Noninvasive Imaging Test Shows Promise for Detecting Endometrial Cancer
The new AI-powered technique could offer a faster, more accurate alternative to invasive biopsies by imaging the entire uterine cavity in seconds.
Researchers at Washington University in St. Louis and Siteman Cancer Center have announced preliminary results for a noninvasive imaging method designed to detect endometrial cancer. The findings, published June 3, 2026, in npj Imaging, utilized optical coherence tomography (OCT) combined with machine learning to analyze tissue from 57 post-hysterectomy uteri.
The Problem with Current Screening
Endometrial cancer is the most common gynecologic cancer in the United States, with over 69,000 cases diagnosed in 2025 and an annual increase of up to 3%. Currently, diagnosis requires an invasive biopsy, which carries an estimated false-negative rate of about 10%, translating to a sensitivity of roughly 90%.
The New Approach
The team, led by Quing Zhu, developed a custom catheter probe that can image the entire endometrial cavity in less than 3 seconds.
- How OCT works: It detects differences in light reflection to create high-resolution 3D images up to 1-2 mm deep.
- The Study: Images were acquired from 57 hysterectomy specimens. Of those, 34 contained high-risk precancerous lesions or early-stage cancers.
- Machine Learning: A model using 26 extracted features categorized tissues as normal/benign versus pre-cancer/cancer with 94% sensitivity and 87% specificity.
What the Researchers Say
"With our three-dimensional OCT imaging system combined with machine learning, we can image the entire endometrial cavity in 2 to 3 seconds and may have a potential to achieve higher sensitivity than random biopsy sampling."
— Quing Zhu, Lead Researcher
"There is currently no reliable screening for endometrial cancer. This technology should allow us to better screen for this cancer and at a minimum catch it much earlier in its development."
— David Mutch, Coauthor
Next Steps
The team plans to evaluate the catheter in live patients to demonstrate the translational potential of the AI-assisted OCT technology.