Researchers from the University of British Columbia have embarked on a promising initiative to enhance treatment for individuals with endometrial cancer, the most prevalent gynecologic cancer, using artificial intelligence. Their study was published in the journal Nature Communications.

Using artificial intelligence (AI) to analyze thousands of cancer cell images, the researchers identified a specific subset of endometrial cancer that significantly increases the risk of recurrence and mortality. This subset would typically go unnoticed by traditional pathology and molecular diagnostics.

The findings will enable physicians to identify patients with high-risk disease who may benefit from more extensive therapy.

“Endometrial cancer is a diverse disease, with some patients much more likely to see their cancer return than others, it is 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,” said Dr. Jessica McAlpine, Professor and Dr. Chew Wei Chair in Gynaecologic Oncology at UBC, and surgeon-scientist at BC Cancer and Vancouver General Hospital.

AI-Powered Precision Medicine

The discovery expands upon research conducted in 2013 by Dr. McAlpine and associates at the Gynecologic Cancer Initiative in British Columbia, a multi-institutional partnership between UBC, BC Cancer, Vancouver Coastal Health, and BC Women’s Hospital.

This collaboration helped demonstrate that endometrial cancer could be categorized into four subtypes according to the molecular features of cancerous cells, each of which presented a distinct risk to patients.

Subsequently, Dr. McAlpine and colleagues created ProMiSE, a novel molecular diagnostic instrument that is capable of precisely differentiating between the subtypes. The instrument is utilized to inform treatment decisions in British Columbia, other parts of Canada, and abroad.

However, difficulties still remain. The most common molecular subtype, accounting for around half of all cases, is essentially a catch-all for endometrial malignancies that do not have any distinguishable molecular characteristics.

There are patients in this very large category who have extremely good outcomes, and others whose cancer outcomes are highly unfavorable. But until now, we have lacked the tools to identify those at-risk so that we can offer them appropriate treatment.

Dr. Jessica McAlpine, Professor, University of British Columbia

In an attempt to further segregate the category using cutting-edge AI techniques, Dr. McAlpine turned to longtime partner and machine learning specialist Dr. Ali Bashashati, an Assistant Professor of Biomedical Engineering, Pathology, and Laboratory Medicine at UBC.

A deep learning artificial intelligence algorithm created by Dr. Bashashati and his colleagues examines photos of tissue samples taken from patients. After analyzing more than 2,300 images of cancer tissue, the AI, which had been trained to distinguish between several subtypes, identified a novel subgroup with noticeably 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, 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.

Dr. Ali Bashashati, Assistant Professor, University of British Columbia

Bringing the Discovery to Patients

With funding from the Terry Fox Research Institute, the team is currently investigating how the AI tool could be incorporated into clinical practice alongside conventional molecular and pathology tests.

“The two work hand-in-hand, with AI providing an additional layer on top of the testing we are already doing,” said Dr. McAlpine.

The AI-based strategy offers the advantages of cost-effectiveness and ease of deployment across geographical boundaries. Even at smaller hospital locations in rural and distant towns, the AI can analyze images that are regularly collected by pathologists and healthcare professionals and shared when seeking a second opinion on a diagnosis.

In addition to ensuring that patients who require treatment at a larger cancer center can receive it, the combined use of molecular and AI-based analysis may enable many patients to undergo less invasive surgery closer to home.

What is really compelling to us is the opportunity for greater equity and access. The AI does not care if you are 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.

Dr. Ali Bashashati, Assistant Professor, University of British Columbia

Journal Reference:

Darbandsari, A., et al. (2024) AI-based histopathology image analysis reveals a distinct subset of endometrial cancers. Nature Communications. doi.org/10.1038/s41467-024-49017-2.