Advancing cardiac MRI multi‐structure segmentation: A semi‐supervised multidimensional consistency constraint learning network
Medical Physics · 2025
DOI: 10.1002/mp.17805 ↗At a glance
Journal article in Medical Physics, 2025. Written by Hongzhen Cui and 5 co-authors. Institution: School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China. Major MEDLINE topics: Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Heart, Supervised Machine Learning. Cited 1 times so far (Crossref); 51 references. Funded by: Non-Profit Central Research Institute Fund of Chinese Academy of Medical Sciences, Fundamental Research Funds for the Central Universities.
Abstract (original language)
Background
Deep convolutional neural networks (DCNNs) have been proposed for medical Magnetic Resonance Imaging (MRI) segmentation, but their effectiveness is often limited by challenges in semantic discrimination, boundary delineation, and spatial context modeling.
Purpose
To address these challenges, we present the Multidimensional Consistency Constraint Learning Network (MDCC‐Net) for multi‐structure segmentation of cardiac MRI using a semi‐supervised approach.
Methods
MDCC‐Net incorporates a shared encoder, multiple differentiated decoders, and leverages pyramid boundary consistency features and spatial consistency constraints. The model employs mutual consistency constraints and pseudo‐labels to enhance segmentation performance. Additionally, MDCC‐Net uses a combination of Dice loss and mean squared error loss to facilitate convergence and improve accuracy.
Results
Experiments on the ACDC cardiac MRI dataset demonstrate that MDCC‐Net achieves state‐of‐the‐art performance in multi‐structure segmentation of the left ventricle (LV), myocardium (MYO), and right ventricle (RV). Specifically, MDCC‐Net attained a Dice coefficient (Dice) of 0.8763 and a Jaccard index of 0.7906 on average. The right ventricle's Average Surface Distance (ASD) reached a best performance of 0.5391, and the left ventricle's Dice attained an optimal value of 0.8965. These results highlight the model's superior ability to utilize semi‐supervised data through consistency and entropy minimization constraints. In addition, the generalization of MDCC‐Net is verified on the M&Ms dataset.
Conclusions
MDCC‐Net significantly enhances the multi‐structure segmentation of cardiac MRI under multidimensional consistency constraints. This approach provides a foundational study for integrating multifeature fusion in clinical automated and semiautomated multi‐organ and multi‐tissue segmentation, thus potentially improving diagnostic and treatment planning processes in clinical settings.
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China.
- School of Nursing, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China.
Funding
- Non-Profit Central Research Institute Fund of Chinese Academy of Medical Sciences
- Fundamental Research Funds for the Central Universities
Cite
APA
Cui, H., Piao, M., Huang, X., Zhu, X., Ma, H., & Peng, Y. (2025). Advancing cardiac MRI multi‐structure segmentation: A semi‐supervised multidimensional consistency constraint learning network. Medical Physics. https://doi.org/10.1002/mp.17805
Vancouver
Cui H, Piao M, Huang X, Zhu X, Ma H, Peng Y. Advancing cardiac MRI multi‐structure segmentation: A semi‐supervised multidimensional consistency constraint learning network. Medical Physics. 2025. doi:10.1002/mp.17805
BibTeX
@article{Cui2025,
author = {Cui, Hongzhen and Piao, Meihua and Huang, Xinghe and Zhu, Xiaoyue and Ma, Haoming and Peng, Yunfeng},
title = {Advancing cardiac MRI multi‐structure segmentation: A semi‐supervised multidimensional consistency constraint learning network},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.17805}
}
EUVIMED