EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MDAU-Net: A Liver and Liver Tumor Segmentation Method Combining an Attention Mechanism and Multi-Scale Features

Jinlin Ma, Mingge Xia, Ziping Ma, Zhiqing Jiu

Applied Sciences · 18.09.2023 · 13 (18) · 10443

DOI: 10.3390/app131810443 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 18.09.2023. Verfasst von Jinlin Ma und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Ningxia, Basic Scientific Research in the Central Universities of North Minzu University, Graduate Innovation Project of North Minzu University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, U-Net and its extended variants have made remarkable progress in the realm of liver and liver tumor segmentation. However, the limitations of single-path convolutional operations have hindered the full exploitation of valuable features and restricted their mobility within networks. Moreover, the semantic gap between shallow and deep features proves that a simplistic shortcut is not enough. To address these issues and realize automatic liver and tumor area segmentation in CT images, we introduced the multi-scale feature fusion with dense connections and an attention mechanism segmentation method (MDAU-Net). This network leverages the multi-head attention (MHA) mechanism and multi-scale feature fusion. First, we introduced a double-flow linear pooling enhancement unit to optimize the fusion of deep and shallow features while mitigating the semantic gap between them. Subsequently, we proposed a cascaded adaptive feature extraction unit, combining attention mechanisms with a series of dense connections to capture valuable information and encourage feature reuse. Additionally, we designed a cross-level information interaction mechanism utilizing bidirectional residual connections to address the issue of forgetting a priori knowledge during training. Finally, we assessed MDAU-Net’s performance on the LiTS and SLiver07 datasets. The experimental results demonstrated that MDAU-Net is well-suited for liver and tumor segmentation tasks, outperforming existing widely used methods in terms of robustness and accuracy.

Förderung

  • Natural Science Foundation of Ningxia
  • Basic Scientific Research in the Central Universities of North Minzu University
  • Graduate Innovation Project of North Minzu University
  • Image and Intelligent Information Processing Innovation Team of the National Ethnic Affairs Commission

Zitieren

APA

Ma, J., Xia, M., Ma, Z., & Jiu, Z. (2023). MDAU-Net: A Liver and Liver Tumor Segmentation Method Combining an Attention Mechanism and Multi-Scale Features. Applied Sciences, 13(18), 10443. https://doi.org/10.3390/app131810443

Vancouver

Ma J, Xia M, Ma Z, Jiu Z. MDAU-Net: A Liver and Liver Tumor Segmentation Method Combining an Attention Mechanism and Multi-Scale Features. Applied Sciences. 2023;13(18):10443. doi:10.3390/app131810443

BibTeX
@article{Ma2023,
  author = {Ma, Jinlin and Xia, Mingge and Ma, Ziping and Jiu, Zhiqing},
  title = {MDAU-Net: A Liver and Liver Tumor Segmentation Method Combining an Attention Mechanism and Multi-Scale Features},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {18},
  pages = {10443},
  doi = {10.3390/app131810443}
}
Kostenlos starten →