Densely Connected U-Net With Criss-Cross Attention for Automatic Liver Tumor Segmentation in CT Images

Qiang Li, Hong Song*, Zenghui Wei, Fengbo Yang, Jingfan Fan*, Danni Ai, Yucong Lin, Xiaoling Yu*, Jian Yang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

Automatic liver tumor segmentation plays a key role in radiation therapy of hepatocellular carcinoma. In this paper, we propose a novel densely connected U-Net model with criss-cross attention (CC-DenseUNet) to segment liver tumors in computed tomography (CT) images. The dense interconnections in CC-DenseUNet ensure the maximum information flow between encoder layers when extracting intra-slice features of liver tumors. Moreover, the criss-cross attention is used in CC-DenseUNet to efficiently capture only the necessary and meaningful non-local contextual information of CT images containing liver tumors. We evaluated the proposed CC-DenseUNet on the LiTS dataset and the 3DIRCADb dataset. Experimental results show that the proposed method reaches the state-of-the-art performance for liver tumor segmentation. We further experimentally demonstrate the robustness of the proposed method on a clinical dataset comprising 20 CT volumes.

Original languageEnglish
Pages (from-to)3399-3410
Number of pages12
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume20
Issue number6
DOIs
Publication statusPublished - 1 Nov 2023

Keywords

  • CT images
  • Dense interconnection
  • U-Net
  • criss-cross attention
  • liver tumor segmentation

Fingerprint

Dive into the research topics of 'Densely Connected U-Net With Criss-Cross Attention for Automatic Liver Tumor Segmentation in CT Images'. Together they form a unique fingerprint.

Cite this