AUNet: Breast Mass Segmentation of Whole Mammograms

@article{Sun2018AUNetBM,
  title={AUNet: Breast Mass Segmentation of Whole Mammograms},
  author={Hui Sun and Cheng Li and Boqiang Liu and Shanshan Wang},
  journal={ArXiv},
  year={2018},
  volume={abs/1810.10151}
}
Deep learning based segmentation has seen rapid development lately in both natural and medical image processing. However, its application to mammographic mass segmentation is still a challenging task due to the low signal-to-noise ratio and the wide variety of mass shapes and sizes. In this study, we propose a new network, AUNet, for the breast mass segmentation. Different from most methods that need to extract mass-centered image patches, AUNet could directly process the whole mammograms… CONTINUE READING
2
Twitter Mentions

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Compared to three existing fully convolutional networks, AUNet achieved the best performances with an average Dice similarity coefficient of 81.8% for CBIS-DDSM and 79.1% for INbreast.
  • Our model shows an average DSC increase of at least 2%, SE increase of 0.7%, and ΔA decrease of 4.4% compared to the respective best performed FCNs.

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 64 REFERENCES

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2016
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Fully convolutional networks for semantic segmentation

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Understanding Convolution for Semantic Segmentation

  • 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2017
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL