Corpus ID: 231979525

Benefits of Linear Conditioning for Segmentation using Metadata

@article{Lemay2021BenefitsOL,
  title={Benefits of Linear Conditioning for Segmentation using Metadata},
  author={Andreanne Lemay and C. Gros and Olivier Vincent and Y. Liu and Joseph Paul Cohen and J. Cohen-Adad},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.09582}
}
Medical images are often accompanied by metadata describing the image (vendor, acquisition parameters) and the patient (disease type or severity, demographics, genomics). This metadata is usually disregarded by image segmentation methods. In this work, we adapt a linear conditioning method called FiLM (Feature-wise Linear Modulation) for image segmentation tasks. This FiLM adaptation enables integrating metadata into segmentation models for better performance. We observed an average Dice score… Expand
1 Citations

Figures and Tables from this paper

Impact of individual rater style on deep learning uncertainty in medical imaging segmentation
  • PDF

References

SHOWING 1-10 OF 26 REFERENCES
A large annotated medical image dataset for the development and evaluation of segmentation algorithms
  • 182
  • PDF
Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation
  • Yuyin Zhou, Z. Li, +5 authors A. Yuille
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
  • 49
  • PDF
ivadomed: A Medical Imaging Deep Learning Toolbox
  • 4
  • PDF
U-Net: Convolutional Networks for Biomedical Image Segmentation
  • 21,122
  • PDF
Adaptive Batch Normalization for practical domain adaptation
  • 155
  • PDF
...
1
2
3
...