In 10 seconds, AI model detects cancerous brain tumor often missed during surgery

Researchers say the technology could one day be applied to other cancers 

11:00 AM

Author | Noah Fromson

surgeon close up operating in bright lighted room
A U-M Health neurosurgical team performing an operation. Credit: Chris Hedly, Michigan Medicine

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. 

The residual tumor may resemble healthy brain, which 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.  

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.” 

-Todd Hollon, M.D.

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.” 

Additional authors: Akhil Kondepudi, Xinhai Hou, Cheng Jiang, M.S., Akshay Rao, Edward S. Harake, Asadur Chowdury, M.S., Wajd Al-Holou, M.D., Lin Wang, M.S.  Pedro R. Lowenstein, M.D., Ph.D., Maria G. Castro, Ph.D.,  Sandra Camelo-Piragua, M.D., all of University of Michigan, Melike Pekmezci, M.D., Katie Scotford,  Mitchel Berger, M.D., all of University of California San Francisco, Lisa Irina Koerner, M.D., Thomas Roetzer-Pejrimovsky, M.D., Georg Widhalm, M.D., all of Medical University of Vienna, Misha Movahed-Ezazi, MD, of Rutgers New Jersey Medical School, Daniel A. Orringer, M.D., of New York University, Christian Freudiger, Ph.D., of 6Invenio Imaging.  

Funding/disclosures: This work was supported by the following National Institute of Health (NIH) funding sources: K12NS080223 (T.H.), R01CA226527 (D.A.O), F31NS135973 (C.J.), and T32GM007863 (A.K.). This work was supported by the Chan Zuckerberg Initiative (CZI) Advancing Imaging Through Collaborative Project grant, Mark Trauner Brain Research Fund, Zenkel Family Foundation (T.H.), Ian’s Friends Foundation (T.H.), UM Stanley and Judith Frankel Institute for Heart and Brain Health Innovative Multidisciplinary Research Pilot Award (T.H.), and U).  

Tech transfer(s)/Conflict(s) of interest: Hollon, Orringer, and Freudiger are shareholders of Invenio Imaging, Inc.  

Paper cited: “Foundation models for fast, label-free detection of glioma infiltration,” NatureDOI: 10.1038/s41586-024-08169-3

Sign up for Health Lab newsletters today. Get medical tips from top experts and learn about new scientific discoveries every week.

Sign up for the Health Lab PodcastAdd us wherever you listen to your favorite shows. 


More Articles About: Brain Tumors Neurological (Brain) Conditions Brain and Spine Neurosurgery & Neurological Procedures Tumors and Lumps Cancer: Help, Diagnosis & Treatment Emerging Technologies
Health Lab word mark overlaying blue cells
Health Lab

Explore a variety of health care news & stories by visiting the Health Lab home page for more articles.

Media Contact Public Relations

Department of Communication at Michigan Medicine

[email protected]

734-764-2220

In This Story
Todd C. Hollon Todd C Hollon, MD

Assistant Professor

portrait of Aditya Pandey Aditya S Pandey, MD

Professor

Related
cancer cell
Health Lab
Artificial intelligence predicts genetics of cancerous brain tumors in under 90 seconds
A new study finds AI-based diagnostic screening system, DeepGlioma, detects genetic mutations in brain tumors in under 90 seconds. Streamlining glioma diagnosis and treatment.
Health Lab
Artificial Intelligence Improves Brain Tumor Diagnosis
Neuropathologists are creating a partnership with AI by teaching it how to help diagnose brain tumors with more speed, accuracy and efficiency.
Stay Informed

Want top health & research news weekly? Sign up for Health Lab’s newsletters today!

Subscribe
Featured News & Stories Microscope
Health Lab
Nerve damage reduced in prediabetic mice with diet, exercise
A low calorie diet and high intensity exercise can reduce nerve damage in prediabetic mice, according to a Michigan Medicine study.
three friends standing outside rogel cancer center building with big white ribbons
Health Lab
A lung cancer survivor shaping lung cancer advocacy
One woman's unexpected lung cancer diagnosis leads her to help many who aren't aware they're at risk of the disease.
On left, a young boy in a wheelchair has his doctor standing to his left and his parent is standing to his right in a show of support. On the right side of the image, the boy is now an adult and is wondering about the cost of his care and if his questions will be answered.
Health Lab
Changing the definition of cerebral palsy
Cerebral palsy is defined as a childhood disorder, which fails to recognize adults living with the condition and the lack of care they receive once they age out of pediatric clinics.
man and woman jogging outside with greenery behind them and fence on sidewalk
Health Lab
Exercise and physical activity help with cancer recovery and prevention
When it comes to living well and preventing cancer, scientists long ago established that exercise and physical activity are key. But some cancer survivors wonder which activities are best for maximizing health benefits. An assistant professor of applied exercise science at the University of Michigan School of Kinesiology talks more.
young woman standing on her own smiling outside
Health Lab
“Miracle Maddy” pursues high school diploma after complex brain surgery for extremely rare epilepsy
Six years after brain surgery for rare epilepsy Rasmussen’s encephalitis that caused rapid brain deterioration, high school senior is seizure free and planning to pursue nursing.
floating AI-type images in red and blues and yellow on blue background
Health Lab
Racial differences in medical testing could introduce bias to AI models
Black patients are less likely than white patients to receive certain medical tests that doctors use to diagnose severe disease, impacting artificial intelligence data. But researchers have found a way to correct the bias in these data sets.