Overcoming barriers to generalizability of deep learning for dental image analysis

Overcoming barriers to generalizability of deep learning for dental image analysis - GEN-DENT.AI

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00038277

Enrollment

10000

Registered

2025-11-12

Start date

2026-04-01

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

Dental caries, Apical periodontitis, Oral mucosal lesions

Interventions

Group 1: Multi-insitutional dataset of de-identified dental radiographs and intraoral photographs with associated metadata used for the development of AI models and an independent dataset used for ext

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: De-identified radiographs and intraoral photographs of adult humans.

Exclusion criteria

Exclusion criteria: Radiographs and intraoral photographs of insufficient quality or with major artifacts.

Design outcomes

Primary

Measure	Time frame
Identification and quantification of factors influencing the generalizability of deep-learning models across sites, modalities, and tasks.	—

Secondary

Measure	Time frame
Comparison of model performance with and without the implementation of generalizability-improving strategies.	—

Countries

Brazil, Chile, Cyprus, Germany, India, Iran, South Korea, Spain

Contacts

Public ContactFalk Schwendicke

LMU Klinikum, Poliklinik für Zahnerhaltung, Parodontologie und digitale Zahnmedizin

Falk.Schwendicke@med.uni-muenchen.de+4989 4400 59301

Outcome results

None listed

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