Skip to content

Using artificial intelligence to improve diagnosis and speed of reporting in patients with oral cancer through cytology and histopathology samples

Diagnostic Accuracy of Deep Learning Model for Touch Imprint Cytology and Histopathology in Oral Squamous Cell Carcinoma - AI

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
CTRI
Registry ID
CTRI/2026/05/111396
Enrollment
200
Registered
2026-05-29
Start date
Unknown
Completion date
Unknown
Last updated
2026-06-01

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Health Condition 1: C148- Malignant neoplasm of overlappingsites of lip, oral cavity and pharynx

Interventions

Intervention1: Nil: Nil

Sponsors

Dr Rajnish Pathania DeanPrincipal Rohilkhand Medical College Hospital
Lead Sponsor
Dr Madhusudan Astekar
Collaborator
Dr Roopa S Rao
Collaborator

Eligibility

Inclusion criteria

Inclusion criteria: All histopathologically diagnosed cases of oral squamous cell carcinoma will be included in the study, patients giving consent informed consent are willing to take part in the study

Exclusion criteria

Exclusion criteria: Patients who have received treatment (such as surgery, chemotherapy, radiation) for the Oral lesions before participating in the study, cases which are non-diagnostic or unsatisfactory for evaluation on Touch Imprint Cytology, inadequate biopsies will be excluded

Design outcomes

Primary

MeasureTime frame
Histopathology slides and Touch Imprint Cytology Smears will be reviewed at 2 weeks. Slide Digital Images will be reviewed at 4 weeks. Deep Learning Model will be trained and assessed at 16 weeks. Trained Deep Learning Model assessment at 20 weeks. Final Deep Learning Model assessment and Approval at 28 weeks. Timepoint: Histopathology slides and Touch Imprint Cytology Smears will be reviewed at 2 weeks. Slide Digital Images will be reviewed at 4 weeks. Deep Learning Model will be trained and assessed at 16 weeks. Trained Deep Learning Model assessment at 20 weeks. Final Deep Learning Model assessment and Approval at 28 weeks.

Secondary

MeasureTime frame
To assess the feasibility of developing deep learning model for cytology & histopathology image analysis & evaluate its diagnostic concordanceTimepoint: Deep Learning Model validity & feasibility testing & its approval at 30 weeks

Countries

India

Contacts

Public ContactDr Nitesh Mohan

Institute of Dental Sciences

madhu.tanu@gmail.com7599247899

Outcome results

None listed

Source: CTRI (via WHO ICTRP) · Data processed: Jun 11, 2026