NCT04890847UnknownNot Applicable
A Platform for Multidisciplinary Medical Artificial Intelligence Development
Sun Yat-sen University1 site in 1 country200 target enrollmentStarted: March 18, 2021Last updated:
Conditions
Trial Snapshot
- Phase
- Not Applicable
- Sponsor
- Enrollment
- 200
- Locations
- 1
- Primary Endpoint
- annotation accuracy
Study Overview
Brief Summary
Biomedical deep learning (DL) often relies heavily on generating reliable labels for large-scale data and highly technical requirements for model training. To efficiently develop DL models, we established an integrated platform to introduce automation to both annotation and model training-the primary process of DL model development. Based on this platform, we quantitively validated and compared the annotation strategy and AI model development with the pure manual annotation method performed on medical image datasets from multiple disciplines.
Study Design
- Study Type
- Observational
- Observational Model
- Case Control
- Time Perspective
- Cross Sectional
Eligibility Criteria
- Sex
- All
- Accepts Healthy Volunteers
- Yes
Inclusion Criteria
- •have medical imaging record (including ophthalmology, pathology, radiography, blood cells, and endoscopy)
Exclusion Criteria
- •unqualified medical imaging
Outcomes
Primary Outcomes
annotation accuracy
Time Frame: baseline
calculate annotation accuracy for comparison between groups with using the annotation results
Secondary Outcomes
- AUC of model performance(baseline)
- accuracy of model performance(baseline)
- annotation time cost(baseline)
Investigators
Haotian Lin
Principal Investigator
Sun Yat-sen University
Study Sites (1)
Loading locations...
Similar Trials
Recruiting
Not Applicable
Development of a Deep Learning System for Identification of Neuro-Ophthalmological Conditions on Color Fundus Photographs in Emergency DepartmentEye DiseasesNCT06643338Fondation Ophtalmologique Adolphe de Rothschild1,000
Recruiting
Not Applicable
Integrating Deep Learning CT-scan Model, Biological and Clinical Variables to Predict Severity of Asthma in ChildrenAsthma in ChildrenNCT05140889Fondazione IRCCS Policlinico San Matteo di Pavia25
Recruiting
Not Applicable
Development of Clinically High Efficient Platforms for Individualised Treatment of Cervix CancerCervix CancerNCT05102240Tata Memorial Hospital1,800
Completed
Not Applicable
RELEVANCE - RWE Study in Unresectable Non-Small Cell Lung Cancer (Stage III) in CanadaNon-small Cell Lung CancerNCT05933044AstraZeneca662
Unknown
Not Applicable
Artificial Intelligence With Deep Learning and Genes on Cardiovascular DiseaseCardiovascular DiseasesNCT03877614National Cheng-Kung University Hospital5,000