Efficient labelling for efficient deep learning: the benefit of a multiple-image-ranking method to generate high volume training data applied to ventricular slice level classification in cardiac MRI.

Zaman, Sameer; Vimalesvaran, Kavitha; Howard, James P; Chappell, Digby; Varela, Marta; Peters, Nicholas S; Francis, Darrel P; Bharath, Anil A; Linton, Nick W F; Cole, Graham D

Zaman, Sameer; Vimalesvaran, Kavitha; Howard, James P; Chappell, Digby; Varela, Marta; Peters, Nicholas S; Francis, Darrel P; Bharath, Anil A; Linton, Nick W F; Cole, Graham D.

Afiliação

Zaman S; National Heart and Lung Institute, Imperial College London, London, UK.
Vimalesvaran K; Imperial College Healthcare NHS Trust, London, UK.
Howard JP; AI for Healthcare Centre for Doctoral Training, Imperial College London, London, UK.
Chappell D; National Heart and Lung Institute, Imperial College London, London, UK.
Varela M; Imperial College Healthcare NHS Trust, London, UK.
Peters NS; AI for Healthcare Centre for Doctoral Training, Imperial College London, London, UK.
Francis DP; National Heart and Lung Institute, Imperial College London, London, UK.
Bharath AA; Imperial College Healthcare NHS Trust, London, UK.
Linton NWF; AI for Healthcare Centre for Doctoral Training, Imperial College London, London, UK.
Cole GD; National Heart and Lung Institute, Imperial College London, London, UK.

J Med Artif Intell ; 6: 4, 2023 Apr.

Article em En | MEDLINE | ID: mdl-37346802

Palavras-chave

Deep learning (DL); clinical imaging; convolution neural network (CNN); data labelling; ground truth

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Tipo de estudo: Guideline / Prognostic_studies Idioma: En Revista: J Med Artif Intell Ano de publicação: 2023 Tipo de documento: Article País de afiliação: Reino Unido

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google