Two New Radiomics Features Predict Lung Cancer Survival in LDCT Screening

The following article features coverage from the IASLC North America Conference on Lung Cancer 2019 meeting. Click here to read more of Cancer Therapy Advisor‘s conference coverage.

Screening patients with lung cancer using low-dose computed tomography (LDCT) has been associated with reducing lung cancer mortality as much as 20%, but the technique remains limited. One such limitation is that LDCT can overdiagnose indolent cancers that may not pose any threat to the patient if left untreated. Now, researchers have found 2 new radiomics features that occur in and around lung cancer tumors and can be used to identify patients that are at risk for poor survival outcomes. Researchers reported their findings at the International Association for the Study of Lung Cancer (IASLC) 2019 North America Conference on Lung Cancer (NACLC 2019) in Chicago, Illinois.¹

Jaileene Perez Morales, MD, of the Moffitt Cancer Center in Tampa, Florida, and colleagues included patients with early-stage lung cancer from the National Lung Screening Trial (NLST) and extracted peritumoral and intratumoral radiomic features from LDCT images. The researchers identified two radiomics features. Statistical root mean square, one of the features, was correlated with occurrence of the genes LOC285403 and FOXF2, the latter of which has been associated with poor outcomes in non-small cell lung cancer. The second identified feature was Neighborhood Grey Tone Difference Matrix (NGTDM) Busyness. Based on these features, the researchers divided patients into low-, moderate-, and high-risk groups. Patients identified as high-risk had 0% 5-year overall survival (hazard ration, 9.91), while patients who were identified as low-risk had 78% 5-year OS (hazard ratio, 1.00).

“Peritumoral and intratumoral radiomics identified a subset of screen-detected lung cancers associated with very poor survival outcomes,” the authors wrote. “These patients may require aggressive follow-up and/or adjuvant therapy to mitigate their poor outcomes.”

Read more of Cancer Therapy Advisor‘s coverage of the IASLC NACLC 2019 meeting by visiting the conference page.

Reference

1. Perez Morales J, Tunali I, Stringfield O, et al. Peritumoral and intratumoral radiomic features identifiy aggressive screen-detected early-stage lung cancers Presented at: International Association for the Study of Lung Cancer (IASLC) 2019 North America Conference on Lung Cancer (NACLC 2019); October 10-12, 2019: Chicago, Illinois. Abstract OA02.08