Dataset Information

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

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.

SUBMITTER: Dudurych I

PROVIDER: S-EPMC8627914 | biostudies-literature | 2021 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Dudurych Ivan I Garcia-Uceda Antonio A Saghir Zaigham Z Tiddens Harm A W M HAWM Vliegenthart Rozemarijn R de Bruijne Marleen M

European radiology experimental 20211129 1

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 Sophi ...[more]

PMID: 34841480

Similar Datasets

Project description:PurposeAs novel tracers are continuously under development, it is important to obtain reliable radiation dose estimates to optimize the amount of activity that can be administered while keeping radiation burden within acceptable limits. Organ segmentation is required for quantification of specific uptake in organs of interest and whole-body dosimetry but is a time-consuming task which induces high interobserver variability. Therefore, we explored using manual segmentations versus an artificial intelligence (AI)-based automated segmentation tool as a pre-processing step for calculating whole-body effective doses to determine the influence of variability in volumetric whole-organ segmentations on dosimetry.ProceduresPET/CT data of six patients undergoing imaging with 89Zr-labelled pembrolizumab were included. Manual organ segmentations were performed, using in-house developed software, and biodistribution information was obtained. Based on the activity biodistribution information, residence times were calculated. The residence times served as input for OLINDA/EXM version 1.0 (Vanderbilt University, 2003) to calculate the whole-body effective dose (mSv/MBq). Subsequently, organ segmentations were performed using RECOMIA, a cloud-based AI platform for nuclear medicine and radiology research. The workflow for calculating residence times and whole-body effective doses, as described above, was repeated.ResultsData were acquired on days 2, 4, and 7 post-injection, resulting in 18 scans. Overall analysis time per scan was approximately 4 h for manual segmentations compared to ≤ 30 min using AI-based segmentations. Median Jaccard similarity coefficients between manual and AI-based segmentations varied from 0.05 (range 0.00-0.14) for the pancreas to 0.78 (range 0.74-0.82) for the lungs. Whole-body effective doses differed minimally for the six patients with a median difference in received mSv/MBq of 0.52% (range 0.15-1.95%).ConclusionThis pilot study suggests that whole-body dosimetry calculations can benefit from fast, automated AI-based whole organ segmentations.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets