Researchers use an artificial intelligence tool to analyze tumor biopsies and measure immune cell changes during treatment.
Researchers from The University of Texas MD Anderson Cancer Center have demonstrated that an artificial intelligence (AI)-based analysis of tumor biopsies can predict responses to immunotherapy in patients with rare cancers, according to a study published in the Journal for ImmunoTherapy of Cancer.
The analysis, led by Aung Naing, MD, professor of investigational cancer therapeutics, builds on research identifying features in the tumor microenvironment that predict immunotherapy response. The AI tool measures how many immune cells are present within a tumor before treatment and tracks changes in immune cell infiltration during treatment.
“AI-based pathology has the potential to provide clinicians with useful information on both the tumor and its surrounding microenvironment, helping to guide personalized treatment decisions for patients receiving immunotherapy,” says Naing in a release.
Advantages for Clinical Laboratories
While manually counting individual immune and cancer cells on pathology slides is labor-intensive, the AI-based tool generates these measurements quickly. The approach utilizes standard pathology slides that are already routinely collected, allowing for longitudinal tracking across multiple biopsies from the same patient.
The study found that an increase in tumor immune infiltration combined with a decrease in tumor content served as a strong predictive metric. Patients with these favorable signals had a 64% lower risk of disease progression or death. These patients lived nearly four times longer on average, with a median survival of 42 months compared to 10 months for those without the markers.
Future Validation Required
Although the results are promising, the researchers note that validation in larger patient populations is required before the approach is ready for clinical use. The study was supported in part by the National Cancer Institute (NCI) and the National Center for Advancing Translational Sciences (NCATS).
“While this AI-powered approach needs validation, this is an exciting step forward because it shows that meaningful insights can be extracted from routine pathology samples across a diverse group of rare cancers,” says Naing in a release.
