A1027
Title: Quantifying imaging heterogeneity via density functions with applications in brain and pancreatic cancer imaging
Authors: Shariq Mohammed - Boston University (United States) [presenting]
Abstract: The quantification of heterogeneity in the tumor microenvironment is extremely important as visually differentiating disease types is challenging. A statistical framework is presented that quantifies spatial interactions in biomedical images to build prediction models for clinical phenotypes. A spatial regression model is first built to assess spatial interactions in regions of interest in the image. The heterogeneity in the spatial interactions in each image is then represented as a probability density function (serving as a signature quantifying spatial interactions). These density functions are analyzed using a Riemannian-geometric framework to include them as covariates in models that predict clinical outcomes of interest. The methodology is presented with applications to radiology imaging in brain cancer to predict isocitrate dehydrogenase mutation and to pathology imaging in pancreatic cancer to distinguish between different pancreatic disease subtypes.
