This study created and assessed a parsimonious radiomic model that was able to identify a vulnerable subset of screen-detected lung cancers that are associated with poor outcome.
Researchers have recently demonstrated how the use of radiomics can improve screening by identifying patients with early stage lung cancer who may be at high risk for poorer outcomes, and therefore require aggressive follow-up and/or adjuvant therapy.1
The study, published in Nature Scientific Reports, could support the use of more aggressive treatment and follow-up for such high-risk patients. However, the researchers indicated that further research is necessary to validate these findings.
“Identifying predictive biomarkers that detect aggressive cancers or those that may be slow developing and non-emergent are a critical unmet need in the lung cancer screening setting,” Matthew Schabath, PhD, associate member of the Cancer Epidemiology Department at Moffitt Cancer Center, said in a press release.2 “Additional research is needed to inform us on the potential translational implications of this model, but it could make a major impact on saving lives by identifying lung cancer patients with aggressive disease while also sparing others from unnecessary therapy.”
Using data from the National Lung Screening Trial (NLST) – a study which compared low dose CT and standard chest x-ray – researchers generated radiomic features from patients included in the NLST who were diagnosed with lung cancer during their screening. Features, including size, shape, volume and textural characteristics, were calculated intratumorally and peritumorally. Based on this information, patients were then split into training and test cohorts; an additional external cohort of non-screen detected patients with lung cancer was used for further validation.
More specifically, researchers identified a model that contained 2 radiomics features, 1 peritumoral and 1 intratumoral, which stratified patients into 3 risk-groups – low-risk, intermediate-risk, and high-risk.
“Our goal was to use radiomic features to develop a reproducible model that can predict survival outcomes among patients who are diagnosed during a lung cancer screening,” lead study author Jaileene Pérez-Morales, PhD, a postdoctoral fellow at Moffitt, said in the release.
The model was able to identify a vulnerable group of patients with early-stage lung cancer with worse overall survival (HR, 9.91; 2.5-year OS, 25% and 5-year OS, 0%) versus the low-risk group (HR, 1.00; 2.5-year OS, 93% and 5-year OS, 78%). The final model was then validated in the test cohort and further replicated in a cohort of patients with non-screen detected adenocarcinoma.
Notably, there were no statistically significant differences observed between the 3 risk groups by age, smoking status, number of pack-years smoked, self-reported COPD, and family history of lung cancer, histological subtypes, and treatment. However, there were statistically significant differences seen across the risk groups for sex (P = 0.04) and stage of disease (P = 0.001). Specifically, 92% of the patients in the high-risk group in were male compared to 54% in the low-risk group (P = 0.04). In terms of lung cancer stage, 33% of participants in the high-risk group had early-stage lung cancer versus 80% in the low-risk group (P = 0.001).
Because disease stage was found to vary significantly across the risk groups, researchers stratified the model by stage and found compelling results among early stage patients, which typically have very good survival outcomes. Among this patient population, the high-risk group was associated with a worse OS (HR, 2.63; 2.5-year OS, 56% and 5-year OS, 42%) compared to the low-risk group (HR = 1.00; 2.5-year OS, 75% and 5-year OS, 75%).
“[Cumulatively], the evidence of our study and others have [demonstrated] the utility of using peritumoral features alone or in combination with intratumoral features,” the authors wrote.
Importantly, though the overall population of patients with lung cancer were treated heterogeneously, among the early stage patients, 92.74% of the patients had surgery as their only treatment. In addition, the validation cohort was limited to strictly patients with lung adenocarcinoma; therefore, additional research is warranted to validate the biological underpinnings of these features.
“The results from our analyses produced a parsimonious radiomic model that identified a vulnerable subset of screen-detected lung cancers that are associated with poor outcome,” the authors wrote. “Nonetheless, additional research will be needed to inform the potential translational implications of these findings, to fully elucidate the biology [of] these high-risk screen-detected tumors, to assess whether these findings are consistent across screening trials and cohorts, and [to determine] how best to personalize cancer management in these vulnerable patients.”
1. Pérez-Morales J, Tunali I, Stringfield O, Eschrich SA, Balagurunathan Y, Gillies RJ, Schabath MB. Peritumoral and intratumoral radiomic features predict survival outcomes among patients diagnosed in lung cancer screening. Nature Scientific Reports. doi: 10.1038/s41598-020-67378-8.
2. Moffitt Researchers Develop Tool to Detect Patients at High Risk for Poor Lung Cancer Outcomes [news release]. Tampa, Florida. Published July 1, 2020. newswise.com/articles/moffitt-researchers-develop-tool-to-detect-patients-at-high-risk-for-poor-lung-cancer-outcomes?sc=sphr&xy=10021790. Accessed July 28, 2020.