Uncertainty-refined image segmentation under domain shift
A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- NA0003525
- Assignee:
- National Technology & Engineering Solutions of Sandia, LLC (Albuquerque, NM)
- Patent Number(s):
- 11,379,991
- Application Number:
- 16/887,311
- OSTI ID:
- 1924873
- Country of Publication:
- United States
- Language:
- English
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
|
conference | October 2016 |
Similar Records
Bayesian SegNet for Semantic Segmentation with Improved Interpretation of Microstructural Evolution During Irradiation of Materials
Automated segmentation of porous thermal spray material CT scans with predictive uncertainty estimation