What type of study is this?

This is a In Vitro Study study.

August 16, 2025PeerJ Computer ScienceOpen Access

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

View Full Paper

Ask AI

Bookmark

Authors

LLLu LianXinjiang Medical University MWMiao WuXinjiang Medical University GSGan SenXinjiang Medical University

Discussion

Member takes

Implication

This analysis demonstrates improved pancreatic cancer segmentation performance using 3D U-Net and multi-scale techniques, indicating enhanced diagnostic support.

Key Points

MDMU-Net achieves a significant improvement in pancreatic segmentation DSC by 11.8% over prior models.
Experimental results show competitive DSC scores of 0.7108 for pancreas and 0.7709 for tumor segmentation on two datasets.
Design features include depthwise separable convolution and multi-dimensional decoupled modules to enhance segmentation accuracy.
Clinical applicability is supported by reduced parameter count and computational efficiency compared to existing methods.

Cite This Study

Lian et al. (2025) studied this question.

synapsesocial.com/papers/68a366b20a429f797332cef3 https://doi.org/10.7717/peerj-cs.3059

View Full Paper

Ask AI

Bookmark

Implication

This analysis demonstrates improved pancreatic cancer segmentation performance using 3D U-Net and multi-scale techniques, indicating enhanced diagnostic support.

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

Discussion

Member takes

Implication

Key Points

Cite This Study

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

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider