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.

Radiogenomics analysis reveals the associations of dynamic contrast-enhanced–MRI features with gene expression characteristics, PAM50 subtypes, and prognosis of breast cancer

“…Compared with previous radiogenomics studies, although our work overcame a few shortcomings, it still had some limitations ( 56 , 66 , 67 ). First, we used two radiogenomics cohorts of BC: one was a local single-center dataset for discovery ( n = 174) and another was a public multi-center dataset for validation ( n = 72).…”

Radiomics analysis in medical imaging research

“…Clinically important problems that have been addressed using radiomic analysis include (1) predicting patient prognosis in patients with lung cancers (2) predicting patients with lung cancer's response to therapy and which type of therapy is optimal (3) predicting whether lung tumours have certain molecular subtypes or genetic mutations, (4) predicting whether a pulmonary nodule is benign or malignant and requires biopsy. 8,[23][24][25] Recent studies have also shown that radiomic analysis of computed tomography (CT) scans of the chest can differentiate patients with coronavirus disease 2019 (COVID-19) from patients with other pneumonia of different aetiologies. [26][27][28] Radiomic analysis has been shown to predict (a) whether a patient who is positive for COVID-19 needs to be hospitalised (b) to predict whether a patient who is positive COVID-19 would need the intensive care unit (ICU) and/or ventilators [29][30][31] (c) how long a patient with COVID-19 is expected to be hospitalised (d) future mortality risk from COVID-19 and (e) predicting whether patients with COVID-19 go on to develop long COVID-19.…”

Imaging in translational cancer research

“…Initially, RF extraction was performed in neuroimaging, e.g., to achieve radiomic profiling of glioblastoma tissue to identify imaging predictors of patient survival and anti-angiogenic treatment response 218 , 219 . Many other studies have applied RF extraction to all types of tumors and imaging modalities, most prominently lung tumors 220 , often in combination with genomic profiling, termed radiogenomics 221 . In many cases, relevant RFs have been found to discriminate between different tumor classes, e.g., low- and high-grade gliomas 222 ; to be highly sensitive to cancerous tissue as in breast cancer 223 ; or to predict treatment response in prostate cancer 224 .…”