Pulmonary Lobe Segmentation


Logo for Pulmonary Lobe Segmentation

About

Creators:
Contact email:
Image Version:
c0722dad-3036-454e-89ad-7f18cec46cae
Last updated:
Sept. 21, 2022, 9:54 a.m.
Associated publication:
Xie W, Jacobs C, Charbonnier J-P, van Ginneken B. Relational Modeling for Robust and Efficient Pulmonary Lobe Segmentation in CT Scans. IEEE Trans Med Imaging. 2020;39(8):2664-2675.
Inputs:
  • CT Image  (Any CT image)
Outputs:
  • Results JSON File  (A collection of results of unknown type. Legacy, if possible please use alternative interfaces.)
  • Pulmonary Lobes  (Segmentation of the pulmonary lobes where 0 - background, 1 - left upper lobe, 2 - left lower lobe, 3 - right upper lobe, 4 - right lower lobe, and 5 - right middle lobe)
  • Pulmonary Lobes Screenshot  (Screenshot of a Pulmonary Lobe Segmentation)

Model Facts

Summary

Automatic segmenting of pulmonary lobes from a given chest CT scan using a contextual two-stage U-Net architecture, validated on COPD and COVID-19 scans.

Mechanism

The paper is available on https://arxiv.org/abs/2004.07443 and in the COVID-19 special issue of IEEE Transactions on Medical Imaging.

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