A multi-stage training and deep supervision based segmentation approach for 3D abdominal multi-organ segmentation.

Journal: Journal of X-ray science and technology
Published Date: Jul 17, 2025

Abstract

Accurate X-ray Computed tomography (CT) image segmentation of the abdominal organs is fundamental for diagnosing abdominal diseases, planning cancer treatment, and formulating radiotherapy strategies. However, the existing deep learning based models for three-dimensional (3D) CT image abdominal multi-organ segmentation face challenges, including complex organ distribution, scarcity of labeled data, and diversity of organ structures, leading to difficulties in model training and convergence and low segmentation accuracy. To address these issues, a novel multi-stage training and a deep supervision model based segmentation approach is proposed. It primary integrates multi-stage training, pseudo- labeling technique, and a developed deep supervision model with attention mechanism (DLAU-Net), specifically designed for 3D abdominal multi-organ segmentation. The DLAU-Net enhances segmentation performance and model adaptability through an improved network architecture. The multi-stage training strategy accelerates model convergence and enhances generalizability, effectively addressing the diversity of abdominal organ structures. The introduction of pseudo-labeling training alleviates the bottleneck of labeled data scarcity and further improves the model's generalization performance and training efficiency. Experiments were conducted on a large dataset provided by the FLARE 2023 Challenge. Comprehensive ablation studies and comparative experiments were conducted to validate the effectiveness of the proposed method. Our method achieves an average organ accuracy (AVG) of 90.5% and a Dice Similarity Coefficient (DSC) of 89.05% and exhibits exceptional performance in terms of training speed and handling data diversity, particularly in the segmentation tasks of critical abdominal organs such as the liver, spleen, and kidneys, significantly outperforming existing comparative methods.

Authors

  • Panpan Wu
    College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China.
  • Peng An
    Department of Radiology, Xiangyang NO.1 People's Hospital Affiliated to Hubei University of Medicine Xiangyang, Hubei, China.
  • Ziping Zhao
    College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China.
  • Runpeng Guo
    College of Computer and Information Engineering, Tianjin Normal University, Tianjin, 300387, China.
  • Xiaofeng Ma
    School of Computer Science & Technology, Anhui University of Technology, Ma'anshan, 243032, Anhui, China.
  • Yue Qu
    Dalian University of Technology, Dalian, China.
  • Yurou Xu
    College of Computer and Information Engineering, Tianjin Normal University, Tianjin, 300387, China.
  • Hengyong Yu
    Department of Electrical and Computer Engineering, University of Masachusetts Lowell, Lowell, MA 01854, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals