A research team is investigating a “fast, safe, and noninvasive imaging method” for endometrial cancer combined with machine learning for an “accurate detection and diagnosis of precancerous lesions and early cancers.”

The team “conducted an initial investigation using optical coherence tomography (OCT), which detects differences in how tissue reflects light and acquires high-resolution 3D images with a depth of up to 1 to 2 millimeters.” The team imaged the entire endometrial cavity to create an optical biopsy. The team acquired OCT images from 57 post-hysterectomy uteri in 2025. 34 of those contained high-risk precancerous lesions or early-stage cancers.

A model the researchers developed to sort results into normal / benign and pre-cancer / cancer groups achieved “an exploratory sensibility of 94% and specificity of 87%.” Currently, no reliable screening for endometrial cancer exists; this new system has potential to “achieve higher sensitivity than random biopsy sampling.”

The research team “plans to evaluate the catheter in live patients to demonstrate the translational potential of the artificial intelligence-assisted OCT technology.”