Researchers have discovered a new artificial intelligence (AI)-derived biomarker that uses routine imaging scans to help predict which patients with non–small cell lung cancer (NSCLC) will respond to immunotherapy, according to a novel study published by Alilou et al in Science Advances. The findings may offer guidance for patients and clinicians and may also curtail the financial burden associated with immunotherapy.
“The ability to predict response[s] to immunotherapy merely from a baseline [computer tomography] scan would be a game-changer, because if we find out which patients [may] and [may] not respond to therapy, we can offer different therapeutic modalities,” highlighted study coauthor Mohammadhadi Khorrami, PhD, a postdoctoral fellow in the Wallace H. Coulter Department of Biomedical Engineering at the Emory University School of Medicine and Georgia Institute of Technology College of Engineering at Emory University. “Moreover, with the staggering costs of immunotherapy—around [$200,000] a year per patient—the need to noninvasively determine this response before initiating therapy becomes crucial.”
The new biomarker—quantitative vessel tortuosity, or QVT—examines features of the blood vessels surrounding tumors—which can influence tumor behavior and therapeutic resistance. Compared to normal blood vessels, tumor-associated vasculature is chaotically arranged and twisted.
Study Methods and Findings
In the new retrospective study, Dr. Khorrami and his colleagues used AI tools to evaluate different aspects of QVT biomarkers in over 500 cases of patients with NSCLC before and after they were treated with immune checkpoint inhibitors. The researchers discovered that the tumor vasculature of patients who did not respond to immune checkpoint inhibitors was more twisted compared with those who did respond to the therapy. They hypothesized that blood vessel twistedness caused antitumor cells to accumulate at the tumor site but fail to efficiently infiltrate the tumor, diminishing the effectiveness of immunotherapy.
“Our imaging biomarker is validated in genomic, molecular, and cellular scales and could potentially serve as a tool for better identification of [patients with] NSCLC who are likely to benefit from immunotherapy,” emphasized study coauthor Mehdi Alilou, PhD, Research Assistant Professor in the Department of Biomedical Engineering at Case Western Reserve University and now a senior AI engineer at the Volkswagen Group of America Innovation and Engineering Center California.
These findings are important because immunotherapy is often the first line of treatment for patients with NSCLC; however, most patients don’t achieve durable results from immune checkpoint inhibitors.
“Immunotherapy only tends to benefit approximately 30% of patients. With the high expense of treatments and a 70% failure rate, we have to find better ways to predict and monitor responses to therapy,” stressed study co-author Anant Madabhushi, PhD, Professor in the Wallace H. Coulter Department of Biomedical Engineering at the Emory University School of Medicine and Georgia Institute of Technology College of Engineering, as well as a member of the Cancer Immunology research program at the Winship Cancer Institute at Emory University. “When making decisions on who to treat and how to treat them, clinicians really need interpretable features. QVT is a novel radiomics method that uses an interpretable and intuitive AI approach to evaluate whether the tumor is responding to therapy even before more obvious changes like tumor size become apparent.”
“Our approach to quantitatively measure abnormal growth of blood vessels can help develop a dynamic way to measure and monitor these changes prior to and in response to treatments,” explained study coauthor Vamsidhar Velcheti, MD, FACP, FCCP, Medical Director of the Thoracic Oncology program in the Department of Hematology and Oncology at New York University Langone’s Perlmutter Cancer Center, who concluded, “This could pave the way to a novel diagnostic approach for combination strategies with immunotherapy.”
In future prospective clinical trials, the researchers plan to seek validation of QVT biomarkers.
Disclosure: For full disclosures of the study authors, visit science.org.The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.