Handheld AI Endomicroscope Enables Real-Time Precancer Detection at Point of Care

Many epithelial cancers are detected late because current diagnostics rely on invasive biopsies and in vivo microscopy with narrow field and shallow depth of field. These constraints can make it difficult to assess large or uneven lesions and to target biopsies effectively. Addressing this gap, a new study describes an artificial intelligence-enabled handheld microscope that provides real-time visualization of both subcellular changes and underlying microvasculature across broader tissue areas at the point of care.

Researchers at Rice University (Houston, TX, USA) and The University of Texas MD Anderson Cancer Center (Houston, TX, USA) have developed PrecisionView, a handheld endomicroscope that integrates advanced optics with artificial intelligence (AI). Designed for point-of-care assessment of epithelial tissue, the device enables wide-area, real-time review without an immediate biopsy. The platform is intended to reveal cellular architecture alongside subepithelial vascular patterns.

PrecisionView combines a deep learning–optimized optical design with real-time computational reconstruction. A custom phase mask and AI reconstruction algorithm expand the field of view and depth of field while maintaining cellular-level resolution. The system captures subcellular features and underlying microvasculature in a single continuous image.

The team validated the device in early studies that imaged healthy volunteers and human tissue samples with precancerous lesions. In one study, scans of the oral cavity generated high‑resolution maps of tissue structure and blood vessels over areas larger than one square centimeter. In another, the device identified precancerous changes in cervical tissue and displayed results in real time at up to 15 frames per second.

Across these experiments, PrecisionView delivered a field of view roughly five times larger and a depth of field about eight times greater than conventional in vivo microscopy. These gains address common constraints of small fields of view, shallow focusing, and uneven tissue surfaces. The device also produced detailed maps spanning several square centimeters while preserving cellular detail.

The research was published online in the Proceedings of the National Academy of Sciences on May 11, 2026. The handheld instrument was built using relatively simple components and has an estimated cost of about $3,000. The investigators noted that larger clinical studies are still needed to fully validate diagnostic accuracy and to define clinical workflows.

“Early detection is one of the most critical factors in improving cancer outcomes, but today’s tools often force clinicians to choose between detail and coverage. With PrecisionView, we no longer have to make that trade-off—we can see both clearly and in real time,” said Rebecca Richards-Kortum, the Malcolm Gillis University Professor at Rice and co-director of the Rice360 Institute for Global Health Technologies.

“PrecisionView has the potential to bring high-quality diagnostic capability directly to the point of care—helping clinicians make more timely decisions which will improve access to life-saving early detection. The impact will be particularly significant in medically underserved areas where access to pathology services may be limited or delayed, leading to missed or late diagnoses,” said Kathleen Schmeler, one of the authors of the study and associate vice president of global oncology in the Department of Cancer Network, Division of Surgery at MD Anderson.

Related Links
MD AndersonMD Anderson
Rice University
Rice360 Institute for Global Health Technologies