Prostate cancer exhibits intra-tumoral heterogeneity that we hypothesize to be the leading confounding factor contributing to the underperformance of the current pre-treatment clinical-pathological and genomic assessment. These limitations impose an urgent need to develop better computational tools to identify men with low risk of prostate cancer versus others that may be at risk for developing metastatic cancer. The patient stratification will directly translate to patient treatments, wherein decisions regarding active surveillance or intensified therapy are made. Multiparametric MRI (mpMRI) provides the platform to investigate tumor heterogeneity by mapping the individual tumor habitats. We hypothesize that quantitative assessment (radiomics) of these habitats results in distinct combinations of descriptors that reveal regions with different physiologies and phenotypes. Radiogenomics, a discipline connecting tumor morphology described by radiomic and its genome described by the genomic data, has the potential to derive “radio phenotypes” that both correlate to and complement existing validated genomic risk stratification biomarkers. In this article we first describe the radiomic pipeline, tailored for analysis of prostate mpMRI, and in the process we introduce our particular implementations of radiomics modules. We also summarize the efforts in the radiomics field related to prostate cancer diagnosis and assessment of aggressiveness. Finally, we describe our results from radiogenomic analysis, based on mpMRI-Ultrasound (MRI-US) biopsies and discuss the potential of future applications of this technique. The mpMRI radiomics data indicate that the platform would significantly improve the biopsy targeting of prostate habitats through better recognition of indolent versus aggressive disease, thereby facilitating a more personalized approach to prostate cancer management. The expectation to non-invasively identify habitats with high probability of housing aggressive cancers would result in directed biopsies that are more informative and actionable. Conversely, providing evidence for lack of disease would reduce the incidence of non-informative biopsies. In radiotherapy of prostate cancer, dose escalation has been shown to reduce biochemical failure. Dose escalation only to determinate prostate habitats has the potential to improve tumor control with less toxicity than when the entire prostate is dose escalated.

Association of multiparametric MRI quantitative imaging features with prostate cancer gene expression in MRI-targeted prostate biopsies

Tumor heterogeneity can be elucidated by mapping subregions of the lesion with differential imaging characteristics, called habitats. Dynamic Contrast Enhanced (DCE-)MRI can depict the tumor microenvironments by identifying areas with variable perfusion and vascular permeability, since individual tumor habitats vary in the rate and magnitude of the contrast uptake and washout. Of particular interest is identifying areas of hypoxia, characterized by inadequate perfusion and hyper-permeable vasculature. An automatic procedure for delineation of tumor habitats from DCE-MRI was developed as a two-part process involving: (1) statistical testing in order to determine the number of the underlying habitats; and (2) an unsupervised pattern recognition technique to recover the temporal contrast patterns and locations of the associated habitats. The technique is examined on simulated data and DCE-MRI, obtained from prostate and brain pre-clinical cancer models, as well as clinical data from sarcoma and prostate cancer patients. The procedure successfully identified habitats previously associated with well-perfused, hypoxic and/or necrotic tumor compartments. Given the association of tumor hypoxia with more aggressive tumor phenotypes, the obtained in vivo information could impact management of cancer patients considerably.

In solid tumors, hypoxia contributes significantly to radiation and chemotherapy resistance and to poor outcomes. The "gold standard" pO(2) electrode measurements of hypoxia in vivo are unsatisfactory because they are invasive and have limited spatial coverage. Here, we present an approach to identify areas of tumor hypoxia using the signal versus time curves of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data as a surrogate marker of hypoxia. We apply an unsupervised pattern recognition (PR) technique to determine the differential signal versus time curves associated with different tumor microenvironmental characteristics in DCE-MRI data of a preclinical cancer model. Well-perfused tumor areas are identified by rapid contrast uptake followed by rapid washout; hypoxic areas, which are regions of reduced vascularization, are identified by delayed contrast signal buildup and washout; and necrotic areas exhibit slow or no contrast uptake and no discernible washout over the experimental observation. The strength of the PR concept is that it captures the pixel-enhancing behavior in its entirety-during both contrast agent uptake and washout-and thus, subtleties in the temporal behavior of contrast enhancement related to features of the tumor microenvironment (driven by vascular changes) may be detected. The assignment of the tumor compartments/microenvironment to well vascularized, hypoxic, and necrotic is validated by comparison to data previously obtained using complementary imaging modalities. The proposed novel analysis approach has the advantage that it can be readily translated to the clinic, as DCE-MRI is used routinely for the identification of tumors in patients, is widely available, and easily implemented on any clinical magnet.