Abstract
This project aims at integrating multi-parametric MR imaging phenotypes (radiomics), tumour metabolites abundance derived from NMR spectroscopy (metabolomics), and combined with genome wide DNA methylation – (epi)genomics – to extract combined biomarkers supported by machine learning algorithms, a combination of methods that has not been previously tested. The novel non-invasive imaging biomarkers, derived from the complex integration of the multifaceted data during the lifetime of this program, are expected to increase the diagnostic accuracy for brain tumours and elucidate the complex tumour pathophysiology, providing a platform that will transform the diagnostics and therapeutics in these patients.
References
- Caulo M, Panara V, Tortora D, et al. (2014) Data-driven grading of brain gliomas: a multiparametric MR imaging study. Radiology. 272:494-503.
- Chinnaiyan P, Kensicki E, Bloom G, et al. (2012) The metabolomic signature of malignant glioma reflects accelerated anabolic metabolism. Cancer Res. 72:5878–88.
- Ellingson BM. (2015) Radiogenomics and imaging phenotypes in glioblastoma: novel observations and correlation with molecular characteristics. Curr Neurol Neurosci Rep.15:506
- Kitchen RR, Rozowsky JS, Gerstein MB, Nairn AC. (2014) Decoding neuroproteomics: integrating the genome, translatome and functional anatomy. Nature Neuroscience 17:1491–99
- Richiardi J, Altmann A, Milazzo AC et al. (2015) BRAIN NETWORKS. Correlated gene expression supports synchronous activity in brain networks. Science. 348:1241-4.