In 10 Seconds, an AI Model Detects Cancerous Brain Tumor often Missed During Surgery

Researchers have developed an AI powered model that - in 10 seconds - can determine during surgery if any part of a cancerous brain tumor that could be removed remains, a study published in Nature suggests.

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 University of Michigan and University of California San Francisco.

"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, M.D., a neurosurgeon at University of Michigan Health and assistant professor of neurosurgery at U-M Medical School.

"The technology works faster and more accurately than 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 residual tumor.

Commonly, the tumor is missed during the operation because surgeons are not able to differentiate between healthy brain and residual tumor in the cavity where the mass was removed. Residual tumor’s ability to resemble healthy brain tissue remains a major challenge in surgery.

Neurosurgical teams employ different methods to locate that residual tumor during a procedure.

They may get MRI imaging, which requires intraoperative machinery that is not available everywhere. The surgeon might also use 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 just 3.8% of the time - compared to a nearly 25% miss rate for conventional methods.

"This model is an innovative departure from existing surgical techniques by rapidly identifying tumor infiltration at microscopic resolution using AI, greatly reducing the risk of missing residual tumor in the area where a glioma is resected," said co-senior author Shawn Hervey-Jumper, M.D., professor of neurosurgery at University of California San Francisco and a former neurosurgery resident at U-M Health.

"The development of FastGlioma can minimize the reliance on radiographic imaging, contrast enhancement or fluorescent labels to achieve maximal tumor removal."

How it Works

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.

After large scale training, foundation models can classify images, act as chatbots, reply to emails and generate images from text descriptions.

To build FastGlioma, investigators pre-trained the visual foundation model using over 11,000 surgical specimens and 4 million unique microscopic fields of view.

The tumor specimens are imaged through stimulated Raman histology, a method of rapid, high resolution optical imaging developed at U-M. The same technology was used to train DeepGlioma, an AI based diagnostic screening system that detects a brain tumor’s genetic mutations in under 90 seconds.

"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 U-M.

Full resolution images take around 100 seconds to acquire using stimulated Raman histology; a "fast mode" lower resolution image takes just 10 seconds. 

Researchers found that the full resolution model achieved accuracy up to 92%, with the fast mode slightly lower at approximately 90%.

"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's Future in Cancer

Over the last 20 years, the rates of residual tumor after neurosurgery have not improved.

Not only does residual tumor result in worse quality of life and earlier death for patients, but it increases the burden on a health system that anticipates 45 million annual surgical procedures needed worldwide by 2030.

Global cancer initiatives have recommended incorporating new technologies, including advanced methods of imaging and AI, into cancer surgery.

In 2015, The Lancet Oncology Commission on global cancer surgery noted that "the need for cost effective... approaches to address surgical margins in cancer surgery provides a potent drive for novel technologies."

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.

"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 said Aditya S. Pandey, M.D., chair of the Department of Neurosurgery at U-M Health.

"In future studies, we will focus on applying the FastGlioma workflow to other cancers, including lung, prostate, breast, and head and neck cancers."

Kondepudi A, Pekmezci M, Hou X, Scotford K, Jiang C, Rao A, Harake ES, Chowdury A, Al-Holou W, Wang L, Pandey A, Lowenstein PR, Castro MG, Koerner LI, Roetzer-Pejrimovsky T, Widhalm G, Camelo-Piragua S, Movahed-Ezazi M, Orringer DA, Lee H, Freudiger C, Berger M, Hervey-Jumper S, Hollon T.
Foundation models for fast, label-free detection of glioma infiltration.
Nature. 2024 Nov 13. doi: 10.1038/s41586-024-08169-3

Most Popular Now

Deep Learning Model Helps Detect Lung Tu…

A new deep learning model shows promise in detecting and segmenting lung tumors, according to a study published in Radiology, a journal of the Radiological Society of North America (RSNA)...

One of the Largest Global Surveys of Soc…

As leaders gather for the World Economic Forum Annual Meeting 2025 in Davos, Leaps by Bayer, the impact investing arm of Bayer, and Boston Consulting Group (BCG) announced the launch...

New Study Reveals AI's Transformati…

Intensive care units (ICUs) face mounting pressure to effectively manage resources while delivering optimal patient care. Groundbreaking research published in the INFORMS journal Information Systems Research highlights how a novel...

Sam Neville Joins the Highland Marketing…

Leading chief nursing information officer Sam Neville is joining the Highland Marketing advisory board. Sam brings a passion for nursing and safety to the board, which debates the big issues...

New Biomarkers to Detect Colorectal Canc…

Machine learning and artificial intelligence (AI) techniques and analysis of large datasets have helped University of Birmingham researchers to discover proteins that have strong predictive potential for colorectal cancer. In a...

AI Tool that may Assist Underserved Hosp…

As the fields of healthcare and technology increasingly evolve and intersect, researchers are collaborating on the best ways to use emerging technologies such as artificial intelligence (AI) to care for...

AI Model Identifies Potential Risk Genes…

Researchers from the Cleveland Clinic Genome Center have successfully applied advanced artificial intelligence (AI) genetics models to Parkinson's disease. Researchers identified genetic factors in progression and FDA-approved drugs that can...

AI-Supported Breast Cancer Screening - N…

The new findings are published in The Lancet Digital Health. The initial results of the Mammography Screening with Artificial Intelligence (MASAI) study* - a randomised trial to evaluate whether AI...

AI Improves Personalized Cancer Treatmen…

Personalized medicine aims to tailor treatments to individual patients. Until now, this has been done using a small number of parameters to predict the course of a disease. However, these...

The Future of Healthcare is Digital

8 - 10 April 2025, Berlin, Germany. The Berlin Exhibition Centre will be all about digital health from 8 to 10 April 2025. DMEA, Europe's leading event for digital healthcare, organised...

DMEA nova Award: Looking for the Best Id…

8 - 10 April 2025, Berlin, Germany. Innovative startups from the digital health sector can now apply for the DMEA nova Award 2025. We are looking for the best idea or...

AI Accelerates the Search for New Tuberc…

Tuberculosis is a serious global health threat that infected more than 10 million people in 2022. Spread through the air and into the lungs, the pathogen that causes "TB" can...