Scientists at the University of British Columbia have used artificial intelligence to identify a high-risk subtype of endometrial cancer, paving the way for better patient outcomes and more targeted treatments.
Groundbreaking research from the University of British Columbia (UBC) could revolutionize care for patients with endometrial cancer, the most common type of gynecologic malignancy. Leveraging the capabilities of artificial intelligence, scientists have uncovered a high-risk subset of this cancer that conventional pathology often misses.
AI Unmasks Hidden Risks
This study, published in Nature Communications, revealed that AI could detect patterns in thousands of cancer cell images, identifying a higher-risk subset of endometrial cancer that would otherwise go undetected by traditional methods.
“Endometrial cancer is a diverse disease, with some patients much more likely to see their cancer return than others,” Jessica McAlpine, a UBC professor and surgeon-scientist at BC Cancer and Vancouver General Hospital, said in a news release. “It’s so important that patients with high-risk disease are identified so we can intervene and hopefully prevent recurrence. This AI-based approach will help ensure no patient misses an opportunity for potentially lifesaving interventions.”
Precision Medicine Through AI
McAlpine’s team has a history of groundbreaking work in this area. Back in 2013, their work helped classify endometrial cancer into four distinct subtypes based on molecular characteristics. This led to the development of ProMiSE, a molecular diagnostic tool that has been widely adopted to improve cancer treatment decisions. Despite these advancements, the largest category, representing roughly 50% of endometrial cancers, remained a catch-all group where patient outcomes varied significantly.
To bridge this gap, McAlpine collaborated with machine learning expert Ali Bashashati, an assistant professor of biomedical engineering at UBC. Bashashati’s team developed a deep learning AI model that analyzed over 2,300 tissue sample images, successfully identifying a subgroup with significantly poorer survival rates.
“The power of AI is that it can objectively look at large sets of images and identify patterns that elude human pathologists,” Bashashati said in the news release. “It’s finding the needle in the haystack. It tells us this group of cancers with these characteristics are the worst offenders and represent a higher risk for patients.”
Expanding Access and Equity in Cancer Diagnosis
The researchers now plan to integrate the AI tool into clinical practice, complementing existing diagnostics. Supported by a grant from the Terry Fox Research Institute, their goal is to make this advanced tool accessible across various settings, from major urban centers to rural communities.
“The two work hand-in-hand, with AI providing an additional layer on top of the testing we’re already doing,” said McAlpine. The AI-driven approach stands out for its cost-efficiency and potential to be deployed even in less resourced facilities, thus improving equity in cancer care across geographic locations.
“What is really compelling to us is the opportunity for greater equity and access,” added Dr. Bashashati. “The AI doesn’t care if you’re in a large urban center or rural community, it would just be available, so our hope is that this could really transform how we diagnose and treat endometrial cancer for patients everywhere.”
Significance of the Breakthrough
Endometrial cancer is known for its biological diversity, making it challenging to treat effectively. This AI-based discovery not only refines the classification of endometrial cancers but also has the potential to significantly improve patient outcomes through more targeted and personalized treatment plans.
Overall, this breakthrough marks a significant step forward in the use of artificial intelligence in health care, promising to enhance the precision and accessibility of cancer diagnostics worldwide.