• Corpus ID: 4861068

Attention U-Net: Learning Where to Look for the Pancreas

@article{Oktay2018AttentionUL,
  title={Attention U-Net: Learning Where to Look for the Pancreas},
  author={Ozan Oktay and Jo Schlemper and Lo{\"i}c Le Folgoc and M. J. Lee and Mattias P. Heinrich and Kazunari Misawa and Kensaku Mori and Steven G. McDonagh and Nils Y. Hammerla and Bernhard Kainz and Ben Glocker and Daniel Rueckert},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.03999}
}
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes. [] Key Method AGs can be easily integrated into standard CNN architectures such as the U-Net model with minimal computational overhead while increasing the model sensitivity and prediction accuracy. The proposed Attention U-Net architecture is evaluated on two large CT abdominal datasets for multi-class image segmentation. Experimental results show that AGs…
[PDF] Semantic Reader
2,134 Citations
Highly Influential Citations
384
Background Citations
728
Methods Citations
872
Results Citations
39

2,134 Citations

MSAA-Net: a multi-scale attention-aware U-Net is used to segment the liver

A segmentation network MSAA-Net combining multi-scale features and an improved attention-aware U-Net is proposed, which achieves the highest segmentation accuracy while saving arithmetic power.

Minimal Information Loss Attention U-Net for abdominal CT of kidney cancers segmentation

A new image pyramid mechanism with dilated convolution that counters the loss of information caused by max-pooling, re-introducing the original image at multiple points within the network is proposed.

RBCA-Net: Reverse Boundary Channel Attention Network for Kidney Tumor Segmentation in CT images

The proposed model shows high performance compared to various architectures using the KiTS19 dataset including kidney and tumor and introduces the RBCA module that combines Reverse, Boundary, and Channel Attention to capture various sizes and shapes of lesions.

Higher accuracy and lower complexity: convolutional neural network for multi-organ segmentation

This work proposes an improved 2D U-Net to segment multiple OARs, aiming to increase accuracy while reducing complexity, and replaces vanilla convolutions with Octave Convolution (OctConv) units to reduce memory use and computation cost without accuracy sacrifice.

Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates

This paper proposes the extension of a popular deep learning methodology, Convolutional Neural Networks (CNN), by including deep supervision and attention gates and shows that the inclusion of attention and deep supervision results in consistent improvement of the tumor prediction accuracy across the different datasets and training sizes while adding minimal computational overhead.

RA-UNet: A Hybrid Deep Attention-Aware Network to Extract Liver and Tumor in CT Scans

This work proposes a 3D hybrid residual attention-aware segmentation method, i.e., RA-UNet, to precisely extract the liver region and segment tumors from the liver.

A Bypass-Based U-Net for Medical Image Segmentation

The proposed bypass-based U-Net can gain further context information, especially the details from the previous convolutional layer, and outperforms the original U- net on the DRIVE dataset for retinal vessel segmentation and the ISBI 2018 challenge for skin lesion segmentation.

Development of Novel Residual-Dense-Attention (RDA) U-Net Network Architecture for Hepatocellular Carcinoma Segmentation

U-Net neural network was used to combine ResBlock in ResNet with Dense Block in DenseNet in the coder part, allowing the training to maintain the parameters while reducing the overall recognition computation time, and the accuracy of liver and lesion segmentation reached 96% and 94.8%, respectively.

DRA U-Net: An Attention based U-Net Framework for 2D Medical Image Segmentation

This paper proposes an attention based U-Net framework, which includes an attention mechanism and residual feature extraction network, and designs an improved loss function to improve the training effect for organ segmentation.

Development of Deep Learning with RDA U-Net Network for Bladder Cancer Segmentation

The U-Net neural network was used to extend the encoder position in combination with the ResBlock in ResNet and the Dense Block in DenseNet, so that the training could maintain the training parameters while reducing the overall identification operation time.
...

References

SHOWING 1-10 OF 41 REFERENCES

BRIEFnet: Deep Pancreas Segmentation Using Binary Sparse Convolutions

This work proposes to use binary sparse convolutions in the first layer as a particularly effective approach to reduce complexity while achieving high accuracy in segmentation of pancreas segmentation in CT.

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Improving Deep Pancreas Segmentation in CT and MRI Images via Recurrent Neural Contextual Learning and Direct Loss Function

This work proposes a new convolutional/recurrent neural network architecture to address the contextual learning and segmentation consistency problem and outperforms the state-of-the-art work on CT and MRI pancreas segmentation, respectively.

Learn To Pay Attention

An end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification that is able to bootstrap standard CNN architectures for the task of image classification, demonstrating superior generalisation over 6 unseen benchmark datasets.

Fully convolutional multi‐scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers

Multi-label Whole Heart Segmentation Using CNNs and Anatomical Label Configurations

Results on the MICCAI 2017 Multi-Modality Whole Heart Segmentation (MM-WHS) challenge show that the proposed architecture performs well on the provided CT and MRI training volumes, delivering in a three-fold cross validation an average Dice Similarity Coefficient over all heart substructures.

Hierarchical 3D fully convolutional networks for multi-organ segmentation

This work shows that a multi-class 3D FCN trained on manually labeled CT scans of seven abdominal structures can achieve competitive segmentation results, while avoiding the need for handcrafting features or training organ-specific models.

A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans

This paper forms a fixed-point model which uses a predicted segmentation mask to shrink the input region and outperform the state-of-the-art by more than \(4\%\), measured by the average Dice-Sorensen Coefficient (DSC).

Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation

This paper explores Ensembles of Multiple Models and Architectures (EMMA) for robust performance through aggregation of predictions from a wide range of methods to reduce the influence of the meta-parameters of individual models and the risk of overfitting the configuration to a particular database.