Ronald Boellaard

Amsterdam UMC

In short, Ronald Boellaard's research entails the following:

AI for improved prognosis and treatment response prediction using FDG PET/CT in multiple myeloma

Multiple myeloma (MM) is an aggressive malignancy of plasma cells in the bone marrow with an annual incidence of ~7 patients per 100,000 inhabitants. The disease cannot be cured and 20% of the patients do not respond (well) to standard therapy, resulting in an even worse outcome (progression free survival < 2 years). Better prognostification and selection of patients, as well as early response assessment based on (lack of) minimal residual disease will avoid futile treatments. There is an urgent need to better discriminate high-risk from standard-risk patients to shift from standard treatments to a more risk-adapted approach. Several studies showed that FDG-PET/CT has high potential to improve prognosis and assess early response.

In this project we aim to apply, adapt and further develop AI methods - e.g., the ones developed for diffuse large B cell lymphoma, funded by a previous Hanarth Fonds Foundation grant - to improve FDG PET/CT-based prognosis (for personalized treatment selection) using baseline scans and early response assessment after induction therapy based on minimal residual disease (MRD) for MM patients. The ultimate aim is to replace the difficult and variable visual reads and criteria by making more reliable, observer-independent quantitative AI reads of FDG PET/CT available and thereby better guide patient treatment selections and adaptions for clinical research.  Moreover, we will combine information extracted by AI from both PET and (low dose) CT for better assessment in a quantitative manner in order to derive objective image-based criteria to determine eligibility for more intensive treatment options.