Skip to main content
Clinical Trials/NCT04665102
NCT04665102UnknownNot Applicable

Validation of a Transfer Learning Deep Learning Algorithm for Image Classification in Multiple Pathologies

CRG UZ Brussel0 sites120 target enrollmentStarted: February 1, 2021Last updated:
Conditions

Trial Snapshot

Phase
Not Applicable
Sponsor
Enrollment
120
Primary Endpoint
Validation of Image classification by transfer learning algorithm

Study Overview

Brief Summary

Deep learning allows you to classify images using a self-learning algorithm. Transfer learning builds on an existing self-learning algorithm to enable image classification with fewer images. In this study, this technique will be applied to different image modalities in different syndromes. Retrospective study design.

Study Design

Study Type
Observational
Observational Model
Cohort
Time Perspective
Retrospective

Eligibility Criteria

Ages
18 Years to 100 Years (Adult, Older Adult)
Sex
All
Accepts Healthy Volunteers
Yes

Inclusion Criteria

  • •Availability of images, which allow discrimination.

Exclusion Criteria

  • •No availability of clear data on disease differentiation

Outcomes

Primary Outcomes

Validation of Image classification by transfer learning algorithm

Time Frame: 1 year

Secondary Outcomes

No secondary outcomes reported

Investigators

Sponsor
CRG UZ Brussel
Sponsor Class
Other
Responsible Party
Principal Investigator
Principal Investigator

Pieter Nelis

Researcher

CRG UZ Brussel

Similar Trials