Abstract 2702: Multi-omics data integration of early lung adenocarcinoma reveals an association between radiomics features and tumor biology

Abstract Lung adenocarcinoma (ADC) is a heterogeneous group of tumors associated with different survival rates, even when detected at an early stage. Here, we aim to investigate the biological determinants of early ADC indolence or aggressiveness using radiomics as a surrogate of behavior. We present a set of 93 ADC patients with data collected across different methodologies. Patients were risk-stratified using the Computed Tomography-Based Score Indicative of Lung Cancer Aggression (SILA) tool (continuous score from 0 to 1, 1 being the highest). We grouped the patients as indolent (x <= 0.4, n=14), intermediate (0.4 > x <= 0.6, n=27) and aggressive (0.6 > x <= 1, n=52). Using CyTOF we identified epithelial, mesenchymal, and immune subpopulations characterized by high HLA-DR expression that were associated with indolent behavior. In the RNA-Seq dataset, pathways related to immune response were downregulated in aggressive tumors compared to indolent while pathways associated with cell cycle and proliferation were upregulated. Pathways associated with structural cellular components, epithelial-mesenchymal transition (EMT), and extracellular matrix organization were upregulated in indolent and aggressive when compared to intermediate. We used HealthMyne (HM) software to extract radiomics features from the CT scans of the patients and computed pairwise correlation with SILA to select significant variables. For the data integration step, we selected features that were significantly associated with SILA from the datasets described above. Features’ and patients’ clusters were obtained by hierarchical clustering (k=4). Feature cluster “a” (FC-a) was composed by proteomics and transcriptomics features associated with immune response, antigen presentation, HLA-DR protein expression and HM features negatively associated with SILA, such as percent of ground glass opacity; FC-b was composed by HM features positively associated with SILA, an epithelial cell subset negative for HLA-DR; FC-c was composed by pathways associated with structural cellular components and EMT; FC-d was composed by pathways associated with DNA replication, proliferation and cell cycle. Patients from patient cluster 4 (PC-4) were all aggressive and were high for FC-d, mid for FC-b and FC-c and low for FC-a; Patients from PC-2 were a mix of indolent, intermediate and aggressive and were high for FC-a, low for FC-d and FC-b and a fractioned low/high for FC-c; PC-3 and PC-1 patients were a mix of intermediate and aggressive and the former showed mid signal for FC-b and FC-c and low for FC-a and FC-d while the latter showed low signal for all FCs. PC-4 patients did significantly worst in progression and recurrence free survival compared to all other PCs and to PC-1 alone. In conclusion, we found a bridge between radiomics and tumor biology which could improve the discrimination between indolent and aggressive ADC tumors. Citation Format: Maria-Fernanda Senosain, Yong Zou, Khushbu Patel, Vera Pancaldi, Carlos F. Lopez, Pierre P. Massion. Multi-omics data integration of early lung adenocarcinoma reveals an association between radiomics features and tumor biology [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 2702.