EUVIMEDEUVIMED entdecken
Crossref

Semi‐supervised medical image segmentation via cross‐guidance and feature‐level consistency dual regularization schemes

Xiaosu Yang, Jiya Tian, Yaping Wan, Mingzhi Chen, Lingna Chen, Junxi Chen

Medical Physics · 2023

DOI: 10.1002/mp.16217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2023. Verfasst von Xiaosu Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Computer School, University of South China, Hengyang, China. Hauptthemen laut MEDLINE: Cell Nucleus, Heart. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Postgraduate Research Innovation, National Natural Science Foundation of China, National Natural Science Foundation of hunan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Semi‐supervised learning is becoming an effective solution for medical image segmentation because of the lack of a large amount of labeled data.

Purpose

Consistency‐based strategy is widely used in semi‐supervised learning. However, it is still a challenging problem because of the coupling of CNN‐based isomorphic models. In this study, we propose a new semi‐supervised medical image segmentation network (DRS‐Net) based on a dual‐regularization scheme to address this challenge.

Methods

The proposed model consists of a CNN and a multidecoder hybrid Transformer, which adopts two regularization schemes to extract more generalized representations for unlabeled data. Considering the difference in learning paradigm, we introduce the cross‐guidance between CNN and hybrid Transformer, which uses the pseudo label output from one model to supervise the other model better to excavate valid representations from unlabeled data. In addition, we use feature‐level consistency regularization to effectively improve the feature extraction performance. We apply different perturbations to the feature maps output from the hybrid Transformer encoder and keep an invariance of the predictions to enhance the encoder's representations.

Results

We have extensively evaluated our approach on three typical medical image datasets, including CT slices from Spleen, MRI slices from the Heart, and FM Nuclei. We compare DRS‐Net with state‐of‐the‐art methods, and experiment results show that DRS‐Net performs better on the Spleen dataset, where the dice similarity coefficient increased by about 3.5%. The experimental results on the Heart and Nuclei datasets show that DRS‐Net also improves the segmentation effect of the two datasets.

Conclusions

The proposed DRS‐Net enhances the segmentation performance of the datasets with three different medical modalities, where the dual‐regularization scheme extracts more generalized representations and solves the overfitting problem.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cell NucleusHeartSpleenSupervised Machine LearningImage Processing, Computer-Assisted

Stichwörter der Autor:innen

co-trainingconsistency regularizationsemi-supervised segmentation

Autor:innen und Institutionen

  • Computer School, University of South China, Hengyang, China.
  • School of Information Engineering, Xinjiang Institute of Technology, Aksu, China.
  • School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China.
  • Affiliated Nanhua Hospital, University of South China, Hengyang, China.

Förderung

  • Postgraduate Research Innovation
  • National Natural Science Foundation of China
  • National Natural Science Foundation of hunan

Zitieren

APA

Yang, X., Tian, J., Wan, Y., Chen, M., Chen, L., & Chen, J. (2023). Semi‐supervised medical image segmentation via cross‐guidance and feature‐level consistency dual regularization schemes. Medical Physics. https://doi.org/10.1002/mp.16217

Vancouver

Yang X, Tian J, Wan Y, Chen M, Chen L, Chen J. Semi‐supervised medical image segmentation via cross‐guidance and feature‐level consistency dual regularization schemes. Medical Physics. 2023. doi:10.1002/mp.16217

BibTeX
@article{Yang2023,
  author = {Yang, Xiaosu and Tian, Jiya and Wan, Yaping and Chen, Mingzhi and Chen, Lingna and Chen, Junxi},
  title = {Semi‐supervised medical image segmentation via cross‐guidance and feature‐level consistency dual regularization schemes},
  journal = {Medical Physics},
  year = {2023},
  doi = {10.1002/mp.16217}
}
Kostenlos starten →