LA-ResUNet: Attention-based network for longitudinal liver tumor segmentation from CT images.

in Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society by Ri Jin, Hu-Ying Tang, Qian Yang, Wei Chen

TLDR

  • A novel strategy for longitudinal liver tumor segmentation is proposed, utilizing images from multiple time points to improve segmentation performance, and achieved effective and accurate segmentation results.

Abstract

Longitudinal liver tumor segmentation plays a fundamental role in studying and monitoring the progression of associated diseases. The correlation and differences between longitudinal data can further improve segmentation performance, which are inevitably omitted in single-time-point segmentation. However, there is no research in this field due to the lack of relevant data. To this issue, we collect and annotate the first longitudinal liver tumor segmentation benchmark dataset. A novel strategy that utilizes images from one time point to facilitate the image segmentation from another time point of the same patient is presented. On this basis, we propose a longitudinal attention based residual U-shaped network. Within it, a channel & spatial attention module quantifies both channel-wise and spatial-wise dependencies of each feature to refine feature representations. And a longitudinal co-segmentation module captures cross-temporal correlation to recalibrate the feature at one time point according to another one for enhanced segmentation. Longitudinal segmentation is achieved by plugging these two multi-scale modules into each layer of the backbone network. Extensive experiments on our CT liver tumor dataset and an MRI brain tumor dataset have validated the effectiveness of the established strategy and the longitudinal segmentation ability of our network. Ablation studies have verified the functions of the proposed modules and their respective components.

Overview

  • The study focuses on developing a longitudinal liver tumor segmentation method, utilizing images from multiple time points to improve segmentation performance.
  • A novel strategy is proposed to utilize images from one time point to facilitate image segmentation from another time point of the same patient
  • The primary objective is to propose a longitudinal attention-based residual U-shaped network that can effectively and accurately segment liver tumors in longitudinal datasets

Comparative Analysis & Findings

  • The proposed strategy and network demonstrate effective and accurate segmentation of liver tumors in longitudinal datasets
  • Experimental results show the superiority of the proposed strategy in terms of segmentation accuracy and cross-temporal correlation
  • Ablation studies have validated the functions of the proposed modules and their respective components

Implications and Future Directions

  • The proposed strategy and network have significant implications for longitudinal liver tumor segmentation tasks and may be applicable to other medical image segmentation tasks
  • Future studies may investigate the use of additional data, such as clinical information or other modalities, to further enhance the segmentation performance
  • The proposed strategy may be extended to other medical image segmentation tasks, such as brain tumor segmentation, to improve their segmentation accuracy
Read Full Article