Oral Potentially Malignant LesionsDEEP UV-MNCT07842211
Feasibility and Validation of an Automated AI-Enabled Deep Ultraviolet (DUV) Cytology Platform for Point-of-Care Oral Cancer Triage
A study testing Deep UV-M and AI Cytology Triage in people with Oral Potentially Malignant Lesions and Oral Potentially Malignant Disorders, run by Anh Le at 1 site in United States.
Trial summary
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). Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Oral Potentially Malignant Lesions, Oral Potentially Malignant Disorders, Oral Cancer , Oral Squamous Cell Carcinoma, Oral Cavity Cancer
- What is being tested?
- Deep UV-M and AI Cytology Triage
- Type of treatment
- Pill or oral medicine, Medical device
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 270 participants
- Where
- 1 siteUnited States
- Study dates
- 1 Dec 2026to Dec 2028
- Phase
- Interventional
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- Suspicious Lesions Cohort: Adults with suspicious oral potentially malignant lesions (OPML), such as leukoplakia, erythroplakia, or speckled lesions), oral precancer (dysplasia), or suspected oral/oropharyngeal squamous cell carcinoma (OSCC) who are scheduled for a diagnostic incisional or excisional tissue punch biopsy.
- Healthy Volunteers Cohort: Clinically normal volunteers without suspicious oral mucosal lesions.
Who cannot join
- Age: Individuals under 18 years of age.
- Currently undergoing treatment for malignancy
- Unwilling or unable to provide informed consent
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
United States1 site
University of Pennsylvania, Department of Oral & Maxillofacial Surgery/Pharmacology
Philadelphia, Pennsylvania, 19104
Annachristine Hoover, 310-560-7767, annachristine.hoover@pennmedicine.upenn.edu
Anh Le, DDS, PhD, 215-662-6176, anh.le@pennmedicine.upenn.edu
About this study
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.
Read more
The following occurs during a singular clinic visit for participants:
- Minimally Invasive Brush Test: A clinician gently rotates a soft brush over the mouth tissue to collect surface cells.
- Stain-Free Imaging \& AI Analysis: The DUV microscope scans the unstained cells in minutes, and the AI analyzes cell features (such as nucleus size and shape) in under 10 seconds.
- Standard Medical Care: Participants with suspicious spots receive a standard tissue biopsy to ensure a definitive, confirmed diagnosis regardless of the AI result.
This is important given that the five-year survival rates for oral cancer exceed 80% when caught early but drop to under 20% if detected late. By delivering rapid results directly at the clinic, this technology aims to eliminate long waiting periods for lab results, accelerate specialist referrals, and improve access to early screening in community dental and medical clinics.
Read the detailed description
This research project establishes a new diagnostic paradigm by transforming oral brush cytology from a centralized, laboratory-dependent procedure into an automated, AI-assisted point-of-care (POC) triage system. Traditional brush cytology relies on chemical staining, physical sample shipping, and off-site expert review, which can introduce diagnostic turnaround delays. By combining label-free optical imaging with automated hardware and deep learning, this system aims to deliver immediate, same-visit triage of suspicious oral lesions directly within primary dental and outpatient clinics.
Optical Physics \& Optomechanical Engineering: The core imaging system utilizes Deep Ultraviolet (DUV) microscopy operating in the 200-280 nm spectral range. At these wavelengths, cellular nucleic acids and proteins exhibit strong intrinsic light absorption, enabling submicron-resolution, high-contrast visualization of nuclear architecture without chemical dyes or fluorescent stains.
Transformer-Based AI Framework (CellViT): Cellular analysis and classification are powered by an adapted CellViT deep learning framework, which replaces traditional object-detection architectures like YOLOv7.
- Conditions
- Oral Potentially Malignant Lesions, Oral Potentially Malignant Disorders, Oral Cancer , Oral Squamous Cell Carcinoma, Oral Cavity Cancer, Oral Cancer
- Being tested
- Deep UV-M and AI Cytology Triage
- Keywords
- oral cancer, oral squamous cell carcinoma, oral cavity cancer, oral potentially malignant lesions
- Medical subject headings
- Mouth Neoplasms, Squamous Cell Carcinoma of Head and Neck
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Deep UV-M and AI Cytology TriageDevice
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).
| Study group | Role | What they receive |
|---|---|---|
| AI-Enabled Deep UV Brush Cytology with Biopsy Validation | Experimental | 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. Receives: Device: Deep UV-M and AI Cytology Triage |
What is being measured
The primary outcome is the main question the study is designed to answer.
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.
Measured: 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.
Secondary outcomes (1)
Three-Class Diagnostic Discrimination
While the primary endpoint focuses on binary triage (non-dysplasia vs. dysplasia/cancer), the secondary analysis evaluates the AI framework's ability to discriminate samples across three distinct diagnostic categories: non-dysplasia, dysplasia, and invasive cancer.
Measured: From sample collection on Day 1 through completion of 3-class histopathological grading, assessed up to 14 days post-procedure.
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted25 Sep 2026
- Study start1 Dec 2026 (estimated)
- Primary completionDec 2028 (estimated)
- Study completionDec 2028 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Oral Potentially Malignant LesionsStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Diagnosis
- Allocation
- Not applicable
- Intervention model
- Single group
- Masking
- None (open label)
- Enrolment
- 270 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Anh Le
- Sponsor type
- University, hospital or other
- Collaborators
- University of Arizona
- Responsible party
- Sponsor-investigator, Anh Le, University of Pennsylvania
- Investigators
- Anh D Le, DDS, PhD, Principal investigator, University of Pennsylvania
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07842211
- Sponsor's protocol ID
- 26-6563
- Acronym
- DEEP UV-M
- Status last verified
- Sep 2026
- First submitted
- 16 Sep 2026
- Last updated
- 25 Sep 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No