AI Model FastGlioma Revolutionizes Brain Tumor Detection During Surgery

AI Technology Detects Cancerous Brain Tumours in 10 Seconds During Surgery

AI model shows promise for broader cancer treatment applications. A groundbreaking artificial intelligence tool called FastGlioma has been developed, enabling surgeons to detect residual cancerous brain tumours within 10 seconds during surgery. The innovation, detailed in a recent study in Nature, is seen as a significant advancement in neurosurgery, outperforming traditional tumour detection methods. Researchers from the University of Michigan and the University of California, San Francisco, led the study, highlighting its potential to improve surgical outcomes for patients with diffuse gliomas. Todd Hollon, M.D., a neurosurgeon at the University of Michigan Health, described FastGlioma as a transformative diagnostic tool that provides a faster and more accurate method for identifying tumour remnants. He noted its ability to reduce reliance on current methods, such as intraoperative MRI or fluorescent imaging agents, which are often inaccessible or unsuitable for all tumour types. As per the study from Michigan Medicine - University of Michigan, residual tumours, which often resemble healthy brain tissue, are a common challenge in neurosurgery. Surgeons have traditionally struggled to differentiate between healthy brain and remaining cancerous tissue, leading to incomplete tumour removal. FastGlioma addresses this by combining high-resolution optical imaging with artificial intelligence to identify tumour infiltration rapidly and accurately. In an international study, the model was tested on specimens from 220 patients with low- or high-grade diffuse gliomas. FastGlioma achieved an average accuracy of 92%, significantly outperforming conventional methods, which had a higher miss rate for high-risk tumour remnants. Co-senior author Shawn Hervey-Jumper, M.D., professor of neurosurgery at UCSF, emphasised its ability to enhance surgical precision while minimising the dependence on imaging agents or time-consuming procedures. FastGlioma is based on foundation models, a type of AI trained on vast datasets, allowing adaptation across various tasks. The model has shown potential for application in other cancers, including lung, prostate, and breast tumours, without requiring extensive retraining. Aditya S. Pandey, M.D., chair of neurosurgery at the University of Michigan, affirmed its role in improving surgical outcomes globally, aligning with recommendations to integrate AI into cancer surgery. Researchers aim to expand its use to additional tumour types, potentially reshaping cancer treatment approaches worldwide.

In 10 seconds, an AI model can detect 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 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."

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. 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. 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."

AI model identifies overlooked brain tumors in just 10 seconds

The team behind FastGlioma has open sourced the model and developed an online demo as well In another triumph for AI in healthcare, researchers have developed a model that can spot bits of brain tumors that surgeons may miss while removing them from patients. It can detect these remaining tissues in as little as 10 seconds, and help prevent a host of long- and short-term post-procedure complications. Developed by University of Michigan and University of California San Francisco researchers, the technology is called FastGlioma - incorporating the term 'glioma' that refers to a brain or spinal cord tumor. "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," said neurosurgeon Todd Hollon, a senior author of the paper detailing FastGlioma's effectiveness that appeared in Nature. "It could serve as a foundational model for guiding brain tumor surgery." With most tumor removal surgeries, it's difficult to tell healthy brain tissue and tumorous tissue apart - and as a result, a bit of residual tumor could remain in the cavity from where the mass was removed. That can lead to any of several complications, including seizures, infections, headaches, cognitive deterioration, and motor dysfunction. Now while these residual tumors can be located using MRI imaging or a fluorescent imaging agent, they're not always accessible during surgery, or applicable to all types of tumors. There have also been other attempts to tackle the problem of hard-to-spot residual tumors, like the laser-equipped SpectroPen from 2010, and gold nanoparticles for imaging during surgery back in 2012. However, it isn't clear if these were successfully commercialized. FastGlioma could find greater success, given that the AI-powered diagnostic system only requires access to the open source model and compute power. FastGlioma uses foundation models, a type of artificial intelligence system trained on large datasets for a variety of tasks. They can learn patterns to understand language and classify images, with OpenAI's GPT-4 being a recent example. In this case, FastGlioma was pre-trained using more than 11,000 surgical specimens and 4 million unique microscopic fields of view. The tumor specimens it looked at are imaged through a high-resolution imaging method called Stimulated Raman Histology. That enables the system to detect tumor infiltration in just 100 seconds using full resolution images with 92% accuracy. When using lower resolution images, FastGlioma achieved 90% accuracy in just 10 seconds. That enables surgeons to quickly determine if there's any residual tumor to be removed during a procedure. This tech represents the biggest advancement in improving the rate of identifying residual tumors in the last two decades. It could help drastically improve patients' quality of life post-surgery as it gains traction, and reduce the need for costly corrective procedures after the fact. It's also a prime example of AI helping to improve patient outcomes in neurosurgery. Last year, we wrote about CHARM, a tool to accurately decode a tumor's genetic makeup and determine next steps quickly enough to be used during procedures. FastGlioma could also be expanded to help other types of patients in the near future too. "In future studies, we will focus on applying the FastGlioma workflow to other cancers, including lung, prostate, breast, and head and neck cancers," said Aditya S. Pandey, who co-authored the paper on the tech.

AI Helps Spot Brain Tumor Tissue Surgeons Miss

WEDNESDAY, Nov. 13, 2024 (HealthDay News) -- A newly developed AI program can help doctors detect and potentially remove brain cancer that might otherwise be missed during surgery, a new study demonstrates. The AI, called FastGlioma, calculated how much residual brain cancer remained following surgery with approximately 92% accuracy, researchers reported Nov. 13 in the journal Nature. FastGlioma missed high-risk residual tumor just under 4% of the time, compared with a nearly 25% miss rate for human doctors relying on MRI scans or fluorescent dyes to detect brain tumors, results showed. Not only that, but the AI can return these results within 10 seconds, making it a potentially powerful aid to surgeons in the middle of removing a brain tumor, researchers said. "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 researcher Dr. Todd Hollon, a neurosurgeon at University of Michigan Health. "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," Hollon added in a university news release. "It could serve as a foundational model for guiding brain tumor surgery." Neurosurgeons are rarely able to remove the entire mass of a life-threatening brain tumor, leaving behind what doctors call residual tumor, researchers said in background notes. This leftover brain cancer is missed because it often resembles healthy brain tissue along the edges of the cavity left behind by the removal of a tumor, researchers said. Residual tumor increases the risk of a person's cancer recurring, robs them of years of life and frequently requires follow-up brain surgeries, researchers said. Doctors try to suss out residual tumor during surgery using MRI scans and fluorescent dyes that highlight tumor cells, but these technologies have limited usefulness, researchers said. To improve surgeons' ability to completely remove a brain tumor, researchers combined artificial intelligence with microscopic optical imaging to create FastGlioma. The team trained FastGlioma's AI using more than 11,000 surgical specimens and 4 million unique microscopic snapshots of healthy brain tissue and cancerous tumors. Researchers then analyzed fresh, unprocessed specimens samples from 220 patients who had operations for brain cancers. FastGlioma detected residual tumor with up to 92% accuracy within about 100 seconds using high-resolution images, and with 90% accuracy when using a "fast mode" that relies on slightly lower resolution images. "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 explained. AI also can be taught to distinguish other cancer types from healthy tissue, researchers added. "In future studies, we will focus on applying the FastGlioma workflow to other cancers, including lung, prostate, breast, and head and neck cancers," said researcher Dr. Aditya Pandey, chair of neurosurgery at University of Michigan Health.

AI technique helps neurosurgeons detect hidden cancer during brain tumor surgery

University of California - San FranciscoNov 13 2024 Technique offers new hope for increased survival in patients with brain tumors. What's new: An AI-based diagnostic system reveals cancerous tissue that may not otherwise be visible during brain tumor surgery. This enables neurosurgeons to remove it while the patient is still under anesthesia - or treat it afterwards with targeted therapies. Why it matters: Brain tumors can grow back from unseen cancer cells. The new technique misses high-risk remaining tumors just 3.8% of the time, versus 24% for conventional methods. These AI techniques could be used in surgeries for other cancers. When brain tumors recur, survival rates go down, and patients with the most lethal tumor type often die within a year. That's because cancerous tissue is left behind after the initial surgery, and it continues to grow, sometimes even faster than the original tumor. Now a new study, led by UC San Francisco and University of Michigan, has demonstrated that using an artificial intelligence (AI)-powered diagnostic tool helps neurosurgeons identify invisible cancer that has spread nearby. The technique has the potential to delay the recurrence of high-grade tumors and it could prevent it in lower-grade tumors. Similar AI techniques will be tested in surgeries for breast, lung, prostate, and head and neck cancers, according to the study, which appears in Nature on Nov. 13. "This technique will improve our ability to identify tumors and hopefully improve survival due to the added tumor being removed," said senior author Shawn Hervey-Jumper, MD, of the UCSF Department of Neurological Surgery and the Weill Institute for Neurosciences. "This model provides physicians with real-time, accurate and clinically actionable diagnostic information within seconds of tissue biopsy." The tool, which is open source and patented by UCSF, is known as FastGlioma, and has not yet been approved by the Food and Drug Administration. In the study, neurosurgeons examined tumor samples from 220 patients with high-grade and low-grade diffuse glioma, the most common type of adult brain tumor. They found that 3.8% of patients for whom FastGlioma had been applied had remaining high-risk tissue, compared with 24% of patients for whom the tool had not been applied. "FastGlioma has the potential to change the field of neurosurgery by immediately improving comprehensive management of patients with glioma," said senior author Todd Hollon, MD, of the Department of Neurosurgery at University of Michigan. "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." FastGlioma works by combining the predictive power of AI with stimulated Raman histology (SRH), an imaging technology that visualizes fresh tissue samples at the bedside within one-to-two minutes. This eliminates time-consuming processing and interpretation of tumor cells in pathology labs. The AI system is "trained" on a dataset of more than 11,000 tumor specimens and 4 million microscopic views. This allows it to classify images and distinguish between tumor and healthy tissue with a high degree of accuracy. Neurosurgeons receive diagnostic information in 10 seconds, enabling them to continue with surgery if required. "If surgery to remove residual cells cannot be performed, other therapeutic options can be immediately considered," said Hervey-Jumper. "These include focal therapies like radiation or targeted chemotherapy in which treatment is delivered via catheter directly to the brain." University of California - San Francisco