HEDN: multi-oriented hierarchical extraction and dual-frequency decoupling network for 3D medical image segmentation

Previous 3D encoder-decoder segmentation architectures struggled with fine-grained feature decomposition, resulting in unclear feature hierarchies when fused across layers. Furthermore, the blurred nature of contour boundaries in medical imaging limits the focus on high-frequency contour features. T...

Full description

Saved in:
Bibliographic Details
Published in:Medical & biological engineering & computing Vol. 63; no. 1; pp. 267 - 291
Main Authors: Wang, Yu, Huang, Guoheng, Lu, Zeng, Wang, Ying, Chen, Xuhang, Yuan, Xiaochen, Li, Yan, Liu, Jieni, Huang, Yingping
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.01.2025
Springer Nature B.V
Subjects:
Algorithms
Biomedical and Life Sciences
Biomedical engineering
Biomedical Engineering and Bioengineering
Biomedicine
Computer Applications
Contours
data collection
Datasets
Decoding
Decomposition
Decoupling
Encoders-Decoders
Feature decomposition
Hierarchies
Human Physiology
Humans
image analysis
Image processing
Image Processing, Computer-Assisted - methods
Image segmentation
Imaging
Imaging, Three-Dimensional - methods
Medical imaging
Metric space
Modules
Neural Networks, Computer
Original Article
Radiology
synapse
3D medical image segmentation
Encoder-decoder architecture
Dual-frequency decoupling
Multi-oriented hierarchical extraction
ISSN:0140-0118, 1741-0444, 1741-0444
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Previous 3D encoder-decoder segmentation architectures struggled with fine-grained feature decomposition, resulting in unclear feature hierarchies when fused across layers. Furthermore, the blurred nature of contour boundaries in medical imaging limits the focus on high-frequency contour features. To address these challenges, we propose a Multi-oriented Hierarchical Extraction and Dual-frequency Decoupling Network (HEDN), which consists of three modules: Encoder-Decoder Module (E-DM), Multi-oriented Hierarchical Extraction Module (Multi-HEM), and Dual-frequency Decoupling Module (Dual-DM). The E-DM performs the basic encoding and decoding tasks, while Multi-HEM decomposes and fuses spatial and slice-level features in 3D, enriching the feature hierarchy by weighting them through 3D fusion. Dual-DM separates high-frequency features from the reconstructed network using self-supervision. Finally, the self-supervised high-frequency features separated by Dual-DM are inserted into the process following Multi-HEM, enhancing interactions and complementarities between contour features and hierarchical features, thereby mutually reinforcing both aspects. On the Synapse dataset, HEDN outperforms existing methods, boosting Dice Similarity Score (DSC) by 1.38% and decreasing 95% Hausdorff Distance (HD95) by 1.03 mm. Likewise, on the Automatic Cardiac Diagnosis Challenge (ACDC) dataset, HEDN achieves  0.5% performance gains across all categories. Graphical abstract
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0140-0118
1741-0444
1741-0444
DOI:10.1007/s11517-024-03192-y