Cross-convolutional transformer for automated multi-organs segmentation in a variety of medical images

Wang, Jing; Zhao, Haiyue; Liang, Wei; Wang, Shuyu; Zhang, Yan

doi:10.1088/1361-6560/acb19a

Cited by 9 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the U-shaped model-based approach mentioned above, to enhance the Transformer network's ability in local feature extraction, Wang et al [ 41 ] proposed the use of a pyramid structure to construct multiscale representations and deal with multiscale variations, firstly, using a lightweight convolutional layer to extract the low-level features and reduce the amount of data, and then, using the Transformer block and the convolution block's mixture of Transformer blocks and Convolutional blocks to handle high-level features. Models with similar ideas include ECT-NAS [ 42 ], C2Former [ 43 ], CASTformer [ 44 ], etc. Niu et al [ 45 ] proposed a novel symmetric supervised network based on the traditional two-branch approach, which utilizes a symmetric supervisory mechanism to enhance the supervision of the network training and introduces a Transformer-based global feature alignment module to improve the global consistency between the two branches.…”

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

“…C 2 Former [22] presents a fresh perspective that stems from SwinUnet. Wang et al innovatively redesigned the cross-convolutional self-attention mechanism algorithm to model long-and short-distance dependencies, resulting in an improved understanding of semantic features.…”

Section: U-shaped Architectures With Transformers For Medical Image S...mentioning

confidence: 99%

CCTrans: Improving Medical Image Segmentation with Contoured Convolutional Transformer Network

Wang

Zhang

2023

Mathematics

View full text Add to dashboard Cite

Medical images contain complex information, and the automated analysis of medical images can greatly assist doctors in clinical decision making. Therefore, the automatic segmentation of medical images has become a hot research topic in recent years. In this study, a novel architecture called a contoured convolutional transformer (CCTrans) network is proposed to solve the segmentation problem. A dual convolutional transformer block and a contoured detection module are designed, which integrate local and global contexts to establish reliable relational connections. Multi-scale features are effectively utilized to enhance semantic feature understanding. The dice similarity coefficient (DSC) is employed to evaluate experimental performance. Two public datasets with two different modalities are chosen as the experimental datasets. Our proposed method achieved an average DSC of 83.97% on a synapse dataset (abdominal multi-organ CT) and 92.15% on an ACDC dataset (cardiac MRI). Especially for the segmentation of small and complex organs, our proposed model achieves better segmentation results than other advanced approaches. Our experiments demonstrate the effectiveness and robustness of the novel method and its potential for real-world applications. The proposed CCTrans network offers a universal solution with which to achieve precise medical image segmentation.

show abstract

“…Li et al [ 19 ] implemented IB-TransUNet, merging the Information Bottleneck and Transformer into the U-Net model, and in [ 20 ], they proposed the MultiIB-TransUNet architecture. Some more recent architectures include High Correlative Non-Local Network (HCNNet), Bilateral Segmentation Network (BiSeNet V3), Contoured Convolutional Transformer (CCTrans), Cross-Convolutional Transformer Network (C 2 Former), Double-stage Codec Attention Network (DSCA-Net), and Medical Vision Transformer (MedViT) [ 21 , 22 , 23 , 24 , 25 , 26 ]. Additionally, specific architectures have been designed for the processing of 3D medical images [ 27 ].…”

Section: Introductionmentioning

confidence: 99%

Improving Surgical Scene Semantic Segmentation through a Deep Learning Architecture with Attention to Class Imbalance

Urrea,

Garcia-Garcia,

Kern

2024

Biomedicines

View full text Add to dashboard Cite

This article addresses the semantic segmentation of laparoscopic surgery images, placing special emphasis on the segmentation of structures with a smaller number of observations. As a result of this study, adjustment parameters are proposed for deep neural network architectures, enabling a robust segmentation of all structures in the surgical scene. The U-Net architecture with five encoder–decoders (U-Net5ed), SegNet-VGG19, and DeepLabv3+ employing different backbones are implemented. Three main experiments are conducted, working with Rectified Linear Unit (ReLU), Gaussian Error Linear Unit (GELU), and Swish activation functions. The applied loss functions include Cross Entropy (CE), Focal Loss (FL), Tversky Loss (TL), Dice Loss (DiL), Cross Entropy Dice Loss (CEDL), and Cross Entropy Tversky Loss (CETL). The performance of Stochastic Gradient Descent with momentum (SGDM) and Adaptive Moment Estimation (Adam) optimizers is compared. It is qualitatively and quantitatively confirmed that DeepLabv3+ and U-Net5ed architectures yield the best results. The DeepLabv3+ architecture with the ResNet-50 backbone, Swish activation function, and CETL loss function reports a Mean Accuracy (MAcc) of 0.976 and Mean Intersection over Union (MIoU) of 0.977. The semantic segmentation of structures with a smaller number of observations, such as the hepatic vein, cystic duct, Liver Ligament, and blood, verifies that the obtained results are very competitive and promising compared to the consulted literature. The proposed selected parameters were validated in the YOLOv9 architecture, which showed an improvement in semantic segmentation compared to the results obtained with the original architecture.

show abstract

Cross-convolutional transformer for automated multi-organs segmentation in a variety of medical images

Cited by 9 publications

References 40 publications

Application of visual transformer in renal image analysis

Application of visual transformer in renal image analysis

CCTrans: Improving Medical Image Segmentation with Contoured Convolutional Transformer Network

Improving Surgical Scene Semantic Segmentation through a Deep Learning Architecture with Attention to Class Imbalance

Contact Info

Product

Resources

About