EUVIMEDEUVIMED entdecken
Crossref

UMamba-Dual: A dual-branch model based on UMamba for cesarean scar disorder segmentation

Jing Zhou, Jian Zhang, Xinran Wang, Yong Lin, Wei Xia

Journal of X-Ray Science and Technology · 2026-05 · 34 (3) · 393-402

DOI: 10.1177/08953996261439080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology, online erschienen am 13.04.2026. Verfasst von Jing Zhou und 4 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School, University of Shanghai for Science and Technology, Shanghai, China. Hauptthemen laut MEDLINE: Cicatrix, Cesarean Section, Image Processing, Computer-Assisted, Image Interpretation, Computer-Assisted. Die Arbeit nennt 32 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction and Hypothesis Accurate segmentation of cesarean scar disorder (CSDi) in ultrasound images is crucial for clinical diagnosis, disease monitoring, and personalized treatment. However, the ambiguous boundaries and complex anatomical structures of CSDi pose significant challenges. To address this, we propose UMamba-Dual, a dual-branch model derived from UMamba, designed to enhance segmentation performance in CSDi regions and provide reliable imaging support for clinical decision-making.

Methods

UMamba-Dual integrates the strengths of two enhanced branches: Dual-Bot, incorporating squeeze-and-excitation (SE) attention, and Dual-Enc, employing a feature pyramid network (FPN) for improved feature representation and multi-scale perception. The training dataset included 1200 augmented 2D ultrasound images from 300 originals via flipping and rotation. An independent test set of 32 images was randomly selected and excluded from training and validation. Model performance was evaluated using Dice similarity coefficient, Intersection over Union (IoU), and Normalized Surface Dice (NSD), and compared with classical segmentation models such as nnUNet and VM-UNet.

Results

UMamba-Dual achieved superior performance with Dice = 0.832, IoU = 0.782, and NSD = 0.788, consistently outperforming both classical models (UNet, nnUNet) and the recent VM-UNet, as well as the internal baselines (UMamba_Bot, UMamba_Enc).

Conclusions

UMamba-Dual enables more accurate and robust segmentation of CSDi regions in ultrasound images, particularly in cases characterized by ambiguous boundaries or irregular anatomical structures. These results highlight its potential for reliable clinical application.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CicatrixCesarean SectionImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedHumansFemaleUltrasonographyAlgorithmsPregnancy

Stichwörter der Autor:innen

CSDi ultrasound image segmentationFPNSEUMambamodel fusion

Autor:innen und Institutionen

  • Graduate School, University of Shanghai for Science and Technology, Shanghai, China.
  • International Peace Maternity and Child Health Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.

Zitieren

APA

Zhou, J., Zhang, J., Wang, X., Lin, Y., & Xia, W. (2026). UMamba-Dual: A dual-branch model based on UMamba for cesarean scar disorder segmentation. Journal of X-Ray Science and Technology, 34(3), 393-402. https://doi.org/10.1177/08953996261439080

Vancouver

Zhou J, Zhang J, Wang X, Lin Y, Xia W. UMamba-Dual: A dual-branch model based on UMamba for cesarean scar disorder segmentation. Journal of X-Ray Science and Technology. 2026;34(3):393-402. doi:10.1177/08953996261439080

BibTeX
@article{Zhou2026,
  author = {Zhou, Jing and Zhang, Jian and Wang, Xinran and Lin, Yong and Xia, Wei},
  title = {UMamba-Dual: A dual-branch model based on UMamba for cesarean scar disorder segmentation},
  journal = {Journal of X-Ray Science and Technology},
  year = {2026},
  volume = {34},
  number = {3},
  pages = {393--402},
  doi = {10.1177/08953996261439080}
}
Kostenlos starten →