Corpus ID: 174801239

Multi-scale guided attention for medical image segmentation

@article{Sinha2019MultiscaleGA,
  title={Multi-scale guided attention for medical image segmentation},
  author={Ashish Sinha and Jos{\'e} Dolz},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.02849}
}
Even though convolutional neural networks (CNNs) are driving progress in medical image segmentation, standard models still have some drawbacks. [...] Key Result This demonstrates the efficiency of our approach to generate precise and reliable automatic segmentations of medical images. Our code and the trained model are made publicly available at: this https URLExpand
MPG-Net: Multi-Prediction Guided Network for Segmentation of Retinal Layers in OCT Images
  • Zeyu Fu, Yang Sun, +5 authors S. Dlay
  • Computer Science, Engineering
  • 2020 28th European Signal Processing Conference (EUSIPCO)
  • 2021
TLDR
A novel multi-prediction guided attention network (MPG-Net) for automated retinal layer segmentation in OCT images which provides pixel-wise semantic prediction guidance to better recover the segmentation mask at each scale. Expand
ASCU-Net: Attention Gate, Spatial and Channel Attention U-Net for Skin Lesion Segmentation
TLDR
This paper proposes an extended version of U-Net for the segmentation of skin lesions using the concept of the triple attention mechanism, and demonstrates the effectiveness to the presence of irregular borders, lesion and skin smooth transitions, noise, and artifacts. Expand
Inter-Slice Context Residual Learning for 3D Medical Image Segmentation
TLDR
The results indicate that the proposed ConResNet is more accurate than six top-ranking methods in brain tumor segmentation and seven top- ranking methods in pancreas segmentation. Expand
Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation
TLDR
This paper proposes Attention Deeplabv3+, an extended version of Deeplabs3+ for skin lesion segmentation by employing the idea of attention mechanism in two stages, and exploits the second level attention strategy to integrate different layers of the atrous convolution. Expand
DT-Net: A novel network based on multi-directional integrated convolution and threshold convolution
TLDR
A novel end-to-end semantic segmentation algorithm, DT-Net, is proposed, and two new convolution strategies are used to better achieve end- to-end semantics segmentation of medical images. Expand
Learning to Segment Anatomical Structures Accurately from One Exemplar
TLDR
This work proposes a novel contribution of Contour Transformer Network (CTN), a one-shot anatomy segmentor including a naturally built-in human-in-the-loop mechanism that significantly outperforms non-learning-based methods and performs competitively to the state-of- the-art fully supervised deep learning approaches. Expand
Segmenting Medical MRI via Recurrent Decoding Cell
TLDR
A novel feature fusion unit called Recurrent Decoding Cell (RDC) is proposed which leverages convolutional RNNs to memorize the long-term context information from the previous layers in the decoding phase to improve the segmentation accuracy and reduce the model size. Expand
Applying 3D U-Net Architecture to the Task of Multi-Organ Segmentation in Computed Tomography
TLDR
This paper investigates fully convolutional neural networks (FCNs) and proposes a modified 3D U-Net architecture devoted to the processing of computed tomography (CT) volumetric images in the automatic semantic segmentation tasks and demonstrates that 3DU-Net based architectures could achieve competitive performance and efficiency in the multi-organ segmentation task. Expand
MDCC-Net: Multiscale double-channel convolution U-Net framework for colorectal tumor segmentation
TLDR
A multiscale double-channel convolution U-Net (MDCC-Net) framework for colorectal tumor segmentation has potential clinical applicability and is close to the expert level. Expand
A deep learning based multiscale approach to segment cancer area in liver whole slide image
TLDR
In this work, several neural architectures were compared using the original image level for the training procedure and the effectiveness of the proposed multi-scales approach achieving better scores compared to the state-of-the-art. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 87 REFERENCES
Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images
TLDR
Experimental results show that AG models consistently improve the prediction performance of the base architectures across different datasets and training sizes while preserving computational efficiency. Expand
Attention to Scale: Scale-Aware Semantic Image Segmentation
TLDR
An attention mechanism that learns to softly weight the multi-scale features at each pixel location is proposed, which not only outperforms averageand max-pooling, but allows us to diagnostically visualize the importance of features at different positions and scales. Expand
Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
TLDR
An efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data, and improves on the state-of-the‐art for all three applications. Expand
Deep Attentional Features for Prostate Segmentation in Ultrasound
TLDR
A novel deep neural network equipped with deep attentional feature (DAF) modules for better prostate segmentation in TRUS by fully exploiting the complementary information encoded in different layers of the convolutional neural network (CNN). Expand
Deep gated attention networks for large-scale street-level scene segmentation
TLDR
A novel Spatial Gated Attention (SGA) module, which automatically highlights the attentive regions for pixel-wise labeling, resulting in effective street-level scene segmentation and an efficient multi-scale feature interaction mechanism which is able to adaptively aggregate the hierarchical features. Expand
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TLDR
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. Expand
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
TLDR
This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. Expand
Segmentation of abdominal organs from CT using a multi-level, hierarchical neural network strategy
  • M. A. Selver
  • Computer Science, Medicine
  • Comput. Methods Programs Biomed.
  • 2014
TLDR
How hierarchical formations can translate to improved accuracy, when large size feature spaces are involved, is explored in this study and a semi-automatic, slice-by-slice segmentation method is developed using a novel multi-level and hierarchical neural network. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
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. Expand
SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning
TLDR
This paper introduces a novel convolutional neural network dubbed SCA-CNN that incorporates Spatial and Channel-wise Attentions in a CNN that significantly outperforms state-of-the-art visual attention-based image captioning methods. Expand
...
1
2
3
4
5
...