EUVIMEDEUVIMED entdecken
Crossref

An enhanced visual state space model for myocardial pathology segmentation in multi‐sequence cardiac MRI

Shuning Li, Xiang Li, Pingping Wang, Kunmeng Liu, Benzheng Wei, Jinyu Cong

Medical Physics · 2025-06 · 52 (6) · 4355-4370

DOI: 10.1002/mp.17761 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 19.03.2025. Verfasst von Shuning Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Myocardium, Heart. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: Demostration Projects of Science and Technology for the People of Qingdao City, National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Myocardial pathology (scar and edema) segmentation plays a crucial role in the diagnosis, treatment, and prognosis of myocardial infarction (MI). However, the current mainstream models for myocardial pathology segmentation have the following limitations when faced with cardiac magnetic resonance(CMR) images with multiple objects and large changes in object scale: the remote modeling ability of convolutional neural networks is insufficient, and the computational complexity of transformers is high, which makes myocardial pathology segmentation challenging.

Purpose

This study aims to develop a novel model to address the image characteristics and algorithmic challenges faced in the myocardial pathology segmentation task and improve the accuracy and efficiency of myocardial pathology segmentation.

Methods

We developed a novel visual state space (VSS)‐based deep neural network, MPS‐Mamba. In order to accurately and adequately extract CMR image features, the encoder employs a dual‐branch structure to extract global and local features of the image. Among them, the VSS branch overcomes the limitations of the current mainstream models for myocardial pathology segmentation by modeling remote relationships through linear computability, while the convolutional‐based branch provides complementary local information. Given the unique properties of the dual branches, we design a modular dual‐branch fusion module for fusing dual branches to enhance the feature representation of the dual encoder. To improve the ability to model objects of different scales in cardiac magnetic resonance (CMR) images, a multi‐scale feature fusion (MSF) module is designed to achieve effective integration and fine expression of multi‐scale information. To further incorporate anatomical knowledge to optimize segmentation results, a decoder with three decoding branches is designed to output segmentation results of scar, edema, and myocardium, respectively. In addition, multiple sets of constraint functions are used to not only improve the segmentation accuracy of myocardial pathology but also effectively model the spatial position relationship between myocardium, scar, and edema.

Results

The proposed method was comprehensively evaluated on the MyoPS 2020 dataset, and the results showed that MPS‐Mamba achieved an average Dice score of 0.717 0.169 in myocardial scar segmentation, which is superior to the current mainstream methods. In addition, MPS‐Mamba also performed well in the edema segmentation task, with an average Dice score of 0.7350.073. The experimental results further demonstrate the effectiveness of MPS‐Mamba in segmenting myocardial pathologies in multi‐sequence CMR images, verifying its advantages in myocardial pathology segmentation tasks.

Conclusions

Given the effectiveness and superiority of MPS‐Mamba, this method is expected to become a potential myocardial pathology segmentation tool that can effectively assist clinical diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingImage Processing, Computer-AssistedMyocardiumHeartHumansNeural Networks, Computer

Stichwörter der Autor:innen

edemamulti‐scale feature fusionmyocardial pathology segmentationscarvisual state space

Autor:innen und Institutionen

  • Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao, China.
  • Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao, China.
  • Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine, Shandong University of Traditional Chinese Medicine, Qingdao, China.

Förderung

  • Demostration Projects of Science and Technology for the People of Qingdao City
  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province
  • Special fund of Qilu Health and Health Leading Talents Training Project
  • Science and Technology of Traditional Chinese Medicine Project of Shandong Province
  • Young Talent of Lifting engineering for Science and Technology in shandong,China

Zitieren

APA

Li, S., Li, X., Wang, P., Liu, K., Wei, B., & Cong, J. (2025). An enhanced visual state space model for myocardial pathology segmentation in multi‐sequence cardiac MRI. Medical Physics, 52(6), 4355-4370. https://doi.org/10.1002/mp.17761

Vancouver

Li S, Li X, Wang P, Liu K, Wei B, Cong J. An enhanced visual state space model for myocardial pathology segmentation in multi‐sequence cardiac MRI. Medical Physics. 2025;52(6):4355-4370. doi:10.1002/mp.17761

BibTeX
@article{Li2025,
  author = {Li, Shuning and Li, Xiang and Wang, Pingping and Liu, Kunmeng and Wei, Benzheng and Cong, Jinyu},
  title = {An enhanced visual state space model for myocardial pathology segmentation in multi‐sequence cardiac MRI},
  journal = {Medical Physics},
  year = {2025},
  volume = {52},
  number = {6},
  pages = {4355--4370},
  doi = {10.1002/mp.17761}
}
Kostenlos starten →