Data augmentation via warping transforms for modeling natural variability in the corneal endothelium enhances semi-supervised segmentation

Image segmentation of the corneal endothelium with deep convolutional neural networks (CNN) is challenging due to the scarcity of expert-annotated data. This work proposes a data augmentation technique via warping to enhance the performance of semi-supervised training of CNNs for accurate segmentati...

Full description

Autores:
Sanchez, Sergio
Vallez, Noelia
Bueno, Gloria
Marrugo, Andres G
Tipo de recurso:
Fecha de publicación:
2024
Institución:
Universidad Tecnológica de Bolívar
Repositorio:
Repositorio Institucional UTB
Idioma:
eng
OAI Identifier:
oai:repositorio.utb.edu.co:20.500.12585/12773
Acceso en línea:
https://hdl.handle.net/20.500.12585/12773
Palabra clave:
Data augmentation
Warping transforms
Corneal endothelium
Semi-supervised segmentation
Deep convolutional neural networks (CNNs)
Image segmentation
Medical imaging
Keypoint extraction
Delaunay triangulation
Affine transformations
Mask refinement Mean intersection over union (mIoU)
Dice coefficient (DC)
Natural variability
Medical image cell segmentation
LEMB
Rights
openAccess
License
http://creativecommons.org/licenses/by-nc-nd/4.0/