Back to all papers

Learning the anatomical topology consistency driven by Wasserstein distance for weakly supervised 3D pancreas registration in multi-phase CT images.

January 16, 2026pubmed logopapers

Authors

Lin J,Zou L,Gao Y,Mao L,Nie Z

Affiliations (4)

  • School of Mathematics, Nanjing University of Aeronautics and Astronautics, No.29, Jiangjun Road, Jiangning District, Nanjing, Jiangsu, 210016, CHINA.
  • School of Mathematics, Nanjing University, Gulou Campus, Nanjing University, Hankou Road 22, Gulou District, Nanjing, Jiangsu Province, China, Nanjing, Jiangsu, 210093, CHINA.
  • Nanjing Drum Tower Hospital, Department of Pancreatic and Metabolic Surgery, Nanjing, Jiangsu, 210008, CHINA.
  • School of Mathematics, Nanjing University, Gulou Campus, Nanjing University, Hankou Road 22, Gulou District, Nanjing, Jiangsu Province, China, Nanjing, 210093, CHINA.

Abstract

Accurate and automatic registration of the pancreas between contrast-enhanced CT (CECT) and non-contrast CT (NCCT) images is crucial for diagnosing and treating pancreatic cancer. However, existing deep learning-based methods remain limited due to inherent intensity differences between modalities, which impair intensity-based similarity metrics, and the pancreas's small size, vague boundaries, and complex surroundings, which trap segmentation-based metrics in local optima. To address these challenges, we propose a weakly supervised registration framework incorporating a novel mixed loss function. This loss leverages Wasserstein distance to enforce anatomical topology consistency in 3D pancreas registration between CECT and NCCT. We employ distance transforms to build the small, uncertain and complex anatomical topology distribution of the pancreas. Unlike conventional voxel-wise L1 or L2 loss, the Wasserstein distance directly measures the similarity between warped and fixed anatomical topologies of pancreas. Experiments on a dataset of 975 paired CECT-NCCT images from patients with seven pancreatic tumor types (PDAC, IPMN, MCN, SCN, SPT, CP, PNET), demonstrate that our method outperforms state-of-the-art weakly supervised approaches, achieving improvements of 3.2% in Dice score, reductions of 28.54% in false positive segmentation rate with 0.89% in Hausdorff distance. The source code will be made publicly available at https://github.com/ZouLiwen-1999/WSMorph.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 8,400+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.