View in EDS

MDMU-Net: 3D multi-dimensional decoupled multi-scale U-Net for pancreatic cancer segmentation

Saved in:
Bibliographic Details
Title: MDMU-Net: 3D multi-dimensional decoupled multi-scale U-Net for pancreatic cancer segmentation
Authors: Lian Lu, Miao Wu, Gan Sen, Fei Ren, Tao Hu
Source: PeerJ Computer Science, Vol 11, p e3059 (2025)
Publisher Information: PeerJ Inc., 2025.
Publication Year: 2025
Collection: LCC:Electronic computers. Computer science
Subject Terms: Pancreatic cancer segmentation, 3D segmentation, Multi-dimensional decoupling and multi-scale, Medical image segmentation, Pancreatic segmentation, Electronic computers. Computer science, QA75.5-76.95
Description: Pancreatic cancer, as a highly lethal malignant tumor, presents significant challenges for early diagnosis and treatment. Accurate segmentation of the pancreas and tumors is crucial for surgical planning and treatment strategy development. However, due to the variable morphology, blurred boundaries, and low contrast with surrounding tissues in CT images, traditional manual segmentation methods are inefficient and heavily reliant on expert experience. To address this challenge, this study proposes a lightweight automated 3D segmentation algorithm—Multi-Dimensional Decoupled Multi-Scale U-Net (MDMU-Net). First, depthwise separable convolution is employed to reduce model complexity. Second, a multi-dimensional decoupled multi-scale module is designed as the primary encoder module, which independently extracts features along depth, height, and width dimensions through parallel multi-scale convolutional kernels, achieving fine-grained modeling of complex anatomical structures. Finally, cross-dimensional channel and spatial attention mechanisms are introduced to enhance recognition capability for small tumors and blurred boundaries. Experimental results on the MSDPT and NIHP datasets demonstrate that MDMU-Net exhibits competitive advantages in both pancreatic segmentation DSC (0.7108/0.7709) and tumor segmentation DSC (showing an 11.8% improvement over AttentionUNet), while achieving a 15.3% enhancement in HD95 boundary accuracy compared to 3DUX-Net. While maintaining clinically viable precision, the model significantly improves computational efficiency, with parameter count (26.97M) and FLOPs (84.837G) reduced by 65.5% and 71%, respectively, compared to UNETR, providing reliable algorithmic support for precise diagnosis and treatment of pancreatic cancer.
Document Type: article
File Description: electronic resource
Language: English
ISSN: 2376-5992
Relation: https://peerj.com/articles/cs-3059.pdf; https://peerj.com/articles/cs-3059/; https://doaj.org/toc/2376-5992
DOI: 10.7717/peerj-cs.3059
Access URL: https://doaj.org/article/4971d0383dc94d54b8ce96b2ffea5ad6
Accession Number: edsdoj.4971d0383dc94d54b8ce96b2ffea5ad6
Database: Directory of Open Access Journals
Description
Abstract:Pancreatic cancer, as a highly lethal malignant tumor, presents significant challenges for early diagnosis and treatment. Accurate segmentation of the pancreas and tumors is crucial for surgical planning and treatment strategy development. However, due to the variable morphology, blurred boundaries, and low contrast with surrounding tissues in CT images, traditional manual segmentation methods are inefficient and heavily reliant on expert experience. To address this challenge, this study proposes a lightweight automated 3D segmentation algorithm—Multi-Dimensional Decoupled Multi-Scale U-Net (MDMU-Net). First, depthwise separable convolution is employed to reduce model complexity. Second, a multi-dimensional decoupled multi-scale module is designed as the primary encoder module, which independently extracts features along depth, height, and width dimensions through parallel multi-scale convolutional kernels, achieving fine-grained modeling of complex anatomical structures. Finally, cross-dimensional channel and spatial attention mechanisms are introduced to enhance recognition capability for small tumors and blurred boundaries. Experimental results on the MSDPT and NIHP datasets demonstrate that MDMU-Net exhibits competitive advantages in both pancreatic segmentation DSC (0.7108/0.7709) and tumor segmentation DSC (showing an 11.8% improvement over AttentionUNet), while achieving a 15.3% enhancement in HD95 boundary accuracy compared to 3DUX-Net. While maintaining clinically viable precision, the model significantly improves computational efficiency, with parameter count (26.97M) and FLOPs (84.837G) reduced by 65.5% and 71%, respectively, compared to UNETR, providing reliable algorithmic support for precise diagnosis and treatment of pancreatic cancer.
ISSN:23765992
DOI:10.7717/peerj-cs.3059