how ai is helping detect types of endometrial cancer

using ai, researchers are arming patients with more knowledge about the disease in order to be proactive with prevention and treatment options.

by raby nguer

published jul 09, 2024

3 minute read

join the conversation

3 minute read

join the conversation

the introduction of ai into the process of identifying types of endometrial cancer has accelerated the capabilities significantly and gives researchers more opportunities to improve patient outcomes. getty images

as the world of artificial intelligence grows, its technological abilities are expanding and entering spaces such as medicine. in the latest groundbreaking study, a team of researchers at the university of british columbia is using ai to find distinct patterns in cancer cell images of endometrial cancer. the identified patterns help researchers see if there is a greater risk of death in a patient with endometrial cancer and if they are susceptible to recurrence of the disease.

what is endometrial cancer?

endometrial cancer is a disease in which cancer cells form in the tissues of the inner lining of a uterus, called the endometrium.

jessica mcalpine, md, a professor at ubc, surgeon-scientist at bc cancer and vancouver general hospital, and member of the research team conducting the study, knows all too well the high rate of recurrence for many endometrial cancer patients and how ai is an important factor in helping people manage the disease.

“endometrial cancer is a diverse disease, with some patients much more likely to see their cancer return than others,” dr. mcalpine said, as quoted by inside precision medicine. “this ai-based approach will help ensure no patient misses an opportunity for lifesaving interventions.”

endometrial cancer has a high survival rate when caught early, but the rate of recurrence is 13%. using ai, researchers are arming patients with more knowledge about the disease in order to be proactive with prevention and treatment options.

the science behind endometrial cancer

endometrial cancer has four molecular subtypes, all of which present different outcomes for the patient and require unique approaches to treatment.

the most common out of the four subtypes is no specific molecular profile (nsmp), which is a designation applied once the other three subtypes are ruled out. nsmp makes up about half of all endometrial cancer cases.

dr. mcalpine and her team previously developed an endometrial cancer molecular test called “promise”, that can more precisely identify the subtype within a patient. however, the introduction of ai into the process has accelerated the capabilities significantly and gives dr. mcalpine and her team more opportunities to improve patient outcomes.

“there are patients in this very large category who have extremely good outcomes, and others whose cancer outcomes are highly unfavourable,” dr. mcalpine said. “but until now, we have lacked the tools to identify those at-risk so that we can offer them appropriate treatment.”

using ai in modern cancer medicine

dr. mcalpine consulted ali bashashti, phd, professor of biomedical engineering, pathology and laboratory medicine at ubc, and machine-learning expert, to get a better understanding of ai in the analysis of endometrial cancers.

bashashti and his team developed a machine learning model to evaluate and understand sample images from patients with cervical cancer. with a database of 2,300 images, the model was trained to identify differences in patients with endometrial cancer. this led to the discovery of a new subgroup of endometrial cancer that showed much worse survival rates.

“the power of ai is that it can objectively look at large sets of images and identify patterns that elude human pathologists,” bashsashti said, as quoted by inside precision medicine. “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.”

the future of ai and cancer

the next step for the team out of ubc is getting this tool into clinics for wider usage, as well as finding ways to use it alongside existing testing methods.

“what is really compelling to us is the opportunity for greater equity and access,” bashashati said. “the ai doesn’t care if you’re in a large urban centre 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.”

the canadian medical association journal reported that in 2017, endometrial cancer had an incidence rate of 35.7 per 100,000 and a mortality rate of 5.3 per 100,000, with both rates increasing.

raby nguer

how ai is helping detect types of endometrial cancer