EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Kidney Tumor Image Segmentation Algorithm based on Deep Learning

Jian Lin, Yan Chen

Frontiers in Computing and Intelligent Systems · 29.06.2026 · 17 (1) · 9-15

DOI: 10.54097/2h3wmj52 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Computing and Intelligent Systems, online erschienen am 29.06.2026. Verfasst von Jian Lin und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper focuses on the segmentation algorithm of kidney tumor image based on deep learning, expounds the research significance of the subject, combs the research status at home and abroad in this field, and defines the research methods and technical routes. In this paper, the overall design of the algorithm is completed, and the preprocessing work such as data collection and annotation of kidney tumor image is completed. On the basis of v-net neural network, the feature fusion module and dual attention mechanism are introduced to improve the segmentation model. By setting experimental parameters to carry out experiments, the segmentation effect of the model is analyzed from the qualitative and quantitative perspectives. This study can provide technical support for the clinical diagnosis of renal tumor, and provide reference for algorithm optimization in related fields.

Zitieren

APA

Lin, J., & Chen, Y. (2026). Kidney Tumor Image Segmentation Algorithm based on Deep Learning. Frontiers in Computing and Intelligent Systems, 17(1), 9-15. https://doi.org/10.54097/2h3wmj52

Vancouver

Lin J, Chen Y. Kidney Tumor Image Segmentation Algorithm based on Deep Learning. Frontiers in Computing and Intelligent Systems. 2026;17(1):9-15. doi:10.54097/2h3wmj52

BibTeX
@article{Lin2026,
  author = {Lin, Jian and Chen, Yan},
  title = {Kidney Tumor Image Segmentation Algorithm based on Deep Learning},
  journal = {Frontiers in Computing and Intelligent Systems},
  year = {2026},
  volume = {17},
  number = {1},
  pages = {9--15},
  doi = {10.54097/2h3wmj52}
}
Kostenlos starten →