Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography
Anatomic landmark detection is crucial during preoperative planning of transcatheter aortic valve implantation (TAVI) to select the proper device size and assess the risk of complications. The detection is currently a time-consuming manual process influenced by the image quality and subject to opera...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Journal of Interventional Cardiology |
| Online Access: | http://dx.doi.org/10.1155/2020/9843275 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524418624356352 |
|---|---|
| author | Patricio Astudillo Peter Mortier Johan Bosmans Ole De Backer Peter de Jaegere Francesco Iannaccone Matthieu De Beule Joni Dambre |
| author_facet | Patricio Astudillo Peter Mortier Johan Bosmans Ole De Backer Peter de Jaegere Francesco Iannaccone Matthieu De Beule Joni Dambre |
| author_sort | Patricio Astudillo |
| collection | DOAJ |
| description | Anatomic landmark detection is crucial during preoperative planning of transcatheter aortic valve implantation (TAVI) to select the proper device size and assess the risk of complications. The detection is currently a time-consuming manual process influenced by the image quality and subject to operator variability. In this work, we propose a novel automatic method to detect the relevant aortic landmarks from MDCT images using deep learning techniques. We trained three convolutional neural networks (CNNs) with 344 multidetector computed tomography (MDCT) acquisitions to detect five anatomical landmarks relevant for TAVI planning: the three basal attachment points of the aortic valve leaflets and the left and right coronary ostia. The detection strategy used these three CNN models to analyse a single MDCT image and yield three segmentation volumes as output. These segmentation volumes were averaged into one final segmentation volume, and the final predicted landmarks were obtained during a postprocessing step. Finally, we constructed the aortic annular plane, defined by the three predicted hinge points, and measured the distances from this plane to the predicted coronary ostia (i.e., coronary height). The methodology was validated on 100 patients. The automatic landmark detection was able to detect all the landmarks and showed high accuracy as the median distance between the ground truth and predictions is lower than the interobserver variations (1.5 mm [1.1–2.1], 2.0 mm [1.3–2.8] with a paired difference −0.5 ± 1.3 mm and p value <0.001). Furthermore, a high correlation is observed between predicted and manually measured coronary heights (for both R2 = 0.8). The image analysis time per patient was below one second. The proposed method is accurate, fast, and reproducible. Embedding this tool based on deep learning in the preoperative planning routine may have an impact in the TAVI environments by reducing the time and cost and improving accuracy. |
| format | Article |
| id | doaj-art-c60b3d9513d44a2584bc9ac6bbc16a5f |
| institution | Kabale University |
| issn | 0896-4327 1540-8183 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Interventional Cardiology |
| spelling | doaj-art-c60b3d9513d44a2584bc9ac6bbc16a5f2025-02-03T05:53:17ZengWileyJournal of Interventional Cardiology0896-43271540-81832020-01-01202010.1155/2020/98432759843275Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed TomographyPatricio Astudillo0Peter Mortier1Johan Bosmans2Ole De Backer3Peter de Jaegere4Francesco Iannaccone5Matthieu De Beule6Joni Dambre7FEops, Technologiepark- Zwijnaarde 122, Ghent 9052, BelgiumFEops, Technologiepark- Zwijnaarde 122, Ghent 9052, BelgiumUniversity Hospital Antwerp (UZA), Antwerp, BelgiumDepartment of Cardiology, Rigshospitalet University Hospital, Copenhagen, DenmarkDepartment of Cardiology, Erasmus MC, Rotterdam, NetherlandsFEops, Technologiepark- Zwijnaarde 122, Ghent 9052, BelgiumFEops, Technologiepark- Zwijnaarde 122, Ghent 9052, BelgiumDepartment of Electronics and Information Systems, UGent—imec, Technologiepark-Zwijnaarde 126, Ghent 9052, BelgiumAnatomic landmark detection is crucial during preoperative planning of transcatheter aortic valve implantation (TAVI) to select the proper device size and assess the risk of complications. The detection is currently a time-consuming manual process influenced by the image quality and subject to operator variability. In this work, we propose a novel automatic method to detect the relevant aortic landmarks from MDCT images using deep learning techniques. We trained three convolutional neural networks (CNNs) with 344 multidetector computed tomography (MDCT) acquisitions to detect five anatomical landmarks relevant for TAVI planning: the three basal attachment points of the aortic valve leaflets and the left and right coronary ostia. The detection strategy used these three CNN models to analyse a single MDCT image and yield three segmentation volumes as output. These segmentation volumes were averaged into one final segmentation volume, and the final predicted landmarks were obtained during a postprocessing step. Finally, we constructed the aortic annular plane, defined by the three predicted hinge points, and measured the distances from this plane to the predicted coronary ostia (i.e., coronary height). The methodology was validated on 100 patients. The automatic landmark detection was able to detect all the landmarks and showed high accuracy as the median distance between the ground truth and predictions is lower than the interobserver variations (1.5 mm [1.1–2.1], 2.0 mm [1.3–2.8] with a paired difference −0.5 ± 1.3 mm and p value <0.001). Furthermore, a high correlation is observed between predicted and manually measured coronary heights (for both R2 = 0.8). The image analysis time per patient was below one second. The proposed method is accurate, fast, and reproducible. Embedding this tool based on deep learning in the preoperative planning routine may have an impact in the TAVI environments by reducing the time and cost and improving accuracy.http://dx.doi.org/10.1155/2020/9843275 |
| spellingShingle | Patricio Astudillo Peter Mortier Johan Bosmans Ole De Backer Peter de Jaegere Francesco Iannaccone Matthieu De Beule Joni Dambre Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography Journal of Interventional Cardiology |
| title | Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography |
| title_full | Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography |
| title_fullStr | Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography |
| title_full_unstemmed | Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography |
| title_short | Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography |
| title_sort | automatic detection of the aortic annular plane and coronary ostia from multidetector computed tomography |
| url | http://dx.doi.org/10.1155/2020/9843275 |
| work_keys_str_mv | AT patricioastudillo automaticdetectionoftheaorticannularplaneandcoronaryostiafrommultidetectorcomputedtomography AT petermortier automaticdetectionoftheaorticannularplaneandcoronaryostiafrommultidetectorcomputedtomography AT johanbosmans automaticdetectionoftheaorticannularplaneandcoronaryostiafrommultidetectorcomputedtomography AT oledebacker automaticdetectionoftheaorticannularplaneandcoronaryostiafrommultidetectorcomputedtomography AT peterdejaegere automaticdetectionoftheaorticannularplaneandcoronaryostiafrommultidetectorcomputedtomography AT francescoiannaccone automaticdetectionoftheaorticannularplaneandcoronaryostiafrommultidetectorcomputedtomography AT matthieudebeule automaticdetectionoftheaorticannularplaneandcoronaryostiafrommultidetectorcomputedtomography AT jonidambre automaticdetectionoftheaorticannularplaneandcoronaryostiafrommultidetectorcomputedtomography |