with 150-200 diagnoses per year in the Netherlands, and the most aggressive subtypes have poor prognosis. To develop new treatment options, we are imaging the interactions between immune system cells and tumor cells within patient biopsies using high-resolution digital microscopy. Machine learning approaches are the state of the art for analyzing such data, but they can require very large datasets to train on, which are usually not available for rare cancer types. In our project, we will address this problem using "transfer learning" methodology that allows machine learning algorithms to benefit from experience gained on larger datasets from more common cancer types and train more effectively on smaller datasets. Leveraging existing data and knowledge in this manner, we hope that our project will help to build a rationale for future immunotherapy treatments for salivary gland caner patients.' read more