Carolien van Deurzen

Erasmus MC

In short, Carolien van Deurzen's research entails the following:

Response prediction to neoadjuvant chemotherapy in patients with triple negative breast cancer based on integrated diagnostics

Triple negative breast cancer is the most aggressive, most difficult to treat form of breast cancer and is relatively common in young women. These patients usually undergo chemotherapy, preferably before surgery. In some of these patients (about 40-50%) the tumor disappears completely after this treatment, in the rest it does not. For personal treatment, i.e. 'tailor-made therapy', it is important to predict, prior to chemotherapy, which patients will respond well to the treatment and which will not. To do this, we will combine characteristics of the cancer cells, the surrounding inflammatory cells and MRI scans of the breast with new techniques.

Short summary of progress/results July 2025

In the first period of this project, we have identified the patients eligible for inclusion, and collected and pseudonymised data of 75% of the anticipated cohort. The collected tissue materials are also being processed. For the MRI data, we have started the construction of a pipeline that can automatically process the scans and use them in a deep learning model to predict a patient's response to neoadjuvant chemotherapy.