Clinical trial · Observational
Deep Learning in Retinoblastoma Detection and Monitoring.
Deep Learning Computer-aided Detection System for Retinoblastoma Detection and Monitoring.
- Source
- ClinicalTrials.gov
- Retrieved
- Sep 8, 2026
- Layer
- normalized (units and labels harmonized; values unchanged)
- Run
- ING-CLINICALTRIALS-20260908-000001
Summary
Brief summary (as posted)
Retinoblastoma is the most common eye cancer of childhood. Eye-preserving therapies require routine monitoring of retinoblastoma regression and recurrence to guide corresponding treatment. In the current study, we develop a deep learning algorism that can simultaneously identify retinoblastoma tumours on Retcam images and distinguish between active and inactive retinoblastoma tumours. This algorism will be validated through a prospectively collected dataset.
Conditions
Conditions (1)
Free-text conditions as registered, with the CancerIndex entity they were reconciled to and the match type.
| Condition (as posted) | Mapped entity | Match | Confidence |
|---|---|---|---|
| Retinoblastoma | Retinoblastoma | ONTOLOGY_EXACT | 0.98 |
Interventions
Interventions (1)
| Intervention | Type | Mapped drug | Match |
|---|---|---|---|
| Deep learning algorism | Diagnostic Test | — | UNRESOLVED |
Design
Arms and outcomes
Arms (1)
- label
- Retinoblastoma patients
- description
- Retinoblastoma patients who undergo standard medical care in Beijing Tongren Hospital. The anonymous image of these patients will be prospectively collected and labelled by senior ophthalmologists.
- interventionNames
- Diagnostic Test: Deep learning algorism
Primary outcomes (1)
- measure
- Diagnosis accurcy of deep learning algorism
- timeFrame
- 1 week
- description
- The diagnosic accurcy of this deep learning algorism is the proportion of true positive and true negative in all evaluated cases
Eligibility
Eligibility (as posted)
- Sex
- All
- Minimum age
- 0 Years
- Maximum age
- 5 Years
Show eligibility criteria text
Inclusion Criteria: * Retinoblastoma patients undergo standard medical management. Exclusion Criteria: * The operators identified images non-assessable for a correct diagnosis, due to reasons such as blur and defocus, and excluded them from further analysis.
References
Publications (1)
- DERIVEDZhang R, Dong L, Li R, Zhang K, Li Y, Zhao H, Shi J, Ge X, Xu X, Jiang L, Shi X, Zhang C, Zhou W, Xu L, Wu H, Li H, Yu C, Li J, Ma J, Wei W. Automatic retinoblastoma screening and surveillance using deep learning. Br J Cancer. 2023 Aug;129(3):466-474. doi: 10.1038/s41416-023-02320-z. Epub 2023 Jun 21. PMID 37344582