nva_atlas
About
Interfaces
This algorithm implements all of the following input-output combinations:
| Inputs | Outputs | |
|---|---|---|
| 1 |
|
|
Model Facts
Summary
We implemented our approach with MONAI. We use the encoder-decoder backbone to extract image features and a smaller decoder to reconstruct the segmentation mask.
Mechanism
We have used the ATLAS dataset for training the model. We have randomly split the entire dataset into 5-folds and trained a model for each fold.
Validation and Performance
Average DICE among classes using 5-fold cross-validation: 0.6463 0.6621 , 0.6578, 0.6576, 0.6353 , 0.6188
Uses and Directions
This algorithm was developed for research purposes only.
Warnings
Common Error Messages
Information on this algorithm has been provided by the Algorithm Editors, following the Model Facts labels guidelines from Sendak, M.P., Gao, M., Brajer, N. et al. Presenting machine learning model information to clinical end users with model facts labels. npj Digit. Med. 3, 41 (2020). 10.1038/s41746-020-0253-3