Researchers have developed an AI-powered model that can determine in 10 seconds during surgery if any part of a cancerous brain tumor that could be removed remains.
The technology, called FastGlioma, outperformed conventional methods for identifying what remains of a tumor by a wide margin, according to the research team led by the universities of Michigan and California and the paper they published.
“FastGlioma is an artificial intelligence-based diagnostic system that has the potential to change the field of neurosurgery by immediately improving comprehensive management of patients with diffuse gliomas,” said senior author Todd Hollon, a neurosurgeon at University of Michigan Health.
“The technology works faster and more accurately than the current standard of care methods for tumor detection and could be generalized to other pediatric and adult brain tumor diagnoses. It could serve as a foundational model for guiding brain tumor surgery.”
When a neurosurgeon removes a life-threatening tumor from a patient’s brain, they are rarely able to remove the entire mass. What remains is known as a residual tumor.
Commonly, the tumor is missed during the operation because surgeons are not able to differentiate between healthy brain and residual tumor tissues in the cavity where the mass was removed.
Neurosurgical teams employ different methods to locate that residual tumor during a procedure, which may include MRI imaging, which may not be available in the hospital, or a fluorescent imaging agent to identify tumor tissue, which is not applicable for all tumor types.
These limitations prevent their widespread use.
In this international study of the AI-driven technology, neurosurgical teams analyzed fresh, unprocessed specimens sampled from 220 patients who had operations for low or high-grade diffuse glioma.
FastGlioma detected and calculated how much tumor remained with an average accuracy of approximately 92%.
In a comparison of surgeries guided by FastGlioma predictions or image and fluorescent-guided methods, the AI technology missed high-risk, residual tumor tissues just 3.8% of the time—compared to a whopping 25% miss rate for conventional methods.
To assess what remains of a brain tumor, FastGlioma combines microscopic optical imaging with a type of artificial intelligence called foundation models. These are AI models, such as GPT-4 and DALL·E 3, trained on massive, diverse datasets that can be adapted to a wide range of tasks.
To build FastGlioma, investigators pre-trained the visual foundation model using over 11,000 surgical specimens and 4 million unique microscopic fields of view.
AI MAKING A DIFFERENCE FOR GOOD: AI Safety System Stops Train After Detecting Elephants Crossing the Tracks Ahead
“FastGlioma can detect residual tumor tissue without relying on time-consuming histology procedures and large, labeled datasets in medical AI, which are scarce,” said Honglak Lee, Ph.D., co-author and professor of computer science and engineering at the University of Michigan
Full-resolution images take around 100 seconds to acquire, while a “fast mode,” lower-resolution image takes just 10 seconds. Even so, researchers found that the fast mode achieved an accuracy of 90%, just 2% lower than the full resolution.
“This means that we can detect tumor infiltration in seconds with extremely high accuracy, which could inform surgeons if more resection is needed during an operation,” Hollon said.
AI IN RADIOLOGY: After Studying Mammograms, AI Can Detect More Breast Cancers Than Humans–With Fewer False Positives
Over the last 20 years, the rates of residual tumor after neurosurgery have not improved.
Residual tumor tissues can lead to worse quality of life and earlier death for patients, but it also increases the burden on a health system that anticipates 45 million annual surgical procedures needed worldwide by 2030.
Not only is FastGlioma an accessible and affordable tool for neurosurgical teams operating on gliomas, but researchers say, it can also accurately detect residual tumor for several non-glioma tumor diagnoses, including pediatric brain tumors, such as medulloblastoma and ependymoma, and meningiomas.
AI IN CANCER TREATMENT: Artificial Intelligence ‘Can Help Spot Early Signs of Cancer in Chest X-Rays’
“These results demonstrate the advantage of visual foundation models such as FastGlioma for medical AI applications and the potential to generalize to other human cancers without requiring extensive model retraining or fine-tuning,” said co-author Aditya S. Pandey, chair of the Department of Neurosurgery at UM Health.
“In future studies, we will focus on applying the FastGlioma workflow to other cancers, including lung, prostate, breast, and head and neck cancers.”
SHARE This Positive Use Of AI With Your Friends…