Radiomics/Radiogenomics in Lung Cancer: Basic Principles and Initial Clinical Results

Abstract

Lung cancer is the leading cause of cancer-related deaths worldwide, and elucidation of its complicated pathobiology has been traditionally targeted by studies incorporating genomic as well other high-throughput approaches. Recently, a collection of methods used for cancer imaging, supplemented by quantitative aspects leading towards imaging biomarker assessment termed "radiomics", has introduced a novel dimension in cancer research. Integration of genomics and radiomics approaches, where identifying the biological basis of imaging phenotypes is feasible due to the establishment of associations between molecular features at the genomic-transcriptomic-proteomic level and radiological features, has recently emerged termed radiogenomics. This review article aims to briefly describe the main aspects of radiogenomics, while discussing its basic limitations related to lung cancer clinical applications for clinicians, researchers and patients.

Keywords: image science; learning algorithms; lung cancer; radiogenomics; radiomics; review.

Figure 1

Typical workflow of a radiomic analysis. Initially, the proper medical imaging modality is selected (PET–CT in our example. Then, the radiologist segments the tissue of interest in all slices, resulting in a volume of interest. Consequently, radiomic features are computed using only the tissues included in the volume of interest. Such features can reflect shape information, signal intensities of tissues inside the VOI, and texture-related information that can reflect tissue heterogeneity. Finally, machine learning models are trained and validated to predict clinical outcomes or to classify patients according to genomic or molecular characteristics.