EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

DSA‐Former: A Network of Hybrid Variable Structures for Liver and Liver Tumour Segmentation

Jun Qin, Huizhen Luo iD, Fei He, Guihe Qin

The International Journal of Medical Robotics and Computer Assisted Surgery · 2024

DOI: 10.1002/rcs.70004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Medical Robotics and Computer Assisted Surgery, 2024. Verfasst von Jun Qin und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China. Hauptthemen laut MEDLINE: Liver Neoplasms, Tomography, X-Ray Computed, Liver, Algorithms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Science Foundation of Jilin Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurately annotated CT images of liver tumours can effectively assist doctors in diagnosing and treating liver cancer. However, due to the relatively low density of the liver, its tumours, and surrounding tissues, as well as the existence of multi‐scale problems, accurate automatic segmentation still faces challenges.

Methods

We propose a segmentation network DSA‐Former that combines convolutional kernels and attention. By combining the morphological and edge features of liver tumour images, capture global/local features and key inter‐layer information, and integrate attention mechanisms obtaining detailed information to improve segmentation accuracy.

Results

Compared to other methods, our approach demonstrates significant advantages in evaluation metrics such as the Dice coefficient, IOU, VOE, and HD95. Specifically, we achieve Dice coefficients of 96.8% for liver segmentation and 72.2% for liver tumour segmentation.

Conclusion

Our method offers enhanced precision in segmenting liver and liver tumour images, laying a robust foundation for liver cancer diagnosis and treatment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Liver NeoplasmsTomography, X-Ray ComputedLiverAlgorithmsHumansImage Processing, Computer-AssistedNeural Networks, ComputerReproducibility of ResultsDeep Learning

Stichwörter der Autor:innen

automatic segmentationinter‐layer informationliver and liver tumourliver cancer

Autor:innen und Institutionen

  • School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China.
  • School of Computer Science and Technology, Jilin University, Changchun, China.

ORCID-Profile: Huizhen Luo

Förderung

  • Natural Science Foundation of Jilin Province

Zitieren

APA

Qin, J., Luo, H., He, F., & Qin, G. (2024). DSA‐Former: A Network of Hybrid Variable Structures for Liver and Liver Tumour Segmentation. The International Journal of Medical Robotics and Computer Assisted Surgery. https://doi.org/10.1002/rcs.70004

Vancouver

Qin J, Luo H, He F, Qin G. DSA‐Former: A Network of Hybrid Variable Structures for Liver and Liver Tumour Segmentation. The International Journal of Medical Robotics and Computer Assisted Surgery. 2024. doi:10.1002/rcs.70004

BibTeX
@article{Qin2024,
  author = {Qin, Jun and Luo, Huizhen and He, Fei and Qin, Guihe},
  title = {DSA‐Former: A Network of Hybrid Variable Structures for Liver and Liver Tumour Segmentation},
  journal = {The International Journal of Medical Robotics and Computer Assisted Surgery},
  year = {2024},
  doi = {10.1002/rcs.70004}
}
Kostenlos starten →