Hybrid dual mean-teacher network with double-uncertainty guidance for semi-supervised segmentation of magnetic resonance images

• Published in: Computerized medical imaging and graphics 2024-07, Vol.115, p.102383, Article 102383
• Main Authors: Zhu, Jiayi, Bolsterlee, Bart, Chow, Brian V.Y., Song, Yang, Meijering, Erik
• Format: Article
• Language: English
• Subjects: Convolutional neural networks; Hybrid learning; Segmentation; Semi-supervised learning
• ISSN: 0895-6111; 1879-0771; 1879-0771
• DOI: 10.1016/j.compmedimag.2024.102383

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. •Most semi-supervised nets learn from a single space, leading to reduced capabilities.•A novel hybrid mean-teacher net for accurate and data-efficient MRI segmentation.•2D and 3D features are merged into hybrid features, greatly improving performance.•Accurate results achieved on three datasets with various structures and voxel sizes.•Human-level performance and consistency achieved with limited labeled data.•The method shows the potential to facilitate large-scale quantitative research.