Lung neuroendocrine neoplasms: recent progress and persistent challenges

How Doctors Could Soon Use AI To Detect Brain Tumors

How doctors could soon use AI to detect brain tumors

Artificial intelligence models are getting better at detecting brain tumors in images from MRIs.

More than 150 types of brain tumors have been identified to date; and while not all of them are brain cancer, they can still be dangerous because of their locations. Benign brain tumors located in vital areas of the brain can be life-threatening. On rare occasions, a benign tumor can become malignant, according to John Hopkins Medicine.

Nearly 19,000 people were projected to die from brain and other nervous system cancers this year. About the same amount were estimated to die from brain and spinal cord tumors last year, according to the American Cancer Society.

Now, scientists have trained convolutional neural networks – also known as machine learning algorithms, a type of AI – to identify which MRI images showed healthy brains and which had been affected by cancer. In addition, the models could determine the area affected by cancer and what type of cancer it looked like.

While brain tumors aren't all cancerous, they can still be dangerous to those who have them. New research is using AI to better detect tumors in MRI images (Getty Images/iStock)

They found that the AI networks scored highly at detecting normal brain images and distinguishing the difference between cancerous and healthy brains. The first could detect brain cancer with an average accuracy rate of nearly 86 percent. The second had a rate of more than 83 percent.

Researchers used public domain MRI imaging data to train the models. Their findings were published Tuesday in a new paper in the journal Biology Methods and Protocols.

To improve the networks' abilities to detect tumors, the authors trained them in camouflage detection. They believed that there was a parallel between an animal that hides through natural camouflage – such as chameleons and walking stick insects – and a group of cancerous cells that blend in with healthy brain tissue.

They authors found that the network could generate images showing specific areas in its classification. This capability, they said, would allow doctors to cross-validate their own decisions with those from the AI.

In all cases, the networks still struggle to distinguish between types of brain cancer.

The best-performing proposed model was about 6 percent less accurate than standard human detection.

Now, scientists have trained convolutional neural networks – also known as machine learning algorithms, a type of AI – to identify which MRI images showed healthy brains and which had been affected by cancer (Getty Images)

Still, the researchers said their accuracy and clarity improved as they were trained in camouflage detection and their capacity to reuse a model trained on one task for a new but related project also led to an increase in accuracy.

The news comes after a study from the University of Michigan Health that found AI could predict the genetics of cancerous brain tumors in under 90 seconds.

"Advances in AI permit more accurate detection and recognition of patterns," the paper's lead author, Arash Yazdanbakhsh, said in a statement. "This consequently allows for better imaging-based diagnosis aid and screening, but also necessitate more explanation for how AI accomplishes the task."

"Aiming for AI explainability enhances communication between humans and AI in general. This is particularly important between medical professionals and AI designed for medical purposes. Clear and explainable models are better positioned to assist diagnosis, track disease progression, and monitor treatment," he said.

Brain Tumor News

Aug. 12, 2024 — Natural killer (NK) cells engineered to express interleukin-21 (IL-21) demonstrated sustained antitumor activity against glioblastoma stem cell-like cells (GSCs) both in vitro and in vivo, according ...

July 31, 2024 — Glioblastomas are highly aggressive, usually incurable brain tumors. If all therapeutic options are exhausted, patients have an average life expectancy of less than two years. Now researchers have ...

July 25, 2024 — Scientists have discovered that electrical currents may make Natural Killer (NK) cells -- our very own cancer-killing immune cells -- even better killers, which could have significant implications ...

July 23, 2024 — A team of researchers has discovered that the tumor suppressor protein Prostate apoptosis response-4 (Par-4) can cause a unique type of cell death called ferroptosis in human glioblastoma -- the most ...

July 17, 2024 — Burst sine wave electroporation was found to cause less damage to cells and tissue but more disruption to the blood-brain ...

July 9, 2024 — A team of researchers has identified and located a population of stem-like cells that initiates and maintains Group 3 medulloblastoma (Gr3-MB) in the developing brain. Gr3-MB is one of the most ...

July 8, 2024 — A new approach to treating the most malignant type of brain cancer -- glioblastoma -- has shown strong promise in pre-clinical settings, raising hopes of increasing current average survival rates ...

July 8, 2024 — Researchers have discovered a new potential drug target for the lethal wasting disease known as cancer cachexia. Their findings illustrate that even small groups of neurons in the brain can have an ...

July 3, 2024 — A new study shows that already a 30-minute exercise can increase the proportion of tumor-killing white blood cells in the bloodstream of breast cancer ...

June 19, 2024 — When low doses of cancer drugs are administered continuously near malignant brain tumors using so-called iontronic technology, cancer cell growth drastically decreases. Researchers demonstrated this ...

June 13, 2024 — Researchers are one step closer to understanding how pediatric DIPG tumors ...

June 7, 2024 — A study has identified a biological mechanism that could lead to more effective treatments for breast cancer that has metastasized to the ...

June 6, 2024 — In a major advance for the treatment of the deadly brain cancer glioblastoma, scientists used ultrasound technology to penetrate the blood-brain barrier and provide a small dose of a chemotherapy and ...

May 30, 2024 — Brain cancer is difficult to treat when it starts growing, and a prevalent type, known as a glioma, has a poor five-year survival rate. In a new study, researchers report on a new surgical platform ...

May 20, 2024 — For many patients with a deadly type of brain cancer called glioblastoma, chemotherapy resistance is a big problem. But now, researchers may have moved a step closer to a ...

May 3, 2024 — Scientists have discovered how glioblastoma evades the immune system by inducing pro-tumor macrophages via a glucose based epigenetic ...

May 1, 2024 — An mRNA cancer vaccine quickly reprogrammed the immune system to attack the most aggressive type of brain tumor in a first-ever human clinical ...

Apr. 22, 2024 — Scientists are developing and validating a patent-pending novel immunotherapy to be used against glioblastoma brain tumors. Glioblastomas are almost always lethal with a median survival time of 14 ...

Mar. 13, 2024 — Targeting two brain tumor-associated proteins -- rather than one -- with CAR T cell therapy shows promise as a strategy for reducing solid tumor growth in patients with recurrent glioblastoma (GBM), ...

Mar. 8, 2024 — Scientists have developed a new approach using the Zika virus to destroy brain cancer cells and inhibit tumor growth, while sparing healthy ...

In 10 Seconds, An AI Model Detects Cancerous Brain Tumors Often Missed During Surgery

A University of Michigan Health neurosurgical team performing an operation – credit Chris Hedly, Michigan Medicine.

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… 

---