MSA-Net: Multiscale spatial attention network for medical image segmentation

Fu, Zhaojin; Li, Jinjiang; Hua, Zhen

doi:10.1016/j.aej.2023.02.039

Cited by 14 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detailed structure of attention calculation and MLP is shown in Figure 3. .12], [13], [14], attention is calculated by the following formula…”

Section: Attention Connection Modulementioning

confidence: 99%

Pathological image segmentation of gastric cancer based on deep learning

Zhou,

Pan,

et al. 2024

Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023)

View full text Add to dashboard Cite

Gastric cancer is a serious health threat and pathological images are an important criterion in its diagnosis. These images can help doctors accurately identify cancerous regions and provide important evidence for clinical decisionmaking. Thanks to the remarkable achievements of deep learning technology in the field of image processing, an increasing number of superior image segmentation models have emerged. The Swin-Unet model has achieved great success in the field of image segmentation. However, when applied to the image segmentation of gastric cancer pathological section data, the segmentation boundary appears jagged. We have put forth two potential solutions. Initially, we devised an attention connection module to supplant the skip connections within the model, thereby enhancing the model's predictive precision. Subsequently, we engineered a prognostic processing unit that inputs the model's predictive outcomes and employs a Conditional Random Field (CRF) for further predictive computations. The enhanced model increases the DSC by 2% and decreases the HD by 17%. Additionally, the issue of jagged boundaries in prediction results has been better optimized. We conducted comparative and ablation experiments, and the results showed that our improved method increased the accuracy of the model's predictions and reduced the jaggedness of the results at the boundary.

show abstract

“…The detailed structure of attention calculation and MLP is shown in Figure 3. .12], [13], [14], attention is calculated by the following formula…”

Section: Attention Connection Modulementioning

confidence: 99%

Pathological image segmentation of gastric cancer based on deep learning

Zhou,

Pan,

et al. 2024

Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023)

View full text Add to dashboard Cite

show abstract

“…As Transformers continue to perform well in computer vision, an increasing number of medical image segmentation studies are adopting self‐attention mechanisms to address related issues 11–18 . These methods mainly focus on fusing self‐attention mechanisms and convolutional operations to improve the accuracy and efficiency of medical image segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…As Transformers continue to perform well in computer vision, an increasing number of medical image segmentation studies are adopting self-attention mechanisms to address related issues. [11][12][13][14][15][16][17][18] These methods mainly focus on fusing self-attention mechanisms and convolutional operations to improve the accuracy and efficiency of medical image segmentation. The self-attention mechanism is one of the most critical components in the Transformer, which can better capture long-distance dependency relationships.…”

mentioning

confidence: 99%

Dynamic weight HiLo attention network for medical image multiple organ segmentation

Zhao,

Li,

Liu

2023

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

In recent years, there has been a surge of research in the field of medical image segmentation using hybrid CNN‐Transformer network architectures. Most of these studies leverage the attention mechanism of ViT to overcome the limitations of CNN architectures in capturing long‐range dependencies. However, these hybrid model approaches also have some potential drawbacks. First, due to the heavy reliance of the Transformer's attention mechanism on global information, it can lead to a significant increase in computational cost when dealing with high‐resolution input images. Furthermore, the convolutional and attention mechanisms in hybrid models have different interpretability in information extraction and decision‐making, which poses a challenge for the interpretability of the convolutional part. Our proposed model, DWHA, addresses these limitations and outperforms state‐of‐the‐art models in a range of medical image segmentation tasks, such as abdominal multiorgan segmentation, automatic cardiac diagnosis, neurostructure segmentation, and skin lesion segmentation, achieving significantly superior performance. Specifically, on the abdominal multiorgan segmentation dataset, DWHA outperformed the previous state‐of‐the‐art baseline by 0.57%; on the neurostructure segmentation dataset, it achieved an improvement of 1.17%; and on the skin lesion segmentation dataset, it achieved an improvement of 0.91%. These significant improvements suggest that DWHA may become the preferred model in the field of medical image segmentation.

show abstract

“…Currently, the concept of visual spatial attention mechanism is applied in medical image analysis to detect representative features from images with multiple lesions, noise, and artifacts [23], [24]. By aggregating different levels of features, the attention model shows strong capability for disease classification.…”

Section: Introductionmentioning

confidence: 99%

Dual-Path and Multi-Scale Enhanced Attention Network for Retinal Diseases Classification Using Ultra-Wide-Field Images

Chen

Hao

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Early computer-aided early diagnosis (CAD) based on retinal imaging is critical to the timely management and treatment planning of retina-related diseases. However, the inherent characteristics of retinal images and the complexity of their pathological patterns, such as low image contrast and different lesion sizes, restrict the performance of CAD systems. Recently, ultra-wide-field (UWF) retinal images have become a useful tool for disease detection due to the capability of capturing much broader view of retina (i.e., up to 200 • ), in comparison with the most commonly used retinal fundus images (45 • ). In this paper, we propose an attention-based multi-branch network for the diseases classification of four different subject groups. The proposed method consists of a multi-scale feature fusion module and a dual attention module. Specifically, small-scale lesions are identified using the features extracted from the multi-scale feature fusion module. To better explore the obtained features, the dual attention module with a global attention graph is incorporated to enable the network to recognize the salient objects of interest. Comprehensive validations on both private and public datasets were carried out to verify the effectiveness of the proposed model.

show abstract

MSA-Net: Multiscale spatial attention network for medical image segmentation

Cited by 14 publications

References 37 publications

Pathological image segmentation of gastric cancer based on deep learning

Pathological image segmentation of gastric cancer based on deep learning

Dynamic weight HiLo attention network for medical image multiple organ segmentation

Dual-Path and Multi-Scale Enhanced Attention Network for Retinal Diseases Classification Using Ultra-Wide-Field Images

Contact Info

Product

Resources

About