EPT-Net: Edge Perception Transformer for 3D Medical Image Segmentation

Yang, Jingyi; Jiao, Licheng; Shang, Ronghua; Liu, Xu; Li, R; Xu, Luping

doi:10.1109/tmi.2023.3278461

Cited by 6 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model obtained good DSC for kidney segmentation (Kidney: 94.3%, Tumor:77.79%, Cyst:70.99%), but the network approach can be improved for segmenting smaller kidneys, tumors, and cysts. To enhance the spatial modeling capability of the network while maintaining the efficient use of computational resources, Yang et al [ 62 ] proposed that the EPT-Net network effectively combines the edge sensing and Transformer structures and introduces the Dual Position Transformer to enhance 3D spatial localization capability. Meanwhile, the Edge Weight Guidance module extracts edge information without additional network parameters.…”

Section: Application Of Transformer In Renal Image Processingmentioning

confidence: 99%

Application of visual transformer in renal image analysis

Yin,

Tang,

Weng

2024

BioMed Eng OnLine

View full text Add to dashboard Cite

Deep Self-Attention Network (Transformer) is an encoder–decoder architectural model that excels in establishing long-distance dependencies and is first applied in natural language processing. Due to its complementary nature with the inductive bias of convolutional neural network (CNN), Transformer has been gradually applied to medical image processing, including kidney image processing. It has become a hot research topic in recent years. To further explore new ideas and directions in the field of renal image processing, this paper outlines the characteristics of the Transformer network model and summarizes the application of the Transformer-based model in renal image segmentation, classification, detection, electronic medical records, and decision-making systems, and compared with CNN-based renal image processing algorithm, analyzing the advantages and disadvantages of this technique in renal image processing. In addition, this paper gives an outlook on the development trend of Transformer in renal image processing, which provides a valuable reference for a lot of renal image analysis.

show abstract

Section: Application Of Transformer In Renal Image Processingmentioning

confidence: 99%

Application of visual transformer in renal image analysis

Yin,

Tang,

Weng

2024

BioMed Eng OnLine

View full text Add to dashboard Cite

show abstract

“…PSPNet 3 proposed a pyramid pooling module based on the encoder-decoder structure, which can realize multi-scale information fusion and help the model obtain richer global context information. Recently, some literatures 7,8 have used Transformer to model long-range dependencies, but they require large amounts of training data and significant computational resources due to the large number of query operations, which limits their practical application in clinical settings. Zhu et al 9 proposed a lightweight 3D segmentation network, SV-net, which replaces the convolutional blocks in V-Net with lightweight convolutional blocks, significantly speeding up the training process.…”

mentioning

confidence: 99%

UNet based on dynamic convolution decomposition and triplet attention

Li,

Yan,

Hou

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The robustness and generalization of medical image segmentation models are being challenged by the differences between different disease types, different image types, and different cases.Deep learning based semantic segmentation methods have been providing state-of-the-art performance in the last few years. One deep learning technique, U-Net, has become the most popular architecture in the medical imaging segmentation. Despite outstanding overall performance in segmenting medical images, it still has the problems of limited feature expression ability and inaccurate segmentation. To this end, we propose a DTA-UNet based on Dynamic Convolution Decomposition (DCD) and Triple Attention (TA). Firstly, the model with Attention U-Net as the baseline network uses DCD to replace all the conventional convolution in the encoding-decoding process to enhance its feature extraction capability. Secondly, we combine TA with Attention Gate (AG) to be used for skip connection in order to highlight lesion regions by removing redundant information in both spatial and channel dimensions. The proposed model are tested on the two public datasets and actual clinical dataset such as the public COVID-SemiSeg dataset, the ISIC 2018 dataset, and the cooperative hospital stroke segmentation dataset. Ablation experiments on the clinical stroke segmentation dataset show the effectiveness of DCD and TA with only a 0.7628 M increase in the number of parameters compared to the baseline model. The proposed DTA-UNet is further evaluated on the three datasets of different types of images to verify its universality. Extensive experimental results show superior performance on different segmentation metrics compared to eight state-of-art methods.The GitHub URL of our code is https://github.com/shuaihou1234/DTA-UNet.

show abstract