Researchers presented a groundbreaking artificial intelligence (AI)-guided technique today at the Society of NeuroInterventional Surgery's (SNIS) 23rd Annual Meeting that may improve the accuracy of delivering experimental therapies directly to malignant brain tumors.

The approach uses AI to identify all the blood vessels feeding a tumor, allowing physicians to deliver therapy to more of the tumor while reducing off-target delivery. Intra-arterial therapy is a minimally invasive procedure, in which a catheter delivers medication directly through an artery. This allows for highly targeted dosing, minimizing side effects on the rest of the body. Traditionally, physicians have delivered these therapies through a single artery, but because many tumors receive blood from multiple vessels, a single-artery approach may result in incomplete tumor coverage.

In the study, "From Single-Pedicle to Whole Tumor Coverage: AI-guided Multi-territory Super-selective Endovascular Infusion for Brain Tumors," researchers at The University of Texas MD Anderson Cancer Center developed a new AI-assisted technique that identifies tumor-feeding arterial pedicles (arteries feeding blood to the tumor) before delivering treatment. After confirming the AI findings with advanced imaging, the physicians then delivered a specific amount of therapy, tailored to each artery, based on the amount of blood each vessel supplied.

Three patients with malignant brain tumors underwent treatment using this approach. The AI-assisted mapping successfully identified multiple tumor-feeding arteries in every patient, allowing physicians to treat all tumor-feeding pedicles. The multi-pedicle approach covered more than 85% of each tumor in all cases, compared to less than 65% coverage with single-pedicle proximal infusion. By creating a patient-specific map of the tumor's blood supply, the physicians delivered therapy more precisely to the areas that needed it, reducing delivery outside of the intended treatment area. Researchers also found the procedure could be safely repeated two weeks later.

"One of the biggest challenges in treating malignant brain tumors is that every patient's anatomy is different," said Christopher Young, MD, PhD, the study's primary author. "AI gives us another tool to personalize treatment based on each patient's unique blood supply, with the goal of delivering therapy more precisely. While more research is needed, this approach has the potential to improve patient care and marks an exciting advancement in neurointerventional oncology."

Additional studies will be needed to determine whether improved tumor coverage leads to better outcomes for patients.