Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution - 07/03/24
, Carole Lazarus a, Mathieu Lederlin c, Sébastien Mulé d, Rafael Wiemker a, Salim Si-Mohamed e, Emilien Jupin-Delevaux e, Olivier Nempont a, Youssef Skandarani a, Mathieu De Craene a, Segbedji Goubalan a, Caroline Raynaud a, Younes Belkouchi f, g, Amira Ben Afia h, Clement Fabre i, Gilbert Ferretti j, Constance De Margerie k, Pierre Berge l, Renan Liberge m, Nicolas Elbaz n, Maxime Blain o, Pierre-Yves Brillet p, Guillaume Chassagnon q, Farah Cadour r, Caroline Caramella s, Mostafa El Hajjam t, Samia Boussouar u, Joya Hadchiti v, Xavier Fablet c, Antoine Khalil h, Hugues Talbot g, Alain Luciani d, Nathalie Lassau f, v, Loic Boussel b, e
Bienvenue sur EM-consulte, la référence des professionnels de santé.
Article gratuit.
Connectez-vous pour en bénéficier!
Highlights |
• | Deep learning-based methods can be used to estimate the severity of pulmonary embolism with 3D computed tomography pulmonary angiographies. |
• | AI-based methods can be used to detect and estimate the severity of pulmonary embolism with 3D computed tomography pulmonary angiographies. |
• | AI-based blood clots supervised segmentation can help detect and classify pulmonary embolism. |
• | AI enables automated estimation of the Qanadli score and the right-to-left ventricle diameter ratio, allowing fast and reproducible quantification of pulmonary embolism severity. |
Abstract |
Purpose |
The purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations.
Materials and methods |
Using a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio.
Results |
Quantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850–0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810–0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668–0.760) and of 0.723 (95% CI: 0.668–0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set.
Conclusion |
This study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.
Le texte complet de cet article est disponible en PDF.Keywords : Artificial intelligence, Pulmonary embolism, Qanadli score, Retina U-net
Abbreviations : 3D, CAD-PE, CI, CT, CTPA, FUM-PE, LV, PE, R², ROC, RV
Plan
Vol 105 - N° 3
P. 97-103 - mars 2024 Retour au numéro
Article précédent
- Treatment of adenomyosis, abdominal wall endometriosis and uterine leiomyoma with interventional radiology: A review of current evidences
- Maxime Barat, Anthony Dohan, Maureen Kohi, Clement Marcelin, Jean-Pierre Pelage, Alban Denys, Sebastian Mafeld, Claire S. Kaufman, Philippe Soyer, Francois H. Cornelis
- External validation of an artificial intelligence solution for the detection of elbow fractures and joint effusions in children
- Michel Dupuis, Léo Delbos, Alexandra Rouquette, Catherine Adamsbaum, Raphaël Veil
Bienvenue sur EM-consulte, la référence des professionnels de santé.