Radiogenomics and Radiomics in Liver Cancers

Abstract

Radiogenomics is a computational discipline that identifies correlations between cross-sectional imaging features and tissue-based molecular data. These imaging phenotypic correlations can then potentially be used to longitudinally and non-invasively predict a tumor's molecular profile. A different, but related field termed radiomics examines the extraction of quantitative data from imaging data and the subsequent combination of these data with clinical information in an attempt to provide prognostic information and guide clinical decision making. Together, these fields represent the evolution of biomedical imaging from a descriptive, qualitative specialty to a predictive, quantitative discipline. It is anticipated that radiomics and radiogenomics will not only identify pathologic processes, but also unveil their underlying pathophysiological mechanisms through clinical imaging alone. Here, we review recent studies on radiogenomics and radiomics in liver cancers, including hepatocellular carcinoma, intrahepatic cholangiocarcinoma, and metastases to the liver.

Keywords: hepatocellular carcinoma; intrahepatic cholangiocarcinoma; liver metastasis; radiogenomics; radiomics.

Figure 1

Diagram of the radiogenomic process. (a) First, imaging traits or “radiographic phenotypes”, such as tumor shape, intensity, margins, and texture, are extracted from segmented images. Genomic maps indicating the expression of individual genes or gene clusters are created from the given tissue specimen. Then, the imaging traits, genomic maps, and other clinical data, including histopathologic information or tumor marker data, are statistically analyzed and aggregated to form a radiogenomic association map. (b) The radiogenomic model is used to gain clinical data, including prognostic and predictive information, for a given set of imaging features and genomic information. (c) Incorporation of outcomes data into the radiogenomic model leads to further refinement and model validation. Reproduced with permission from [4], published by Elsevier, 2018.

Figure 2

Examples of various radiomics features that can be extracted from CT and positron emission tomography (PET) images. Gray-level co-occurrence matrix (GLCM), histogram analysis, mesh-based shape, intensity size zone matrix (ISZM), two-dimensional joint histogram, surface rendering for sigmoid features, and sub-regional portioning are various features than can be extracted from CT and PET images. These features can then be correlated with clinicopathologic data to gain prognostic and predictive information. Reproduced under a CC-BY-NC 4.0 license from [19].