EUVIMEDEUVIMED entdecken
Crossref

Automatic segmentation of pericardial adipose tissue from cardiac MR images via semi‐supervised method with difference‐guided consistency

Xinru Zhang, Shoujun Zhou, Bohan Li, Yuanquan Wang, Ke Lu, Weipeng Liu, Zhida Wang

Medical Physics · 2025-03 · 52 (3) · 1679-1692

DOI: 10.1002/mp.17558 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 05.12.2024. Verfasst von Xinru Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Hebei University of Technology (HeBUT), Tianjin, China. Hauptthemen laut MEDLINE: Adipose Tissue, Pericardium, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Shenzhen Medical Research Fund, National Science Foundation, National science foundation of Hebei Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate and automatic segmentation of pericardial adipose tissue (PEAT) in cardiac magnetic resonance (MR) images is essential for the diagnosis and treatment of cardiovascular diseases. Precise segmentation is challenging due to high costs and the need for specialized knowledge, as a large amount of accurately annotated data is required, demanding significant time and medical resources.

Purpose

In order to reduce the burden of data annotation while maintaining the high accuracy of segmentation tasks, this paper introduces a semi‐supervised learning method to solve the limitations of current PEAT segmentation methods.

Methods

In this paper, we propose a difference‐guided collaborative mean teacher (DCMT) semi‐supervised method, designed for the segmentation of PEAT from DCMT consists of two main components: a semi‐supervised framework with a difference fusion strategy and a backbone network MCM‐UNet using Mamba‐CNN mixture (MCM) blocks. The differential fusion strategy effectively utilizes the uncertain areas in unlabeled data, encouraging the model to reach a consensus in predictions across these difficult‐to‐segment yet information‐rich areas. In addition, considering the sparse and scattered distribution of PEAT in cardiac MR images, which makes it challenging to segment, we propose MCM‐UNet as the backbone network in our semi‐supervised framework. This not only enhances the processing ability of global information, but also accurately captures the detailed local features of the image, which greatly improves the accuracy of PEAT segmentation.

Results

Our experiments conducted on the MRPEAT dataset show that our DCMT method outperforms existing state‐of‐the‐art semi‐supervised methods in terms of segmentation accuracy. These findings underscore the effectiveness of our approach in handling the specific challenges associated with PEAT segmentation.

Conclusions

The DCMT method significantly improves the accuracy of PEAT segmentation in cardiac MR images. By effectively utilizing uncertain areas in the data and enhancing feature capture with the MCM‐UNet, our approach demonstrates superior performance and offers a promising solution for semi‐supervised learning in medical image segmentation. This method can alleviate the extensive annotation requirements typically necessary for training accurate segmentation models in medical imaging.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Adipose TissuePericardiumMagnetic Resonance ImagingImage Processing, Computer-AssistedSupervised Machine LearningHeartHumansAutomation

Stichwörter der Autor:innen

cardiac MR imagesmambamean teacherpericardial adipose tissue (PEAT)semi‐supervised learning

Autor:innen und Institutionen

  • School of Artificial Intelligence, Hebei University of Technology (HeBUT), Tianjin, China.
  • Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
  • School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China.
  • NHC Key Laboratory of Hormones and Development, Chu Hsien-I Memorial Hospital and Tianjin Institute of Endocrinology, Tianjin Key Laboratory of Metabolic Diseases, Tianjin Medical University, Tianjin, China.

Förderung

  • Shenzhen Medical Research Fund
  • National Science Foundation
  • National science foundation of Hebei Province
  • National Science foundation of Guangdong Province
  • Shenzhen Technology Innovation Commission

Zitieren

APA

Zhang, X., Zhou, S., Li, B., Wang, Y., Lu, K., Liu, W., & Wang, Z. (2025). Automatic segmentation of pericardial adipose tissue from cardiac MR images via semi‐supervised method with difference‐guided consistency. Medical Physics, 52(3), 1679-1692. https://doi.org/10.1002/mp.17558

Vancouver

Zhang X, Zhou S, Li B, Wang Y, Lu K, Liu W, et al. Automatic segmentation of pericardial adipose tissue from cardiac MR images via semi‐supervised method with difference‐guided consistency. Medical Physics. 2025;52(3):1679-1692. doi:10.1002/mp.17558

BibTeX
@article{Zhang2025,
  author = {Zhang, Xinru and Zhou, Shoujun and Li, Bohan and Wang, Yuanquan and Lu, Ke and Liu, Weipeng and Wang, Zhida},
  title = {Automatic segmentation of pericardial adipose tissue from cardiac MR images via semi‐supervised method with difference‐guided consistency},
  journal = {Medical Physics},
  year = {2025},
  volume = {52},
  number = {3},
  pages = {1679--1692},
  doi = {10.1002/mp.17558}
}
Kostenlos starten →