Radiomics, a growing area of cancer research that extracts noninvasive biomarkers from medical imaging, may be able to improve lung cancer screening by identifying patients with early stage disease at high risk for poorer outcomes.
This is the conclusion from a group of researchers who used data from the National Lung Screening Trial (NLST) to develop and validate a model based on radiomics that could identify a vulnerable high-risk group of early stage patients associated with poor outcomes. These patients would generally require aggressive follow-up and/or adjuvant therapy.
The study was published June 29 in Nature Scientific Reports.
Radiomics, also known as quantitative image features, are noninvasive biomarkers that are generated from medical imaging. An emerging translational field of research, radiomics extracts large amounts of features from radiographic medical images using data-characterization algorithms, which reflect the underlying tumor pathophysiology and heterogeneity.
The authors note that radiomics has many advantages over circulating and tissue-based biomarkers, as these quantitative image features are rapidly calculated from standard-of-care imaging and reflect the entire tumor burden — and not just a sample as is the case with tissue-based biomarkers.
"We view radiomics as a decision support tool across the cancer control continuum, whether it be screening and early detection, diagnosis, prognostication, or treatment response," said lead author Matthew B. Schabath, PhD, associate member in cancer epidemiology at the H. Lee Moffitt Cancer Center & Research Institute in Tampa, Florida.
"Radiomic features are generated from standard-of-care imaging and validated radiomic models can provide real-time decision support information to clinicians," he explained.
Last year, another study showed that combining radiomics and imaging may be able to determine which patients with lung cancer were most likely to respond to chemotherapy. The researchers used CT imaging of radiomic features from within and outside the lung nodule and found it could predict time to progression and overall survival, as well as response to chemotherapy, in patients with non-small cell lung cancer (NSCLC).
Anant Madabhushi, PhD, a professor of biomedical engineering and director of the Center for Computational Imaging and Personalized Diagnostics at Case Western Reserve University in Cleveland, Ohio, commented that the new study is "complementary and supports the premise that radiomics both from inside and outside the tumor can tell us about outcome and treatment response."
Madabhushi also noted his group has released several other studies along similar lines, including a study showing how radiomics can predict the benefit of adjuvant therapy in lung cancer, a study showing how radiomics can predict recurrence in early stage NSCLC, and a study showing that radiomics can predict survival and response to immunotherapy in NSCLC.
Improving Current Lung Cancer Screening
The landmark NLST showed that, as compared with chest x-rays, low-dose helical computed tomography (LDCT) was associated with a 20% relative reduction in lung cancer mortality in high-risk individuals. However, LDCT screening can lead to overdiagnosis and subsequent overtreatment of slow-growing, indolent cancers.
"Current lung cancer screening inclusion criteria in the US are largely based on the criteria used in the NLST," Schabath told Medscape Medical News. "Though the NLST clearly demonstrated that screening LDCT is a lifesaving tool, the NLST was not designed to create public policy."
He pointed out that fewer than 30% of Americans diagnosed with lung cancer meet the current screening entry criteria and that subsequent trials (eg, NELSON, LUSI, or MILD) used broader and more inclusive criteria and also showed the efficacy of LDCT for early detection of lung cancer. "Thus, there should be consideration in making the lung cancer screening guidelines more inclusive," said Schabath.
"Additionally, adjunct risk-stratification tools, such as blood-based biomarkers, could be an important complement to determine who should be part of a lung cancer screening program," he said. "This could be particularly salient for people who have no or very few risk factors, such as never smokers."
Pinpointing Poor Outcomes
In the current study, Schabath and colleagues used publicly available data and LDCT images from the NLST to generate radiomic features from screen detected, incidentally-diagnosed lung cancers. Radiomic features describing size, shape, volume, and textural characteristics were then calculated from both the intratumoral and peritumoral regions.
Patients were divided into training and test cohorts, and an external cohort of non-screen-detected lung cancer patients was used for further validation. There were no statistically significant differences between training and test cohorts for most demographics, including age, sex, smoking status, number of pack-years smoked, treatment, stage, and baseline screening result. However, self-reported chronic obstructive pulmonary disease (COPD) was significantly higher in the test cohort compared with the training group (16% vs. 7%, P = .02).
A total of 91 stable and reproducible radiomics features (peritumoral and intratumoral) were identified and 40 (26 peritumoral and 14 intratumoral) were significantly associated with overall survival in the training cohort. The features were subsequently narrowed to four, and backward elimination analyses identified a single model. Patients were then stratified into three risk-groups: low risk, intermediate risk, and high risk.
According to their model, the high-risk group had worse overall survival (hazard ratio [HR], 9.91; 25% 2.5-year and 0% 5-year OS) as compared with the low-risk group (HR, 1.00; 93% 2.5-year and 78% 5-year OS).
The final model was validated in the test group and then replicated in the non-screen-detected patients with adenocarcinoma patients. Since the disease stage differed significantly across the risk groups, the model was stratified by stage and the authors found "compelling" results among early-stage patients, who generally have good outcomes. In this subset, the high-risk group was associated with a worse overall survival (HR, 2.63; 56% 2.5-year and 42% 5-year OS) vs the low-risk group (HR, 1.00; 75% 2.5-year and 75% 5-year OS).
"We have ongoing studies to determine if these results are consistent in the real-world setting of lung cancer screening across multiple centers," said Schabath. "If the NELSON, LUSI, or MILD trial data become publicly available, we will certainly pursue validating our results in those clinical trials."
The study was funded by the National Cancer Institute. Schabath and Madabhushi have disclosed no relevant financial relationships.
Sci Rep. Published online June 29, 2020. Full text
Medscape Medical News © 2020
Cite this: Radiomics Can Identify High-Risk Early Stage Lung Cancer - Medscape - Jul 07, 2020.