From the Journals

Radiomics can identify high-risk early stage lung cancer


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, Cleveland, 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.”

Dr. 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,” Dr. 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 (e.g., 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 Dr. 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.”

Next Article: