Creating a training set for artificial intelligence from initial segmentations of airways

Ivan Dudurych*, Antonio Garcia-Uceda, Zaigham Saghir, Harm A.W.M. Tiddens, Rozemarijn Vliegenthart, Marleen de Bruijne

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

4 Citations (Scopus)
11 Downloads (Pure)

Abstract

Airways segmentation is important for research about pulmonary disease but require a large amount of time by trained specialists. We used an openly available software to improve airways segmentations obtained from an artificial intelligence (AI) tool and retrained the tool to get a better performance. Fifteen initial airway segmentations from low-dose chest computed tomography scans were obtained with a 3D-Unet AI tool previously trained on Danish Lung Cancer Screening Trial and Erasmus-MC Sophia datasets. Segmentations were manually corrected in 3D Slicer. The corrected airway segmentations were used to retrain the 3D-Unet. Airway measurements were automatically obtained and included count, airway length and luminal diameter per generation from the segmentations. Correcting segmentations required 2–4 h per scan. Manually corrected segmentations had more branches (p < 0.001), longer airways (p < 0.001) and smaller luminal diameters (p = 0.004) than initial segmentations. Segmentations from retrained 3D-Unets trended towards more branches and longer airways compared to the initial segmentations. The largest changes were seen in airways from 6th generation onwards. Manual correction results in significantly improved segmentations and is potentially a useful and time-efficient method to improve the AI tool performance on a specific hospital or research dataset.

Original languageEnglish
Article number54
JournalEuropean radiology experimental
Volume5
Issue number1
DOIs
Publication statusPublished - 29 Nov 2021

Bibliographical note

Funding Information:
This study is part of the first author’s PhD which has received funding by IMDI (Innovative Medical Devices Initiative)/ZonMW (Netherlands Organisation for Health Research and Development.

Funding Information:
The authors of this manuscript declare no competing relationships with any companies, whose products or services may be related to the subject matter of the article. Harm Tiddens received consultancy fees from Thirona. Rozemarijn Vliegenthart is supported by an institutional research grant from Siemens Healthineers.

Publisher Copyright:
© 2021, The Author(s).

Research programs

  • EMC OR-01-54-02

Fingerprint

Dive into the research topics of 'Creating a training set for artificial intelligence from initial segmentations of airways'. Together they form a unique fingerprint.

Cite this