Automatic coronary artery calcium scoring from unenhanced-ECG-gated CT using deep learning - 16/11/21
, Mario Viti a, c, Luc Nicodème a, Mickaël Ohana b, Hugues Talbot c, Umit Gencer d, Magloire Mekukosokeng e, Thomas Caramella f, Yann Diascorn f, Jean-Yves Airaud g, Marc-Samir Guillot d, Zoubir Bensalah h, Caroline Dam Hieu a, Bassam Abdallah a, Imad Bousaid i, Nathalie Lassau i, j, Elie Mousseaux d
Bienvenue sur EM-consulte, la référence des professionnels de santé.
Article gratuit.
Connectez-vous pour en bénéficier!
Highlights |
• | A three-dimensional (3D) deep learning-based model can be trained effectively to compute automatically the coronary artery calcium score from a CT examination. |
• | The proposed model is based on a U-Net architecture designed for 3D segmentation of coronary artery calcifications. |
• | It would be useful to test and validate this method on a wider range of CT acquisitions, including non-ECG-gated ones, performed for routine examinations for lung disease. |
Abstract |
Purpose |
The purpose of this study was to develop and evaluate an algorithm that can automatically estimate the amount of coronary artery calcium (CAC) from unenhanced electrocardiography (ECG)-gated computed tomography (CT) cardiac volume acquisitions by using convolutional neural networks (CNN).
Materials and methods |
The method used a set of five CNN with three-dimensional (3D) U-Net architecture trained on a database of 783 CT examinations to detect and segment coronary artery calcifications in a 3D volume. The Agatston score, the conventional CAC scoring, was then computed slice by slice from the resulting segmentation mask and compared to the ground truth manually estimated by radiologists. The quality of the estimation was assessed with the concordance index (C-index) on CAC risk category on a separate testing set of 98 independent CT examinations.
Results |
The final model yielded a C-index of 0.951 on the testing set. The remaining errors of the method were mainly observed on small-size and/or low-density calcifications, or calcifications located near the mitral valve or ring.
Conclusion |
The deep learning-based method proposed here to compute automatically the CAC score from unenhanced-ECG-gated cardiac CT is fast, robust and yields accuracy similar to those of other artificial intelligence methods, which could improve workflow efficiency, eliminating the time spent on manually selecting coronary calcifications to compute the Agatston score.
Le texte complet de cet article est disponible en PDF.Keywords : Tomography, X-ray computed, Deep learning, Coronary artery disease, Convolutional neural networks (CNN)
Abbreviations : 2D, 3D, AI, CAD, CAC, C-index, CNN, CT, ECG, FCNN, HU, ICC, SFR
Plan
Vol 102 - N° 11
P. 683-690 - novembre 2021 Retour au numéro
Article précédent
- Automatic cervical lymphadenopathy segmentation from CT data using deep learning
- Adele Courot, Diana L.F. Cabrera, Nicolas Gogin, Loic Gaillandre, Geoffrey Rico, Jules Zhang-Yin, Mickael Elhaik, François Bidault, Imad Bousaid, Nathalie Lassau
- Deep learning for lung disease segmentation on CT: Which reconstruction kernel should be used?
- Trieu-Nghi Hoang-Thi, Maria Vakalopoulou, Stergios Christodoulidis, Nikos Paragios, Marie-Pierre Revel, Guillaume Chassagnon
Bienvenue sur EM-consulte, la référence des professionnels de santé.