Domain generalization in deep learning for contrast-enhanced imaging
Sendra-Balcells, C. (Universitat de Barcelona)
Campello, Victor M (Universitat de Barcelona)
Martín-Isla, C. (Universitat de Barcelona)
Viladés Medel, David (Institut d'Investigació Biomèdica Sant Pau)
Descalzo, Martin (Institut d'Investigació Biomèdica Sant Pau)
Guala, Andrea (Hospital Universitari Vall d'Hebron)
Rodriguez-Palomares, Jose F (Hospital Universitari Vall d'Hebron)
Lekadir, K. (Universitat de Barcelona)
Universitat Autònoma de Barcelona
Fecha: |
2022 |
Resumen: |
The domain generalization problem has been widely investigated in deep learning for non-contrast imaging over the last years, but it received limited attention for contrast-enhanced imaging. However, there are marked differences in contrast imaging protocols across clinical centers, in particular in the time between contrast injection and image acquisition, while access to multi-center contrast-enhanced image data is limited compared to available datasets for non-contrast imaging. This calls for new tools for generalizing single-domain, single-center deep learning models across new unseen domains and clinical centers in contrast-enhanced imaging. In this paper, we present an exhaustive evaluation of deep learning techniques to achieve generalizability to unseen clinical centers for contrast-enhanced image segmentation. To this end, several techniques are investigated, optimized and systematically evaluated, including data augmentation, domain mixing, transfer learning and domain adaptation. To demonstrate the potential of domain generalization for contrast-enhanced imaging, the methods are evaluated for ventricular segmentation in contrast-enhanced cardiac magnetic resonance imaging (MRI). The results are obtained based on a multi-center cardiac contrast-enhanced MRI dataset acquired in four hospitals located in three countries (France, Spain and China). They show that the combination of data augmentation and transfer learning can lead to single-center models that generalize well to new clinical centers not included during training. Single-domain neural networks enriched with suitable generalization procedures can reach and even surpass the performance of multi-center, multi-vendor models in contrast-enhanced imaging, hence eliminating the need for comprehensive multi-center datasets to train generalizable models. |
Derechos: |
Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original. |
Lengua: |
Anglès |
Documento: |
Article ; recerca ; Versió publicada |
Materia: |
Cardiac image segmentation ;
Contrast-enhanced imaging ;
Data augmentation ;
Deep learning ;
Domain generalization ;
Transfer learning |
Publicado en: |
Computers in Biology and Medicine, Vol. 149 (october 2022) , p. 106052, ISSN 1879-0534 |
DOI: 10.1016/j.compbiomed.2022.106052
PMID: 36055164
El registro aparece en las colecciones:
Documentos de investigación >
Documentos de los grupos de investigación de la UAB >
Centros y grupos de investigación (producción científica) >
Ciencias de la salud y biociencias >
Institut de Recerca Sant PauArtículos >
Artículos de investigaciónArtículos >
Artículos publicados
Registro creado el 2024-03-25, última modificación el 2024-05-22