Researchers develop AI to help detect hard-to-spot lobular breast cancer
NEWYou can now listen to Fox News articles!
Artificial intelligence is making its mark on the future of cancer treatment.
One of the newest applications of technology is locating hard-to-detect breast cancer.
Researchers at The Ohio State University Comprehensive Cancer Center – Arthur G. James Cancer Hospital and the Richard J. Solove Research Institute are using frontline artificial intelligence to predict which patients may develop lobular breast cancer.
WOMAN DEFEATED FATAL BRAIN CANCER WITH EXPERIMENTAL STEM CELL THERAPY: ‘IT’S REALLY AMAZING’
What is lobular breast cancer?
Breast cancer is the most common cancer in women and ranks second in cancer-related deaths in the country.
Data show that lobular breast cancer, which is aggressive and difficult to detect, represents 10% to 15% of breast cancer diagnoses in the United States.
This is what lobular breast cancer may look like on a mammogram. Dr. Arya Roy noticed blurriness in the imaging, which prompted her to recommend additional scans. (Ohio State University)
Lobular cancer grows as a long chain of cells rather than a clump of cells forming a tumor, so it appears as a “thin thickness” on mammograms. This means it can be difficult to detect until it spreads to other parts of the body, according to OSU.
This form of the disease carries a risk of recurrence even 10 years after the patient is cancer-free.
“We urgently need better tools that can predict which patients are truly at high risk.”
Additionally, according to the Breast Imaging Association, approximately 40% of women over the age of 40 have dense breast tissue, which can lead to greater detection difficulty and a higher risk of developing breast cancer.
Although invasive lobular cancer grows, spreads, and responds differently to treatment differently than the more common invasive ductal carcinoma, lead researcher Dr. According to Arya Roy, oncologists follow the same guidelines for both diseases.
CLICK TO REACH THE FOX NEWS APPLICATION
“The genomic tests we currently use often provide ambiguous or conflicting results for lobular cancer, making it difficult for oncologists to decide the best treatment,” he said in the press release. “We urgently need better lobular cancer-specific tools that can predict which patients are truly at high risk.”
Cancer-fighting technology
Roy reiterated how difficult it is to identify lobular breast cancer through imaging.
“It’s also very difficult to identify patients who are at higher risk of recurrence after treatments,” he told Fox News Digital. “This is where we use artificial intelligence techniques to identify patients who are at risk of this cancer coming back.”
Dr. seen examining breast scan. Arya Roy investigates a type of cancer that is often missed in regular screenings. It uses data from real cases of lobular breast cancer to train artificial intelligence to improve early detection. (Ohio State University)
By combining AI models with digital pathology images, doctors can detect biomarkers and other indicators in high-risk cancer patients. These findings, along with patients’ clinical data, were used to create a scoring system that predicts the likelihood of cancer recurrence over the next decade, the researchers said.
The AI tool is currently under development; There are clinical trials and a funded study on the horizon.
CLICK TO SIGN UP FOR OUR HEALTH NEWSLETTER
“We hope that once we fully develop this AI tool to help us identify patients at risk of relapse, we will be able to use it for all lobular breast cancer patients,” Roy said.
“If we know that a patient has a 10% increased chance that this cancer will recur within five years, we can keep that patient under close surveillance.”
The study’s investigator encourages women to discuss with their doctors whether additional imaging is appropriate for them. (iStock)
Roy added that oncologists can also use other imaging techniques to ensure no cancer recurrences are missed in these high-risk patients, noting that this new AI-supported method “could give hope to many patients.”
The oncologist encourages women to talk to their doctor about whether additional imaging is appropriate for them.
Potential limitations
Dr., an emergency room physician and artificial intelligence expert in Texas. Harvey Castro was not involved in OSU’s investigation but commented on the findings to Fox News Digital.
TEST YOURSELF WITH OUR LATEST LIFESTYLE QUIZ
“The Ohio State study marks significant progress in using AI to detect lobular breast cancer, an elusive subtype, but it also highlights barriers that prevent AI from fully matching real-world complexity,” he said.
The doctor stated that one of the biggest problems is training artificial intelligence on old data. “Medicine is evolving rapidly, and algorithms built on yesterday’s images can miss today’s patterns, which I call temporal drift.”
“Before these tools go into routine maintenance, we need to make sure they are tested on a variety of real-world populations.”
Castro cautioned that many systems “perform beautifully” in the laboratory but may stumble when tested in new hospitals or patient populations.
“Dense breast tissue remains the Achilles heel of AI,” he said. “The same density that hides tumors from radiologists can confuse algorithms, especially across race and age groups.”
CLICK FOR MORE HEALTH NEWS
According to Castro, artificial intelligence will not replace radiologists; instead, it will redefine the way they work.
“But before these tools go into routine maintenance, we need to make sure they are tested in the real world, in diverse populations, not just with excellent laboratory data.”
