EUVIMEDEUVIMED entdecken
Crossref

MCPNet: Morphological Constraint‐Based Copy‐Paste Network for Semi‐Supervised Foetal Head Segmentation

Baoping Zhu, Linjie Qu, Linkuan Zhou, Zhenyu Luo, Yan Chen

The International Journal of Medical Robotics and Computer Assisted Surgery · 2026

DOI: 10.1002/rcs.70140 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Medical Robotics and Computer Assisted Surgery, 2026. Verfasst von Baoping Zhu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Aristogenesis, Department of Obstetrics and Gynecology, Women and Children's Hospital, School of Medicine, Xiamen University, Xiamen, F…. Hauptthemen laut MEDLINE: Ultrasonography, Prenatal, Head, Image Processing, Computer-Assisted, Fetus. Die Arbeit nennt 41 Literaturangaben. Gefördert von: Young Scientists Research Project of Xiamen Health and Wellness High-Quality Development Science and Technology Plan Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The foetal head's automatic segmentation from ultrasound imagery is considered a key step in prenatal examination. However, achieving high‐quality semi‐supervised foetal head image segmentation remains challenging due to low image resolution, unclear boundaries, and inconsistencies between labelled and unlabelled data.

Methods

To overcome these obstacles, we propose MCPNet, a morphological constraint‐based copy‐paste network for semi‐supervised foetal head segmentation, incorporating score‐guided morphological refinement (SMR) and copy‐paste mixing augmentation (CPMA). SMR employs weighted scores derived from Sobel operators and Euclidean transform to ensure boundary consistency. Additionally, to mitigate the distribution gap between labelled and unlabelled data, we introduce CPMA. This method uses random cropping to swap foreground and background between labelled and unlabelled data.

Results

On the HC18 and PSFH benchmarks, our method achieves Dice scores of 93.72% and 92.31% respectively with 20% labelled data.

Conclusions

The results demonstrate our superior performance and clinical potential.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ultrasonography, PrenatalHeadImage Processing, Computer-AssistedFetusHumansAlgorithmsFemalePregnancy

Stichwörter der Autor:innen

foetal head segmentationsemi‐supervised learningultrasound images

Autor:innen und Institutionen

  • Department of Aristogenesis, Department of Obstetrics and Gynecology, Women and Children's Hospital, School of Medicine, Xiamen University, Xiamen, Fujian, China.
  • School of Informatics, Xiamen University, Xiamen, Fujian, China.
  • School of Software, Northwestern Polytechnical University, Xi'an, Shaanxi, China.
  • Department of Ultrasound, Fujian Maternity and Child Health Hospital College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics, Fujian Medical University, Fuzhou, Fujian, China.

Förderung

  • Young Scientists Research Project of Xiamen Health and Wellness High-Quality Development Science and Technology Plan Program

Zitieren

APA

Zhu, B., Qu, L., Zhou, L., Luo, Z., & Chen, Y. (2026). MCPNet: Morphological Constraint‐Based Copy‐Paste Network for Semi‐Supervised Foetal Head Segmentation. The International Journal of Medical Robotics and Computer Assisted Surgery. https://doi.org/10.1002/rcs.70140

Vancouver

Zhu B, Qu L, Zhou L, Luo Z, Chen Y. MCPNet: Morphological Constraint‐Based Copy‐Paste Network for Semi‐Supervised Foetal Head Segmentation. The International Journal of Medical Robotics and Computer Assisted Surgery. 2026. doi:10.1002/rcs.70140

BibTeX
@article{Zhu2026,
  author = {Zhu, Baoping and Qu, Linjie and Zhou, Linkuan and Luo, Zhenyu and Chen, Yan},
  title = {MCPNet: Morphological Constraint‐Based Copy‐Paste Network for Semi‐Supervised Foetal Head Segmentation},
  journal = {The International Journal of Medical Robotics and Computer Assisted Surgery},
  year = {2026},
  doi = {10.1002/rcs.70140}
}
Kostenlos starten →