Automated MSCT Analysis for Planning Left Atrial Appendage Occlusion Using Artificial Intelligence.
Journal
Journal of interventional cardiology
ISSN: 1540-8183
Titre abrégé: J Interv Cardiol
Pays: United States
ID NLM: 8907826
Informations de publication
Date de publication:
2022
2022
Historique:
received:
21
12
2021
accepted:
29
03
2022
entrez:
16
5
2022
pubmed:
17
5
2022
medline:
20
5
2022
Statut:
epublish
Résumé
The number of multislice computed tomography (MSCT) analyses performed for planning structural heart interventions is rapidly increasing. Further automation is required to save time, increase standardization, and reduce the learning curve. The purpose of this study was to investigate the feasibility of a fully automated artificial intelligence (AI)-based MSCT analysis for planning structural heart interventions, focusing on left atrial appendage occlusion (LAAO) as the selected use case. Different deep learning models were trained, validated, and tested using a cohort of 583 patients for which manually annotated data were available. These models were used independently or in combination to detect the anatomical ostium, the landing zone, the mitral valve annulus, and the fossa ovalis and to segment the left atrium (LA) and left atrial appendage (LAA). The accuracy of the models was evaluated through comparison with the manually annotated data. The automated analysis was performed on 25 randomly selected patients of the test cohort. The results were compared to the manually identified landmarks. The predicted segmentation of the LA(A) was similar to the manual segmentation (dice score of 0.94 ± 0.02). The difference between the automatically predicted and manually measured perimeter-based diameter was -0.8 ± 1.3 mm (anatomical ostium), -1.0 ± 1.5 mm (Amulet landing zone), and -0.1 ± 1.3 mm (Watchman FLX landing zone), which is similar to the operator variability on these measurements. Finally, the detected mitral valve annulus and fossa ovalis were close to the manual detection of these landmarks, as shown by the Hausdorff distance (3.9 ± 1.2 mm and 4.8 ± 1.8 mm, respectively). The average runtime of the complete workflow, including data pre- and postprocessing, was 57.5 ± 34.5 seconds. A fast and accurate AI-based workflow is proposed to automatically analyze MSCT images for planning LAAO. The approach, which can be easily extended toward other structural heart interventions, may help to handle the rapidly increasing volumes of patients.
Sections du résumé
Background
UNASSIGNED
The number of multislice computed tomography (MSCT) analyses performed for planning structural heart interventions is rapidly increasing. Further automation is required to save time, increase standardization, and reduce the learning curve.
Objective
UNASSIGNED
The purpose of this study was to investigate the feasibility of a fully automated artificial intelligence (AI)-based MSCT analysis for planning structural heart interventions, focusing on left atrial appendage occlusion (LAAO) as the selected use case.
Methods
UNASSIGNED
Different deep learning models were trained, validated, and tested using a cohort of 583 patients for which manually annotated data were available. These models were used independently or in combination to detect the anatomical ostium, the landing zone, the mitral valve annulus, and the fossa ovalis and to segment the left atrium (LA) and left atrial appendage (LAA). The accuracy of the models was evaluated through comparison with the manually annotated data.
Results
UNASSIGNED
The automated analysis was performed on 25 randomly selected patients of the test cohort. The results were compared to the manually identified landmarks. The predicted segmentation of the LA(A) was similar to the manual segmentation (dice score of 0.94 ± 0.02). The difference between the automatically predicted and manually measured perimeter-based diameter was -0.8 ± 1.3 mm (anatomical ostium), -1.0 ± 1.5 mm (Amulet landing zone), and -0.1 ± 1.3 mm (Watchman FLX landing zone), which is similar to the operator variability on these measurements. Finally, the detected mitral valve annulus and fossa ovalis were close to the manual detection of these landmarks, as shown by the Hausdorff distance (3.9 ± 1.2 mm and 4.8 ± 1.8 mm, respectively). The average runtime of the complete workflow, including data pre- and postprocessing, was 57.5 ± 34.5 seconds.
Conclusions
UNASSIGNED
A fast and accurate AI-based workflow is proposed to automatically analyze MSCT images for planning LAAO. The approach, which can be easily extended toward other structural heart interventions, may help to handle the rapidly increasing volumes of patients.
Identifiants
pubmed: 35571991
doi: 10.1155/2022/5797431
pmc: PMC9068333
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
5797431Informations de copyright
Copyright © 2022 Kilian Michiels et al.
Déclaration de conflit d'intérêts
PM is a shareholder of FEops, and KM, EH, PA, and AB are employees of FEops. IW has no conflicts of interest to declare.
Références
J Am Coll Cardiol. 2020 Nov 24;76(21):2492-2516
pubmed: 33213729
Europace. 2019 Aug 31;22(2):184
pubmed: 31504441
Comput Methods Programs Biomed. 2018 May;158:113-122
pubmed: 29544777
J Interv Cardiol. 2020 May 28;2020:9843275
pubmed: 32549802
JACC Cardiovasc Interv. 2020 Feb 10;13(3):277-292
pubmed: 31678086
JACC Cardiovasc Imaging. 2019 Aug;12(8 Pt 1):1549-1565
pubmed: 31395244
Morphologie. 2019 Dec;103(343):139-147
pubmed: 31570309
IEEE Trans Med Imaging. 2018 Aug;37(8):1822-1834
pubmed: 29994628
Front Physiol. 2019 Mar 22;10:237
pubmed: 30967786
IEEE Trans Ultrason Ferroelectr Freq Control. 2019 May;66(5):922-929
pubmed: 30869614
JACC Cardiovasc Imaging. 2019 Jan;12(1):1-24
pubmed: 30621986
J Cardiovasc Comput Tomogr. 2020 Mar - Apr;14(2):149-154
pubmed: 31445885
J Interv Cardiol. 2019 Nov 3;2019:3591314
pubmed: 31777469
Nat Rev Cardiol. 2021 Aug;18(8):600-609
pubmed: 33712806