Posted in | News | Medical Robotics

A New Approach to Brain Tumor Surgery

Download PDF Copy

Reviewed

Reviewed by Lexie CornerNov 14 2024

A study published in Nature by researchers from UC San Francisco and the University of Michigan found that an artificial intelligence (AI)-powered diagnostic tool can assist neurosurgeons in detecting unseen cancer that has spread to nearby areas.

Why it Matters:

Unseen cancer cells can lead to the recurrence of brain tumors.
The new AI-powered methodology misses high-risk residual tumors only 3.8 % of the time, compared to 24 % with current methods.
These AI tools could be used for various types of cancer procedures

Survival rates decrease with recurrent brain tumors, and patients with the deadliest tumor types often pass away within a year. This is because malignant tissue left behind after the initial surgery can grow back much faster than the original tumor.

The study also suggests that similar AI techniques will be tested in surgeries for head and neck, prostate, lung, and breast cancers.

This technique will improve our ability to identify tumors and hopefully improve survival due to the added tumor being removed. This model provides physicians with real-time, accurate, and clinically actionable diagnostic information within seconds of tissue biopsy.

Shawn Hervey-Jumper, MD, Study Senior Author and Professor, Weill Institute for Neurosciences, University of California - San Francisco

The technology, called FastGlioma, is patented by UCSF and is open source, though it has not yet received FDA approval.

Neurosurgeons analyzed tumor samples from 220 individuals with diffuse gliomas, the most common type of adult brain tumor, both high-grade and low-grade. They found that, compared to 24 % of patients who did not use FastGlioma, only 3.8% of patients who used the tool still had high-risk tissue remaining.

FastGlioma has the potential to change the field of neurosurgery by immediately improving comprehensive management of patients with glioma. The technology works faster and more accurately than current standards of care methods for tumor detection and could be generalized to other pediatric and adult brain tumor diagnoses.

Todd Hollon, MD, Study Senior Author and Professor, Department of Neurosurgery, University of Michigan

FastGlioma works by combining stimulated Raman histology (SRH), an imaging technique that provides real-time imaging of fresh tissue samples at the bedside in one to two minutes, with the predictive capabilities of AI. This eliminates the need for pathology labs to spend time processing and interpreting tumor cells.

The AI system is trained using a dataset of 4 million microscopic views and over 11,000 tumor specimens. This allows it to accurately differentiate between tumor and healthy tissue. Neurosurgeons can make informed decisions quickly, as they receive diagnostic information within 10 seconds, enabling them to proceed with surgery if necessary.

Hervey-Jumper concluded, “If surgery to remove residual cells cannot be performed, other therapeutic options can be immediately considered. These include focal therapies like radiation or targeted chemotherapy in which treatment is delivered via catheter directly to the brain.”