A discovery by researchers at the University of British Columbia promises to improve care for patients suffering from endometrial cancerthe most common gynecological neoplasm.
Diagnosing endometrial cancer with artificial intelligence
Using artificial intelligence (AI) to spot patterns in thousands of images of cancer cells, researchers have identified a distinct subset of endometrial cancer that puts patients at a much higher risk of recurrence and death, but which otherwise would not would be recognized by traditional pathology and molecular diagnostics.
The results, published on Nature Communications will help doctors identify patients with high-risk diseases who may benefit from more comprehensive treatment.
“Endometrial cancer is a diverse disease, with some patients being much more likely to have their cancer recur than others,” said Dr. Jessica McAlpine, professor and Dr. Chew Wei Chair in Gynecologic Oncology at UBC and a surgeon-scientist at BC Cancer and Cancer. Vancouver General Hospital.
“It is so important that patients with high-risk disease are identified so we can intervene and hopefully prevent recurrence. This AI-driven approach will help ensure that no patient misses out on potentially life-saving interventions.”
The discovery builds on the work of Dr. McAlpine and colleagues at BC’s Gynecologic Cancer Initiative, a multi-institutional collaboration between UBC, BC Cancer, Vancouver Coastal Health and BC Women’s Hospital, which in 2013 helped demonstrate that Endometrium can be classified into four subtypes based on the molecular characteristics of the cancer cells, each presenting a different level of risk to patients.
Dr McAlpine and his team then developed an innovative molecular diagnostic tool, called ProMiSE, that can accurately distinguish between subtypes. The tool is now used throughout BC, in parts of Canada and internationally to guide treatment decisions.
However, challenges remain. The most prevalent molecular subtype, comprising approximately 50% of all cases, is largely a generic category for endometrial tumors with no discernible molecular features.
There are patients in this very broad category who have extremely good outcomes, and others whose cancer outcomes are highly poor. But until now, we didn’t have the tools to identify those at risk so we could offer them appropriate treatment,” said Dr. McAlpine.
Dr. McAlpine turned to long-time collaborator and machine learning expert Dr. Ali Bashashati, assistant professor of biomedical engineering, pathology and laboratory medicine at UBC, to try to further segment the category using advanced artificial intelligence methods .
Dr Bashashati and his team developed a deep learning AI model that analyzes images of tissue samples collected from patients. The AI was trained to distinguish between different subtypes and, after analyzing over 2,300 images of tumor tissue, identified the new subgroup that showed significantly lower survival rates.
“The power of AI is that it can objectively look at large sets of images and identify patterns that elude human pathologists,” said Dr. Bashashati. “It’s like finding the needle in the haystack. He tells us that this group of tumors with these characteristics are the worst offenders and pose a higher risk to patients.”
The team is now exploring how the AI tool could be integrated into clinical practice alongside traditional molecular and pathology diagnostics, thanks to funding from the Terry Fox Research Institute.
“The two work hand in hand, with AI providing an additional layer on top of the tests we’re already doing,” Dr McAlpine said.
One of the advantages of the AI-based approach is that it is cost-effective and easy to implement across geographies. AI analyzes images that are routinely collected by pathologists and healthcare workers, even in smaller hospitals in rural and remote communities, and shared when seeking a second opinion on a diagnosis.
The combined use of molecular and AI-based analysis could allow many patients to remain in their home communities for less intensive surgery, while ensuring that those requiring treatment at a larger cancer center can to do it.
“What we’re really interested in is the opportunity for greater equity and access,” Dr. Bashashati said. “The AI doesn’t care if you’re in a large urban center or a rural community, it would just be available, so our hope is that this could really transform the way we diagnose and treat endometrial cancer for patients of all the world.”
Estrogen receptor mutation study suggests potential treatments for endometrial cancers
Researchers at the Huntsman Cancer Institute have identified potential new treatment options for people with endometrial cancer. Endometrial cancer is the most common gynecological cancer and high levels of estrogen promote its development. The study, published in Molecular Cancer Research, found that estrogen receptor mutations found in endometrial cancers cause large changes in endometrial cancer cells.
Estrogen is a reproductive hormone that binds to and activates estrogen receptors. Cancer can cause estrogen receptors to remain in a constant state of activity. This increases the shedding of the endometrial lining.
“Our goal was to characterize estrogen receptor mutations in endometrial cancer to see how they affected gene expression, along with how these mutations made the cells more aggressive and rapidly growing,” says Zannel Blanchard, Ph.D. , postdoctoral researcher at the Huntsman Cancer Institute. and principal investigator of the study. “We found that the mutations caused large changes in gene expression and cell behavior.”
The team used the findings to identify potential treatments for endometrial cancers with high levels of estrogen receptor activity. They found that inhibitors of CDK9, a protein that works with estrogen receptors, were effective in reducing the growth and aggressiveness of endometrial cancer cells.
“Other than surgery to treat endometrial cancer, there is only one drug approved by the Food and Drug Administration to treat primary endometrial cancer, and it was approved in the 1970s,” says Jay Gertz, Ph.D ., senior author and investigator at Huntsman Cancer Institute and associate professor of cancer sciences at the University of Utah. “Our findings help us really start moving toward personalized, or precision, medicine for endometrial cancer.”
The study was presented to a breast and gynecological cancer research advocacy group of patients. Participants volunteer their time and meet once a month at the Huntsman Cancer Institute.
“We can write letters of support to help with upcoming research funding and offer a patient perspective to researchers,” says Deb Jordan, an endometrial cancer patient at the Huntsman Cancer Institute and a participant in the advocacy group. “We also have the opportunity to learn about ongoing research at the Huntsman Cancer Institute. This reassures me and learns about everything that is being done for endometrial cancer.”
“It’s exciting because the study suggests there may be more options for patients with endometrial cancer,” Blanchard says. “There’s more to come when you look deeper and you can share those findings with patients who have been through treatment.”
Gertz says treatment options for endometrial cancer are limited and that patients play an important role in inspiring researchers to find new therapies. The study suggests that molecular assessment of tumors could lead to more personalized treatment options for endometrial cancer patients.
#Endometrial #cancer #highrisk #form #discovered