Corpus ID: 226956106

A Study of Domain Generalization on Ultrasound-based Multi-Class Segmentation of Arteries, Veins, Ligaments, and Nerves Using Transfer Learning

@article{Chen2020ASO,
  title={A Study of Domain Generalization on Ultrasound-based Multi-Class Segmentation of Arteries, Veins, Ligaments, and Nerves Using Transfer Learning},
  author={E. Chen and T. Mathai and Vinit Sarode and Howie Choset and J. Galeotti},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.07019}
}
  • E. Chen, T. Mathai, +2 authors J. Galeotti
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Identifying landmarks in the femoral area is crucial for ultrasound (US) -based robot-guided catheter insertion, and their presentation varies when imaged with different scanners. As such, the performance of past deep learning-based approaches is also narrowly limited to the training data distribution; this can be circumvented by fine-tuning all or part of the model, yet the effects of fine-tuning are seldom discussed. In this work, we study the US-based segmentation of multiple classes through… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 16 REFERENCES
    Segmentation of Vessels in Ultra High Frequency Ultrasound Sequences Using Contextual Memory
    • 4
    Fine Tuning U-Net for Ultrasound Image Segmentation: Which Layers?
    • 4
    • PDF
    Transfusion: Understanding Transfer Learning for Medical Imaging
    • 158
    • PDF
    U-Net: Convolutional Networks for Biomedical Image Segmentation
    • 18,282
    • Highly Influential
    • PDF
    Deep learning robotic guidance for autonomous vascular access
    • 8
    • PDF
    TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
    • 239
    • PDF
    Fast Vessel Segmentation and Tracking in Ultra High-Frequency Ultrasound Images
    • 7
    • PDF
    Coverage Testing of Deep Learning Models using Dataset Characterization
    • 3
    • PDF
    Adam: A Method for Stochastic Optimization
    • 56,437
    • Highly Influential
    • PDF