DEEP UV-M
Sponsor study identifier
interventional
270
1 country
1
Study Start
December 1, 2026
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
Primary Completion
December 2028
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
Study Completion
December 2028
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
This research study evaluates an experimental, point-of-care tool that combines Deep Ultraviolet (DUV) light imaging with Artificial Intelligence (AI) to rapidly screen for oral cancer and pre-cancer (dysplasia). The main goal is to determine if this automated tool can accurately deliver immediate, same-visit triage results (categorizing cells as either non-dysplasia or dysplasia/cancer) without needing chemical stains, sample transport, or off-site laboratory processing. The following occurs during a singular clinic visit for participants:
Registry-reported information. Elapsed time and enrollment totals alone do not measure study progress or recruitment pace.
December 2028
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
Click on a node to explore related trials.
Some registry-reported names shown below are not yet linked in this graph.
Dates and qualifiers reported by the registry. Estimated dates do not confirm that a milestone has occurred.
September 16, 2026
Actual (reported)September 25, 2026
Actual (reported)December 1, 2026
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
December 2028
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
December 2028
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
Triage Classification
The primary endpoint is the accurate binary triage classification (distinguishing non-dysplasia from dysplasia/cancer) performed by the AI DUV-M platform, compared against the reference standard of histopathology.
From the time of oral brush cytology sampling on Day 1 through completion of the reference biopsy histopathology report, assessed up to 14 days post-procedure.
Three-Class Diagnostic Discrimination
From sample collection on Day 1 through completion of 3-class histopathological grading, assessed up to 14 days post-procedure.
Participants with suspicious oral lesions undergo a quick, non-invasive oral brush test analyzed in real time by the experimental Deep UV AI platform. Immediately after, participants receive the routine 5 mm tissue biopsy to confirm their diagnosis. The AI scan result is compared directly against the biopsy pathology to measure the AI's diagnostic accuracy.
Non-invasive oral brush cytology harvests full-thickness epithelial cells from suspicious lesions. Cells are smeared onto UV glass slides and fixed in 95% ethanol. Unstained slides are scanned on a point-of-care Deep UV Microscope (DUV-M). An adapted AI model performs per-cell instance segmentation, extracts nuclear morphometric features, and delivers a binary triage result (non-dysplasia vs. dysplasia/cancer).
Registry-reported names are shown in full. Names without a link have not yet been matched to a Syfrah profile.
University of Pennsylvania, Department of Oral & Maxillofacial Surgery/Pharmacology
Philadelphia, Pennsylvania, 19104, United States
Anh D Le, DDS, PhD
University of Pennsylvania
First Submitted
September 16, 2026
First Posted
September 25, 2026
Study Start
December 1, 2026
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
Primary Completion
December 2028
Contact the study team to confirm eligibility.
Planned date reported by the registry; this milestone is not confirmed as achieved.
Study Completion
December 2028
EstimatedPlanned date reported by the registry; this milestone is not confirmed as achieved.
Last Updated
September 25, 2026
Record last verified: 2026-09
Download the complete ClinicalTrials.gov record imported by Syfrah, including fields not shown in this page. The registry may contain a newer revision.
Source: ClinicalTrials.gov.
JSON downloads include source attribution and retrieval details alongside the unchanged original record or the separately normalized values.
Source retrieved: