Non-Small Cell Lung Cancer Radiogenomics Map Identifies Relationships between Molecular and Imaging Phenotypes with Prognostic Implications

Abstract

Purpose To create a radiogenomic map linking computed tomographic (CT) image features and gene expression profiles generated by RNA sequencing for patients with non-small cell lung cancer (NSCLC). Materials and Methods A cohort of 113 patients with NSCLC diagnosed between April 2008 and September 2014 who had preoperative CT data and tumor tissue available was studied. For each tumor, a thoracic radiologist recorded 87 semantic image features, selected to reflect radiologic characteristics of nodule shape, margin, texture, tumor environment, and overall lung characteristics. Next, total RNA was extracted from the tissue and analyzed with RNA sequencing technology. Ten highly coexpressed gene clusters, termed metagenes, were identified, validated in publicly available gene-expression cohorts, and correlated with prognosis. Next, a radiogenomics map was built that linked semantic image features to metagenes by using the t statistic and the Spearman correlation metric with multiple testing correction. Results RNA sequencing analysis resulted in 10 metagenes that capture a variety of molecular pathways, including the epidermal growth factor (EGF) pathway. A radiogenomic map was created with 32 statistically significant correlations between semantic image features and metagenes. For example, nodule attenuation and margins are associated with the late cell-cycle genes, and a metagene that represents the EGF pathway was significantly correlated with the presence of ground-glass opacity and irregular nodules or nodules with poorly defined margins. Conclusion Radiogenomic analysis of NSCLC showed multiple associations between semantic image features and metagenes that represented canonical molecular pathways, and it can result in noninvasive identification of molecular properties of NSCLC. Online supplemental material is available for this article.

Figure 1:

Overview of radiogenomic analysis to identify associations between, A, semantic features at CT and, B, RNA sequencing data.

Figure 2:

Radiogenomic map revealing 32 statistically significant associations between 35 CT semantic features and top 10 metagenes in NSCLC. Only image features above the variance cutoff of 10% are shown. The order of image features and metagenes is determined by hierarchical clustering of the P values.

Figure 3a:

Association of the activity of metagene 19 with two distinct image phenotypes. (a) Low activity of metagene 19 is associated with low activity of LRIG1 (green arrow), and high activity of the EGF–EGF receptor (EGFR; red arrow) pathway results in cell proliferation through activating KRAS and PIK3CA. (b) High activity of metagene 19 results in high activity of LRIG1 (red arrow) with inhibition of the EGF–EGF receptor pathway (green arrow), but results in higher occurrence of EGF receptor mutations, which severs the link between LRIG1 and EGF receptor.

Figure 3b:

Association of the activity of metagene 19 with two distinct image phenotypes. (a) Low activity of metagene 19 is associated with low activity of LRIG1 (green arrow), and high activity of the EGF–EGF receptor (EGFR; red arrow) pathway results in cell proliferation through activating KRAS and PIK3CA. (b) High activity of metagene 19 results in high activity of LRIG1 (red arrow) with inhibition of the EGF–EGF receptor pathway (green arrow), but results in higher occurrence of EGF receptor mutations, which severs the link between LRIG1 and EGF receptor.

Figure 4:

Box-and-whisker plot shows the distribution of the normalized expression of metagene 19 regarding different types of nodule margins at CT. The normalized expression of metagene 19 reflects the activity of the genes in this metagene.