Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks

@article{Wang2018AleatoricUE,
  title={Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks},
  author={Guotai Wang and Wenqi Li and Michael Aertsen and Jan Deprest and S{\'e}bastien Ourselin and Tom Vercauteren},
  journal={ArXiv},
  year={2018},
  volume={abs/1807.07356}
}
Despite the state-of-the-art performance for medical image segmentation, deep convolutional neural networks (CNNs) have rarely provided uncertainty estimations regarding their segmentation outputs, e.g., model (epistemic) and image-based (aleatoric) uncertainties. In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks. We additionally propose a test-time augmentation-based aleatoric uncertainty to analyze the effect of different… CONTINUE READING
BETA
39
Twitter Mentions

Similar Papers

References

Publications referenced by this paper.
SHOWING 1-10 OF 44 REFERENCES

Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning

  • IEEE Transactions on Medical Imaging
  • 2018
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

NiftyNet: a deep-learning platform for medical imaging

  • Computer Methods and Programs in Biomedicine
  • 2018
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

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

  • 2016 Fourth International Conference on 3D Vision (3DV)
  • 2016
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL