Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution
Copyright © 2023 Société française de radiologie. Published by Elsevier Masson SAS. All rights reserved..
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.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:105 |
|---|---|
| Enthalten in: |
Diagnostic and interventional imaging - 105(2024), 3 vom: 18. März, Seite 97-103 |
| Sprache: |
Englisch |
|---|
| Links: |
|---|
| Themen: |
Artificial intelligence |
|---|
| Anmerkungen: |
Date Completed 11.03.2024 Date Revised 11.03.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.diii.2023.09.006 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM36752046X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM36752046X | ||
| 003 | DE-627 | ||
| 005 | 20240311232135.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240124s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.diii.2023.09.006 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1323.xml |
| 035 | |a (DE-627)NLM36752046X | ||
| 035 | |a (NLM)38261553 | ||
| 035 | |a (PII)S2211-5684(23)00180-8 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Djahnine, Aissam |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 11.03.2024 | ||
| 500 | |a Date Revised 11.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2023 Société française de radiologie. Published by Elsevier Masson SAS. All rights reserved. | ||
| 520 | |a 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 | ||
| 520 | |a 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 | ||
| 520 | |a 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 | ||
| 520 | |a 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 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Artificial intelligence | |
| 650 | 4 | |a Pulmonary embolism | |
| 650 | 4 | |a Qanadli score | |
| 650 | 4 | |a Retina U-net | |
| 700 | 1 | |a Lazarus, Carole |e verfasserin |4 aut | |
| 700 | 1 | |a Lederlin, Mathieu |e verfasserin |4 aut | |
| 700 | 1 | |a Mulé, Sébastien |e verfasserin |4 aut | |
| 700 | 1 | |a Wiemker, Rafael |e verfasserin |4 aut | |
| 700 | 1 | |a Si-Mohamed, Salim |e verfasserin |4 aut | |
| 700 | 1 | |a Jupin-Delevaux, Emilien |e verfasserin |4 aut | |
| 700 | 1 | |a Nempont, Olivier |e verfasserin |4 aut | |
| 700 | 1 | |a Skandarani, Youssef |e verfasserin |4 aut | |
| 700 | 1 | |a De Craene, Mathieu |e verfasserin |4 aut | |
| 700 | 1 | |a Goubalan, Segbedji |e verfasserin |4 aut | |
| 700 | 1 | |a Raynaud, Caroline |e verfasserin |4 aut | |
| 700 | 1 | |a Belkouchi, Younes |e verfasserin |4 aut | |
| 700 | 1 | |a Afia, Amira Ben |e verfasserin |4 aut | |
| 700 | 1 | |a Fabre, Clement |e verfasserin |4 aut | |
| 700 | 1 | |a Ferretti, Gilbert |e verfasserin |4 aut | |
| 700 | 1 | |a De Margerie, Constance |e verfasserin |4 aut | |
| 700 | 1 | |a Berge, Pierre |e verfasserin |4 aut | |
| 700 | 1 | |a Liberge, Renan |e verfasserin |4 aut | |
| 700 | 1 | |a Elbaz, Nicolas |e verfasserin |4 aut | |
| 700 | 1 | |a Blain, Maxime |e verfasserin |4 aut | |
| 700 | 1 | |a Brillet, Pierre-Yves |e verfasserin |4 aut | |
| 700 | 1 | |a Chassagnon, Guillaume |e verfasserin |4 aut | |
| 700 | 1 | |a Cadour, Farah |e verfasserin |4 aut | |
| 700 | 1 | |a Caramella, Caroline |e verfasserin |4 aut | |
| 700 | 1 | |a Hajjam, Mostafa El |e verfasserin |4 aut | |
| 700 | 1 | |a Boussouar, Samia |e verfasserin |4 aut | |
| 700 | 1 | |a Hadchiti, Joya |e verfasserin |4 aut | |
| 700 | 1 | |a Fablet, Xavier |e verfasserin |4 aut | |
| 700 | 1 | |a Khalil, Antoine |e verfasserin |4 aut | |
| 700 | 1 | |a Talbot, Hugues |e verfasserin |4 aut | |
| 700 | 1 | |a Luciani, Alain |e verfasserin |4 aut | |
| 700 | 1 | |a Lassau, Nathalie |e verfasserin |4 aut | |
| 700 | 1 | |a Boussel, Loic |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Diagnostic and interventional imaging |d 2012 |g 105(2024), 3 vom: 18. März, Seite 97-103 |w (DE-627)NLM21623557X |x 2211-5684 |7 nnns |
| 773 | 1 | 8 | |g volume:105 |g year:2024 |g number:3 |g day:18 |g month:03 |g pages:97-103 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.diii.2023.09.006 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 105 |j 2024 |e 3 |b 18 |c 03 |h 97-103 | ||