Using PET/CT images to assess the level of a non-small cell lung cancer biomarker can help patients avoid invasive biopsy.
PET/CT images can non-invasively measure levels of a non-small cell lung cancer (NSCLC) biomarker, eliminating the need for biopsy and predicting the patient’s response to therapy.
Checkpoint inhibitors that target the PD1/PD-L1 signaling pathway are an effective treatment for NSCLC, but it only works in roughly half of patients. Investigators from Moffitt Cancer Center demonstrated, in a study published this week in the Journal for ImmunoTherapy of Cancer, that PET/CT can effectively assess the patient’s PD-L1 level, helping patients and providers to side-step the risks that come with invasive biopsy.
“This study is important, as it is the single largest multi-institutional radiomic study population of NSCLC patients to date treated with immunotherapy to predict PD-L1 status and subsequent treatment response using PET/CT scans,” said Robert Gillies, Ph.D., chair of Moffitt’s cancer physiology department. “Because images are routinely obtained and are not subject to sampling bias per se, we propose that the individualized risk assessment information provided by these analyses may be useful as a future clinical decision support tool pending larger prospective trials.”
For their study, the team examined PET/CT scans for nearly 700 patients who had NSCLC who were treated in three institutions. They assessed shape, size, pixel intensity, and textures to train a deep learning tool to accurately measure PD-L1 expression. Using the data, they developed a deep learning score that could predict PD-L1 expression which, after validation, could predict checkpoint inhibitor outcomes in these patients.
Their results point to the usefulness of using images as a replacement for biopsy, said Matthew Schabath, Ph.D., associate member of the cancer epidemiology department.
“These data demonstrate the feasibility of using an alternative non-invasive approach to predict expression of PD-L1,” he said. “This approach could help physicians determine optimum treatment strategies for their patients, especially when tissue samples are not available or when common testing approaches for PD-L1 fail.”
For more coverage based on industry expert insights and research, subscribe to the Diagnostic Imaging e-Newsletter here.
FDA Approves Fluorescence Imaging System for Detecting Residual Breast Cancer
April 18th 2024The combination of the optical imaging agent Lumisight and the fluorescence imaging device Lumicell Direct Visualization System, collectively known as LumiSystem, reportedly offers 84 percent accuracy with real-time detection of residual breast cancer after lumpectomy procedures.
AI Adjudication Bolsters Chest CT Assessment of Lung Adenocarcinoma
April 11th 2024The inclusion of simulated adjudication for resolving discordant nodule classifications in a deep learning model for assessing lung adenocarcinoma on chest CT resulted in a 12 percent increase in sensitivity rate.
Five-Year Study Shows Significant Overuse of CT Angiography in the ER
April 2nd 2024Researchers noted a 67.4 percent increase in head and neck CT angiography and a 38 percent reduction in findings of acute pathology in a recent comparison of 2017 and 2021 statistics for headache and/or dizziness presentations at the emergency department of an urban academic medical center.
Interventional Radiology Study Shows Low Breast Cancer Recurrence 16 Months After Cryoablation
March 29th 2024In a cohort of patients with invasive breast cancer and tumor sizes ranging between 0.3 to 9 cm, image-guided cryoablation was associated with a 10 percent recurrence rate at 16 months, according to research recently presented at the Society of Interventional Radiology (SIR) conference.