DAC-Net: A light-weight U-shaped network based efficient convolution and attention for thyroid nodule segmentation

Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Soph...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers in biology and medicine Jg. 180; S. 108972
Hauptverfasser: Yang, Yingwei, Huang, Haiguang, Shao, Yingsheng, Chen, Beilei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Elsevier Ltd 01.09.2024
Elsevier Limited
Schlagworte:
Algorithms
Attention mechanism
Clinical medicine
Complexity
Computation
Convolution
Deep learning
Design parameters
Feature extraction
Feature maps
Humans
Image Interpretation, Computer-Assisted - methods
Information processing
Internal Medicine
Light-weight model
Modules
Neural Networks, Computer
Nodules
Other
Segmentation
Source code
Thyroid
Thyroid gland
Thyroid Nodule - diagnostic imaging
Thyroid nodule segmentation
U-shaped network
Weight reduction
Light-weight model
Deep learning
Attention mechanism
Convolution
Thyroid nodule segmentation
U-shaped network
ISSN:0010-4825, 1879-0534, 1879-0534
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Sophisticated models have difficulties in being implemented in clinical medicine platforms because of limited resources. DAC-Net is a Lightweight U-shaped network created to achieve high performance in segmenting thyroid nodules. Our method consists of three main components: DWSE, which combines depthwise convolution and squeeze-excitation block to enhance feature extraction and connections between samples; ADA, which includes Split Atrous and Dual Attention to extract global and local feature information from various viewpoints; and CSSC, which involves channel- scale and spatial-scale connections. This module enables the fusing of multi-stage features at global and local levels, producing feature maps at different channel and geographical scales, delivering a streamlined integration of multi-scale information. Combining these three components in our U- shaped design allows us to achieve competitive performance while also decreasing the number of parameters and computing complexity. Several experiments were conducted on the DDTI and TN3K datasets. The experimental results demonstrate that our model outperforms state-of-the-art thyroid nodule segmentation architectures in terms of segmentation performance. Our model not only reduces the number of parameters and computing expenses by 73x and 56x, respectively, but also exceeds TransUNet in segmentation performance. The source code is accessible at https://github.com/Phil-y/DAC-Net. •The paper provides open-source project code and utilizes public datasets, engaging hospitals, which notably enhance the credibility of the experimental results.•The experimental design not only focuses on performance optimization, but also successfully reduces the number of model parameters and computational complexity, contributing to the model’s practical application significance.•The experimental protocol demonstrates a comprehensive approach, including comparative experiments, qualitative analyses, ROC curve comparisons, ablation experiments, and analyses of hyperparameters. Various metrics were used, ensuring the experiments’ thoroughness and reliability.•The article is well structured and the diagrams are beautifully drawn.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0010-4825
1879-0534
1879-0534
DOI:10.1016/j.compbiomed.2024.108972