Bringing radiomics into a multi-omics framework for a comprehensive genotype–phenotype characterization of oncological diseases

Abstract

Genomic and radiomic data integration, namely radiogenomics, can provide meaningful knowledge in cancer diagnosis, prognosis and treatment. Despite several data structures based on multi-layer architecture proposed to combine multi-omic biological information, none of these has been designed and assessed to include radiomic data as well. To meet this need, we propose to use the MultiAssayExperiment (MAE), an R package that provides data structures and methods for manipulating and integrating multi-assay experiments, as a suitable tool to manage radiogenomic experiment data. To this aim, we first examine the role of radiogenomics in cancer phenotype definition, then the current state of radiogenomics data integration in public repository and, finally, challenges and limitations of including radiomics in MAE, designing an extended framework and showing its application on a case study from the TCGA-TCIA archives. Radiomic and genomic data from 91 patients have been successfully integrated in a single MAE object, demonstrating the suitability of the MAE data structure as container of radiogenomic data.

The Impact of Normalization Approaches to Automatically Detect Radiogenomic Phenotypes Characterizing Breast Cancer Receptors Status

“…A closely related field is 'radiogenomics', which explores the associations between imaging phenotype (radiomic data) and disease genotype (genomic patterns) [13,14]. Two public data resources such as The Cancer Genome Atlas (TCGA) and The Cancer Imaging Archive (TCIA), provide cancer genomic profiling and medical images counterpart, respectively [15,16], to promote cross-disciplinary research including radiogenomic studies [17][18][19].…”

Radiomic model for differentiating parotid pleomorphic adenoma from parotid adenolymphoma based on MRI images

“…One is that we did not apply the multicenter cases. The other is the lack of the results on the combination of radiological features with tumor molecular markers or genomic information [26,27] . In the future, we will further explore the relationship between radiomics and genomics, and such multi-omics might conducive to the precise diagnosis.…”

From Medical Imaging to Radiomics: Role of Data Science for Advancing Precision Health

“…In such scenario, data science research would be focused to assemble a first layer of raw and processed data, metadata, combined feature measurements, and biomarkers derived from medical images, with another layer fueled by other disease-related factors such as patient prognosis, pathological findings, and genomic profiling. The products of this complex merge of organized, harmonized, and integrated data should become a genotype-phenotype-enriched system that is linkable to other repositories and subjected to full technical validation and further qualification for best possible routine clinical use [35]. Correspondingly, a final goal should consider assimilating such multilevel information and organize it into a prediction model with selected key features depending on defined clinical endpoints.…”