Radiomic biomarkers for the prediction of immunotherapy outcome in patients with metastatic non-small cell lung cancer.

Abstract

e14520 Background: PD-1 checkpoint inhibitors have recently been approved for the treatment of patients with metastatic NSCLC. Predicting to what extent patients will benefit from these treatments is challenging. Research on predictive biomarkers focus on genetic and histological markers from biopsies, necessarily limited to parts of the tumor. Radiomics is a novel approach to quantify characteristics of the tumor on medical imaging, which may have potential value as non-invasive biomarkers. In this study, we explored the value of radiomic data from primary tumors to predict overall survival (OS) in patients with metastatic NSCLC treated with Nivolumab Methods: We retrospectively selected 64 metastatic NSCLC patients treated in 2ndline setting with Nivolumab (240 mg q 2 weeks until progression). Inclusion criteria were: primary tumor in situ with contrast enhanced CT scan (thorax abdomen; slice thickness ≤3mm) within 6 weeks before the start of the treatment. Exclusion criteria were: presence of atelectasis or fusion with other structures and presence of multiple lung lesions at first scan. A certified radiologist delineated the tumors on CT from which we extracted 1696 Radiomic features. Unsupervised feature selection was performed. Multivariate Cox Regression was used to model the OS based on the selected features, as well as, histopathological type (adeno vs squamous), age at the start of the treatment, and extent of metastatic disease ( < 5, 5–10, or > 10 metastasis) Results: The selection resulted in three textural features derived from a Laplacian of Gaussian (LoG): regions dissimilarity (GLRLM_rlnun), entropy (GLSZM_ze), and uniformity. The resulting model was significant (p = 0.005). Both regions dissimilarity (HR = 0.11, 95% CI 0.03–0.46, p = 0.002) and entropy (HR = 0.20, 95% CI 0.06–0.67, p = 0.009) were significant predictors of OS. Subtype and disease extent were close to significance (p = 0.099) Conclusions: Results indicate that more heterogeneous tumors with irregular patterns of intensities showed better OS. The availability of CT scans makes Radiomics a potentially valuable adjunct to other clinical biomarkers. Further validation of our findings in larger cohorts are warranted

Changes in CT Radiomic Features Associated with Lymphocyte Distribution Predict Overall Survival and Response to Immunotherapy in Non–Small Cell Lung Cancer

“…Previous studies have also used radiomics to predict response to ICIs (15,24,62,63). Response to immunotherapy was negatively correlated with tumor convexity and positively correlated with edgeto-core size ratio on CT scans of patients with NSCLC (64).…”

“…Indeed, radiomic features in regions around the tumor might reflect immune response in breast and lung cancers (9)(10)(11). In addition to intranodular heterogeneity in PD-L1 status (12)(13)(14)(15), microenvironmental factors in the peritumoral region may be contributing to treatment failure. For instance, angiogenesis, a pathologic response to hypoxia, is routinely observed adjacent to the tumor.…”

Role of artificial intelligence in the care of patients with nonsmall cell lung cancer

“…Research on predictive biomarkers is currently focused on genetic and histological markers from biopsies. However, ML and radiomics have shown promising results in improving patient selection and outcome prediction by providing unique insights into tumour and its microenvironment in a noninvasive manner . For example, Charoentong et al used ML algorithms on cancer antigenomes from The Cancer Immunome Atlas to identify determinants of tumour immunogenicity and developed a scoring scheme for predicting response to CPI's, while Coroller et al demonstrated predictive radiomic features for treatment response using CT data .…”

A tumor vasculature–based imaging biomarker for predicting response and survival in patients with lung cancer treated with checkpoint inhibitors

“…Radiomics refers to the process of image analysis that results in high-throughput extraction of subvisual and quantitative features from radiologic scans including x-rays, computed tomography (CT), ultrasound, and magnetic resonance imaging. Recently, radiomic approaches have been applied in the context of prognosticating outcome and predicting response to IO (11)(12)(13)(14). Most of these studies have analyzed the tumoral shape and textural radiomic features for predicting response and outcome in patients with NSCLC.…”