IRM-UNet: backbone-agnostic implicit refinement for enhanced pancreatic CT segmentation
Applied Intelligence · 2026-04 · 56 (5)
DOI: 10.1007/s10489-026-07162-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Intelligence, online erschienen am 17.03.2026. Verfasst von Chaohui Zhang und 1 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Universiti Sains Malaysia.
Abstract (Originalsprache)
Accurate pancreatic segmentation in computed tomography (CT) remains challenging due to irregular morphology, low contrast, and blurred boundaries. Most segmentation backbones produce discrete, fixed-grid voxel predictions, which can lead to coarse contours and limited representation of subtle, continuous anatomical deformations. To mitigate this limitation, IRM-UNet is introduced as a backbone-agnostic refinement framework that augments segmentation backbones with an implicit neural representation (INR) module for sub-voxel boundary refinement. The main innovations are as follows: (1) Continuous boundary reconstruction: modeling pancreatic morphology in a continuous domain via an INR enables accurate delineation of complex boundaries; (2) Multi-scale feature fusion and uncertainty-aware sampling: multi-scale feature integration with uncertainty-aware sampling concentrates refinement on low-contrast and ambiguous regions, improving robustness; and (3) High-frequency detail enhancement: combining positional encoding with Fourier feature mapping projects low-dimensional coordinates into a higher-dimensional space, facilitating the representation of high-frequency boundary details. Experiments on the NIH pancreatic CT dataset yield a Dice coefficient of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$89.87 \pm 1.82\%$$\end{document} and a Jaccard index of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$81.60 \pm 1.65\%$$\end{document}. Additional experiments indicate that the implicit refinement module functions as a plug-and-play component across different backbones and is associated with improved boundary quality.
Förderung
- Universiti Sains Malaysia
Zitieren
APA
Zhang, C., & Achuthan, A. (2026). IRM-UNet: backbone-agnostic implicit refinement for enhanced pancreatic CT segmentation. Applied Intelligence, 56(5). https://doi.org/10.1007/s10489-026-07162-9
Vancouver
Zhang C, Achuthan A. IRM-UNet: backbone-agnostic implicit refinement for enhanced pancreatic CT segmentation. Applied Intelligence. 2026;56(5). doi:10.1007/s10489-026-07162-9
BibTeX
@article{Zhang2026,
author = {Zhang, Chaohui and Achuthan, Anusha},
title = {IRM-UNet: backbone-agnostic implicit refinement for enhanced pancreatic CT segmentation},
journal = {Applied Intelligence},
year = {2026},
volume = {56},
number = {5},
doi = {10.1007/s10489-026-07162-9}
}
EUVIMED