Detection and quantification of pulmonary embolism with artificial intelligence : The SFR 2022 artificial intelligence data challenge
Copyright © 2023 Société française de radiologie. Published by Elsevier Masson SAS. All rights reserved..
PURPOSE: In 2022, the French Society of Radiology together with the French Society of Thoracic Imaging and CentraleSupelec organized their 13th data challenge. The aim was to aid in the diagnosis of pulmonary embolism, by identifying the presence of pulmonary embolism and by estimating the ratio between right and left ventricular (RV/LV) diameters, and an arterial obstruction index (Qanadli's score) using artificial intelligence.
MATERIALS AND METHODS: The data challenge was composed of three tasks: the detection of pulmonary embolism, the RV/LV diameter ratio, and Qanadli's score. Sixteen centers all over France participated in the inclusion of the cases. A health data hosting certified web platform was established to facilitate the inclusion process of the anonymized CT examinations in compliance with general data protection regulation. CT pulmonary angiography images were collected. Each center provided the CT examinations with their annotations. A randomization process was established to pool the scans from different centers. Each team was required to have at least a radiologist, a data scientist, and an engineer. Data were provided in three batches to the teams, two for training and one for evaluation. The evaluation of the results was determined to rank the participants on the three tasks.
RESULTS: A total of 1268 CT examinations were collected from the 16 centers following the inclusion criteria. The dataset was split into three batches of 310, 580 and 378 C T examinations provided to the participants respectively on September 5, 2022, October 7, 2022 and October 9, 2022. Seventy percent of the data from each center were used for training, and 30% for the evaluation. Seven teams with a total of 48 participants including data scientists, researchers, radiologists and engineering students were registered for participation. The metrics chosen for evaluation included areas under receiver operating characteristic curves, specificity and sensitivity for the classification task, and the coefficient of determination r2 for the regression tasks. The winning team achieved an overall score of 0.784.
CONCLUSION: This multicenter study suggests that the use of artificial intelligence for the diagnosis of pulmonary embolism is possible on real data. Moreover, providing quantitative measures is mandatory for the interpretability of the results, and is of great aid to the radiologists especially in emergency settings.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:104 |
|---|---|
| Enthalten in: |
Diagnostic and interventional imaging - 104(2023), 10 vom: 15. Okt., Seite 485-489 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Belkouchi, Younes [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Artificial intelligence |
|---|
| Anmerkungen: |
Date Completed 23.10.2023 Date Revised 23.10.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.diii.2023.05.007 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM358234654 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM358234654 | ||
| 003 | DE-627 | ||
| 005 | 20231226210517.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.diii.2023.05.007 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1194.xml |
| 035 | |a (DE-627)NLM358234654 | ||
| 035 | |a (NLM)37321875 | ||
| 035 | |a (PII)S2211-5684(23)00118-3 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Belkouchi, Younes |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Detection and quantification of pulmonary embolism with artificial intelligence |b The SFR 2022 artificial intelligence data challenge |
| 264 | 1 | |c 2023 | |
| 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 23.10.2023 | ||
| 500 | |a Date Revised 23.10.2023 | ||
| 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: In 2022, the French Society of Radiology together with the French Society of Thoracic Imaging and CentraleSupelec organized their 13th data challenge. The aim was to aid in the diagnosis of pulmonary embolism, by identifying the presence of pulmonary embolism and by estimating the ratio between right and left ventricular (RV/LV) diameters, and an arterial obstruction index (Qanadli's score) using artificial intelligence | ||
| 520 | |a MATERIALS AND METHODS: The data challenge was composed of three tasks: the detection of pulmonary embolism, the RV/LV diameter ratio, and Qanadli's score. Sixteen centers all over France participated in the inclusion of the cases. A health data hosting certified web platform was established to facilitate the inclusion process of the anonymized CT examinations in compliance with general data protection regulation. CT pulmonary angiography images were collected. Each center provided the CT examinations with their annotations. A randomization process was established to pool the scans from different centers. Each team was required to have at least a radiologist, a data scientist, and an engineer. Data were provided in three batches to the teams, two for training and one for evaluation. The evaluation of the results was determined to rank the participants on the three tasks | ||
| 520 | |a RESULTS: A total of 1268 CT examinations were collected from the 16 centers following the inclusion criteria. The dataset was split into three batches of 310, 580 and 378 C T examinations provided to the participants respectively on September 5, 2022, October 7, 2022 and October 9, 2022. Seventy percent of the data from each center were used for training, and 30% for the evaluation. Seven teams with a total of 48 participants including data scientists, researchers, radiologists and engineering students were registered for participation. The metrics chosen for evaluation included areas under receiver operating characteristic curves, specificity and sensitivity for the classification task, and the coefficient of determination r2 for the regression tasks. The winning team achieved an overall score of 0.784 | ||
| 520 | |a CONCLUSION: This multicenter study suggests that the use of artificial intelligence for the diagnosis of pulmonary embolism is possible on real data. Moreover, providing quantitative measures is mandatory for the interpretability of the results, and is of great aid to the radiologists especially in emergency settings | ||
| 650 | 4 | |a Multicenter Study | |
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Artificial intelligence | |
| 650 | 4 | |a Computed tomography | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Pulmonary embolism | |
| 650 | 4 | |a Qanadli's score | |
| 700 | 1 | |a Lederlin, Mathieu |e verfasserin |4 aut | |
| 700 | 1 | |a Ben Afia, Amira |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 Luciani, Alain |e verfasserin |4 aut | |
| 700 | 1 | |a Cotten, Anne |e verfasserin |4 aut | |
| 700 | 1 | |a Meder, Jean-Francois |e verfasserin |4 aut | |
| 700 | 1 | |a Talbot, Hugues |e verfasserin |4 aut | |
| 700 | 1 | |a Lassau, Nathalie |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Diagnostic and interventional imaging |d 2012 |g 104(2023), 10 vom: 15. Okt., Seite 485-489 |w (DE-627)NLM21623557X |x 2211-5684 |7 nnns |
| 773 | 1 | 8 | |g volume:104 |g year:2023 |g number:10 |g day:15 |g month:10 |g pages:485-489 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.diii.2023.05.007 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 104 |j 2023 |e 10 |b 15 |c 10 |h 485-489 | ||