Glioma Grade Classification via Omics Imaging

Omics imaging is an emerging interdisciplinary field concerned with the integration of data collected frombiomedical images and omics experiments. Bringing together information coming from different sources, itpermits to reveal hidden genotype-phenotype relationships, with the aim of better understanding the onsetand progression of many diseases, and identifying new diagnostic and prognostic biomarkers. In this work,we present an omics imaging approach to the classification of different grades of gliomas, which are primarybrain tumors arising from glial cells, as this is of critical clinical importance for making decisions regardinginitial and subsequent treatment strategies. Imaging data come from analyses available in The Cancer ImagingArchive, while omics attributes are extracted by integrating metabolic models with transcriptomic dataavailable from the Genomic Data Commons portal. We investigate the results of feature selection for the twotypes of data separately, as well as for the integrated data, providing hints on the most distinctive ones thatcan be exploited as biomarkers for glioma grading. Moreover, we show how the integrated data can provideadditional clinical information as compared to the two types of data separately, leading to higher performance.We believe our results can be valuable to clinical tests in practice.