Radiomics: from qualitative to quantitative imaging

Discovery Radiomics for Imaging-driven Quantitative Personalized Cancer Decision Support

In this paper, we describe the underlying methodology behind discovery radiomics, where the ultimate goal is to discover customized, abstract radiomic feature models directly from the wealth of medical imaging data to better capture highly unique tumor traits beyond what can be captured using hand-crafted radiomic feature models. We further explore the current state-of-the-art in discovery radi...

From Quantitative to Qualitative Spaces

Based on previous work, we present our position statement encompassing two mutually complementary topics. The first topic pertains to the ontological grounding of quantitatively specified synthetic environment data. Here, the objective is to generate a qualitative spatial description of a quantitatively modelled (e.g., using primitive geometric features) synthetic environment. The basic aim her...

From Qualitative to Quantitative Probabilistic Networks

Quantification is well known to be a major ob­ stacle in the construction of a probabilistic net­ work, especially when relying on human experts for this purpose. The construction of a qualitative probabilistic network has been proposed as an initial step in a network's quantification, since the qualitative network can be used to gain prelimi­ nary insight in the projected network's reasoning b...

From Qualitative to Quantitative Information Erasure

We define a quantitative measure of information erasure as a dual of the well-understood notion of quantitative information release. Our journey begins from a qualitative, equivalence relations-based, definition of information erasure and release, which we show to be tightly linked to the quantitative measures of these notions. In particular, given the necessary probability distribution over th...

Prostate cancer Radiomics using multiparametric MR imaging