maging biomarkers for treatment response

Co-PI: Eliana Gioscio

Our research focuses on identifying and validating imaging biomarkers to predict and monitor treatment response in oncology treatments. We extract quantitative features from standard imaging modalities such as CT, MRI, and PET, as well as from non-conventional imaging systems, including sublingual microcirculation microscopy (e.g., Glycocheck) and spectrophotometric devices. These diverse sources provide complementary insights into tumor biology, vascular function, and tissue composition.

We explore integrating multimodal imaging data to capture complex spatial and temporal patterns of tumor and normal tissue response. Radiomic analysis and machine learning techniques are used to develop predictive models that combine imaging biomarkers with clinical, dosimetric, and biological information. A key aspect of our work includes using physical and digital phantoms to assess the robustness and reproducibility of imaging features across different acquisition systems and settings.

Our studies aim to ensure methodological rigor and reproducibility, focusing on protocol standardization and multi-center validation. This integrated approach supports the development of non-invasive, data-driven biomarkers for driving personalized and adaptive radiotherapy strategies.