Airway Anatomical Labeling


Logo for Airway Anatomical Labeling

About

Creators:
Contact email:
Version:
9ddc877b-943d-4dd3-9df5-4c67c1d8473e
Last updated:
Dec. 15, 2021, 10:40 p.m.
Associated publication:
Xie W, Jacobs C, Charbonnier J-P, van Ginneken B. Structure and position-aware graph neural network for airway labeling. arXiv. Published online January 13, 2022.
Inputs:
  • Airway Segmentation  (A segmented airway tree, where individual branches are extracted and assigned a random unique value larger than 0, from 1 at the trachea to to a larger value in its descendants.)
Outputs:
  • Labeled Airway Segmentation  (A labeled airway segmentation, in which 18-segmental branches are labeled with 0: 'background', 1: 'rest', 2: 'RB1', 3: 'RB2', 4: 'RB3', 5: 'RB4', 6: 'RB5', 7: 'RB6', 8: 'RB7', 9: 'RB8', 10: 'RB9', 11: 'RB10', 12: 'LB1+2', 14: 'LB3', 15: 'LB4', 16: 'LB5', 17: 'LB6', 18: 'LB7+8', 20: 'LB9', 21: 'LB10', 22: 'RMB', 23: 'LMB', 24:"Trachea". Note: 13 and 19 are collapsed into 12 and 18, respectively.)

Model Facts

Summary

Mechanism

Validation and Performance

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