Skip to content

A Deep Learning-Based Model for Automated Diagnosis of Dental Diseases from Panoramic Radiographs: A Multi-Center Retrospective Study

A Deep Learning-Based Model for Automated Diagnosis of Dental Diseases from Panoramic Radiographs: A Multi-Center Retrospective Study

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500109073
Enrollment
Unknown
Registered
2025-09-11
Start date
2025-09-30
Completion date
Unknown
Last updated
2026-02-02

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

Conditions

?Diseases of oral cavity

Interventions

Observation Group:none

Sponsors

Shanghai Ninth People's Hospital, Shanghai JiaoTong University School of Medicine
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 90 Years

Inclusion criteria

Inclusion criteria: 1. Age > 18 years? with a fully erupted permanent dentition. 2. Panoramic radiographs were obtained ?within 14 days after a clinical diagnosis? (e.g., dental caries, periapical lesions, impacted teeth, periodontitis) was confirmed by a clinician. 3. Radiographs must demonstrate ?complete dentition? and include ?complete maxillary and mandibular structures. ?4. Image Quality:?? Radiographs must be of ?diagnostic quality, without severe artifacts that obscure key anatomical structures of the jaws or critical areas of the dentition.

Exclusion criteria

Exclusion criteria: 1. Non-diagnostic scans? (significant motion artifacts, improper positioning). 2. Severe crowding or overlapping of the dentition, resulting in ?indistinguishable crown contours or margins? for multiple teeth in the anterior region.

Design outcomes

Primary

MeasureTime frame
accuracy;sensitivity;specificity;Area under receiver operating characteristic curve, AUC;

Countries

China

Contacts

Public ContactJiannan Liu

Shanghai Ninth People's Hospital, Shanghai JiaoTong University School of Medicine

laurence_ljn@163.com+86 156 1883 3445

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 7, 2026