VISIBLE: The future of radiomics: understanding, Validating and Increasing the Specificity of Imaging Biomarkers for personaLizEd medicine
We plan to build upon ongoing efforts in (i) the development of novel imaging biomarkers and (ii) deployment of web-based radiomics platforms. (i) includes novel trainable and highly-specific texture operators that already achieved state-of-the-art performance in a variety of applications. (ii) allows bringing front-end open access to our latest research outcomes to medical researchers and practitioners. Second, the project will innovate in the validation of the developed methods by moving from tumor- to habitat- level validation (i.e., seeking for cancer hallmarks) based on high-quality and innovative datasets gathered at the CHUV, international collaborations and public sources. These will include the acquisition of subjects with sub-tumoral local ground truth based on localized stereotactic core biopsies for histopathological and molecular analyses as well as molecular tracers of hallmarks (e.g., cell proliferation, hypoxia, angiogenesis). While being expensive and difficult to use in clinical routine, the aforementioned biomarkers can be used transiently to consolidate the link between radiomics attributes and tumor habitats. The proposal will primarily focus on Non-Small Cell Lung Cancer (NSCLC) and GlioBlastoma Multiforme (GBM) as they are two important cancer types with most data and knowledge available.
Swiss National Science Foundation (SNSF) project number 205320_179069