• Corpus ID: 243833097

Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention

@article{Wu2021HepaticVS,
  title={Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention},
  author={Mian Wu and Yinling Qian and Xiangyun Liao and Qiong Wang and Pheng-Ann Heng},
  journal={ArXiv},
  year={2021},
  volume={abs/2111.03368}
}
Purpose: Segmentation of liver vessels from CT images is indispensable prior to surgical planning and aroused broad range of interests in the medical image analysis community. Due to the complex structure and low contrast background, automatic liver vessel segmentation remains particularly challenging. Most of the related researches adopt FCN, U-net, and V-net variants as a backbone. However, these methods mainly focus on capturing multi-scale local features which may produce misclassified… 

Figures and Tables from this paper

Transformers in Medical Imaging: A Survey

TLDR
This survey surveys the use of Transformers in medical image segmentation, detection, classification, reconstruction, synthesis, registration, clinical report generation, and other tasks and develops taxonomy for each application.

3D Shuffle-Mixer: An Efficient Context-Aware Vision Learner of Transformer-MLP Paradigm for Dense Prediction in Medical Volume

TLDR
A novel 3D Shuffle-Mixer network of a new Local Vision Transformer-MLP paradigm for medical dense prediction that outperforms other state-of-the-artmedical dense prediction methods.

Computational Approaches for Acute Traumatic Brain Injury Image Recognition

TLDR
This review provides an overview of computational approaches that have been proposed for the detection and characterization of acute TBI imaging abnormalities, including intracranial hemorrhage, skull fractures, intrac Cranial mass effect, and stroke.

Hepatic Vein and Arterial Vessel Segmentation in Liver Tumor Patients

TLDR
This work proposes an unsupervised domain-adaptive two-stage vessel segmentation framework for simultaneous fine segmentation of arterial and venous vessels on venous phase CT, and proposes an orthogonal depth projection loss function to enhance the representation ability of the 3D U-shape segmentation network for the geometric information of the vessel model.

References

SHOWING 1-10 OF 32 REFERENCES

Attention-Guided Deep Neural Network With Multi-Scale Feature Fusion for Liver Vessel Segmentation

TLDR
A novel deep neural network for liver vessel segmentation, called LVSNet, is proposed, which employs special designs to obtain the accurate structure of the liver vessel and a series of ablation studies are conducted that comprehensively support the superiority of the underlying concepts.

Liver Vessels Segmentation Based on 3d Residual U-NET

TLDR
To accelerate convergence speed and enhance the representation for discriminative features, the residual block structure in the ResNet is introduced into the 3D U- net, and a new 3D Residual U-Net architect is constructed to segment the hepatic and portal veins from abdominal CT volumes.

TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation

TLDR
A novel parallelin-branch architecture, TransFuse, that combines Transformers and CNNs in a parallel style, where both global dependency and low-level spatial details can be efficiently captured in a much shallower manner, with significant parameter decrease and inference speed improvement.

Training Liver Vessel Segmentation Deep Neural Networks on Noisy Labels from Contrast CT Imaging

TLDR
Experimental results of 3DIRCADb dataset show that the proposed liver vessel segmentation deep neural networks that are able to perform the segmentation automatically can effectively extract liver vessel trees from contrast CT images with minimum annotations.

Robust liver vessel extraction using 3D U-Net with variant dice loss function

Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation

TLDR
Under the direct downsampling and up-sampling of the inputs and outputs by 4×, experiments demonstrate that the pure Transformer-based U-shaped Encoder-Decoder network outperforms those methods with full-convolution or the combination of transformer and convolution.

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

TLDR
It is argued that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information, and empirical results suggest that the Transformer-based architecture presents a better way to leverage self-attention compared with previous CNN-based self-Attention methods.

UNETR: Transformers for 3D Medical Image Segmentation

TLDR
This work reformulates the task of volumetric (3D) medical image segmentation as a sequence-to-sequence prediction problem and introduces a novel architecture, dubbed as UNEt TRansformers (UNETR), that utilizes a transformer as the encoder to learn sequence representations of the input volume and effectively capture the global multi-scale information.

Segmentation of Liver Vasculature From Contrast Enhanced CT Images Using Context-Based Voting

A novel vessel context-based voting is proposed for automatic liver vasculature segmentation in CT images. It is able to conduct full vessel segmentation and recognition of multiple vasculatures

Vesselness Filters: A Survey with Benchmarks Applied to Liver Imaging

TLDR
This article compares seven vessel enhancement filters covering the last twenty years literature in a unique common framework focusing on the liver vascular network which is under-represented in the literature.