Hybrid dual mean-teacher network with double-uncertainty guidance for semi-supervised segmentation of magnetic resonance images.
Comput Med Imaging Graph
; 115: 102383, 2024 Jul.
Article
em En
| MEDLINE
| ID: mdl-38643551
ABSTRACT
Semi-supervised learning has made significant progress in medical image segmentation. However, existing methods primarily utilize information from a single dimensionality, resulting in sub-optimal performance on challenging magnetic resonance imaging (MRI) data with multiple segmentation objects and anisotropic resolution. To address this issue, we present a Hybrid Dual Mean-Teacher (HD-Teacher) model with hybrid, semi-supervised, and multi-task learning to achieve effective semi-supervised segmentation. HD-Teacher employs a 2D and a 3D mean-teacher network to produce segmentation labels and signed distance fields from the hybrid information captured in both dimensionalities. This hybrid mechanism allows HD-Teacher to utilize features from 2D, 3D, or both dimensions as needed. Outputs from 2D and 3D teacher models are dynamically combined based on confidence scores, forming a single hybrid prediction with estimated uncertainty. We propose a hybrid regularization module to encourage both student models to produce results close to the uncertainty-weighted hybrid prediction to further improve their feature extraction capability. Extensive experiments of binary and multi-class segmentation conducted on three MRI datasets demonstrated that the proposed framework could (1) significantly outperform state-of-the-art semi-supervised methods (2) surpass a fully-supervised VNet trained on substantially more annotated data, and (3) perform on par with human raters on muscle and bone segmentation task. Code will be available at https//github.com/ThisGame42/Hybrid-Teacher.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Imageamento por Ressonância Magnética
/
Aprendizado de Máquina Supervisionado
Limite:
Humans
Idioma:
En
Revista:
Comput Med Imaging Graph
Assunto da revista:
DIAGNOSTICO POR IMAGEM
Ano de publicação:
2024
Tipo de documento:
Article