A multidisciplinary research team at Washington University in St. Louis and Siteman Cancer Center announced on June 18 the development of a noninvasive imaging method combined with machine learning to accurately detect precancerous lesions and early endometrial cancers. Endometrial cancer is the most common gynecologic cancer, with more than 69,000 cases diagnosed in the United States in 2025 and increasing up to 3% annually.
The new approach uses optical coherence tomography (OCT), which captures high-resolution three-dimensional images by detecting differences in how tissue reflects light. With a custom catheter probe developed by Quing Zhu, Edwin H. Murty Professor of Engineering at Washington University, the team imaged the entire endometrial cavity in less than three seconds to create an 'optical biopsy.' According to the researchers, this is the first catheter-based, three-dimensional OCT imaging study that integrates optical functional, structural, and radiomic features for assessing endometrial tissue. The results were published in npj Imaging on June 3.
To gather patient data, Zhu's team collaborated with WashU Medicine physicians led by Lindsay Kuroki and Ian Hagemann. The group acquired OCT images from 57 post-hysterectomy uteri collected in 2025; of these samples, 34 contained high-risk precancerous lesions or early-stage cancers. The images revealed clear differences among normal endometrium, benign conditions, high-risk precancerous lesions, and various stages of endometrial cancer.
First authors Sanskar Thakur and Yixiao Lin developed an image feature extraction pipeline along with a machine learning model that categorized results into two groups: normal/benign versus pre-cancer/cancer using twenty-six extracted features. Their exploratory model achieved a sensitivity of ninety-four percent and specificity of eighty-seven percent.
"There is currently no reliable screening for endometrial cancer," said coauthor David Mutch, Ira C. and Judith Gall Professor at WashU Medicine and principal investigator of the National Cancer Institute-funded Route 66 Endometrial Cancer Specialized Program of Research Excellence grant. "This technology, developed by Dr. Zhu and her colleagues, should allow us to better screen for this cancer and at a minimum catch it much earlier in its development," Mutch added. "This is really novel, cutting-edge technology." Going forward, Zhu said the team plans to evaluate their catheter device in live patients.
