Transfer Learning
Cross-source consensus on Transfer Learning from 1 sources and 4 claims.
1 sources · 4 claims
Uses
How it works
Risks & contraindications
Evidence quality
Highlighted claims
- Fine-tuning CAD4TBv7 with only 525 paediatric CXRs improved AUC from 0.58 to 0.72 against a radiological reference standard, a statistically significant gain. — Catalysing Artificial Intelligence for Paediatric Tuberculosis Research (CAPTURE): protocol for a global multicentre study establishing a paediatric chest X-ray repository to evaluate computer-aided detection algorithms
- Approximately two-thirds of the CAPTURE repository will be made available as a training set for developers to fine-tune paediatric-specific algorithms. — Catalysing Artificial Intelligence for Paediatric Tuberculosis Research (CAPTURE): protocol for a global multicentre study establishing a paediatric chest X-ray repository to evaluate computer-aided detection algorithms
- Transfer learning — fine-tuning adult-trained algorithms on smaller paediatric datasets — is a feasible alternative to building paediatric CAD from scratch. — Catalysing Artificial Intelligence for Paediatric Tuberculosis Research (CAPTURE): protocol for a global multicentre study establishing a paediatric chest X-ray repository to evaluate computer-aided detection algorithms
- Building a paediatric CAD system from scratch would require prohibitively large labelled image datasets. — Catalysing Artificial Intelligence for Paediatric Tuberculosis Research (CAPTURE): protocol for a global multicentre study establishing a paediatric chest X-ray repository to evaluate computer-aided detection algorithms