The team is developing a non-invasive approach to predict lung cancer outcomes


CA lung seen in CXR. Credit: James Heilman, MD / Wikipedia

Tests that analyze biomarkers are used during cancer management to guide treatment and provide information about the patient’s prognosis. These tests are often performed on tissue biopsy samples that require invasive procedures and can cause significant side effects. In a new article published in Journal for Cancer Immunotherapy, Moffitt Cancer Center researchers show that PET / CT images can be used to measure PD-L1 biomarker levels in patients with non-small cell lung cancer (NSCLC) in a non-invasive way and turn, predict a patient’s response to therapy.

Checkpoint inhibitors, drugs used to reactivate the immune system directed to the PD1 / PD-L1 signaling pathway, are commonly used to treat patients with NSCLC. Although this type of therapy has greatly improved patient outcomes, it only works for about half of this patient population. To avoid dealing with those who may not respond, it is often limited to patients who are shown that surgical biopsy sampling expresses the PD-L1 biomarker. However, performing invasive surgery is associated with inherent risks and, from time to time, the biopsy sample is not suitable for performing diagnostic tests or the testing procedure itself may fail. Therefore, researchers are trying to develop alternative strategies to identify patients who should be treated with specific agents, such as checkpoint inhibitors.

Moffitt researchers wanted to leverage the capabilities of deep computer learning to develop a new framework for measuring PD-L1 biomarker levels in NSCLC patients in a non-invasive manner. They chose to use PET / CT scanning imaging features, such as shape, size, pixel intensity, and textures, to train computers to measure PD-L1 expression. They developed a score to predict PD-L1 expression, and after validation across different cohorts of patients were able to use their model to predict the results of checkpoint inhibitors in patients with NSCLC.

“These data demonstrate the feasibility of using a noninvasive alternative approach to predict PD-L1 expression,” said Matthew Schabath, Ph.D., associate member of the Department of Cancer Epidemiology. “This approach could help physicians determine optimal treatment strategies for their patients, especially when there are no tissue samples or when the usual test methods for PD-L1 fail.”

“This study is important because it is the largest multi-institutional radiological study population of patients with NSCLC to date treated with immunotherapy to predict PD-L1 status and post-treatment response by PET / CT.” said Robert Gillies, Ph.D. ., chair of Moffitt’s Department of Cancer Physiology. “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 analyzes may be useful as a future clinical decision support tool in waiting for larger prospective trials “.

Researchers are developing tools to better predict the course of lung cancer treatment

More information:
Wei Mu et al, Noninvasive measurement of PD-L1 status and prediction of immunotherapy response through deep learning of PET / CT imaging, Journal for Cancer Immunotherapy (2021). DOI: 10.1136 / jitc-2020-002118

Citation: The team develops a non-invasive approach to predict the results of retrieved lung cancer (2021, June 17) on June 18, 2021 at invasive-approach-outcomes-lung. html

This document is subject to copyright. Apart from any fair treatment for private study or research purposes, no part may be reproduced without written permission. Content is provided for informational purposes only.

Source link


Please enter your comment!
Please enter your name here