Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation.
<h4>Background</h4>Atrial fibrillation (AF) has been linked to left atrial (LA) enlargement. Whereas most studies focused on 2D-based estimation of static LA volume (LAV), we used a fully-automatic convolutional neural network (CNN) for time-resolved (CINE) volumetry of the whole LA on c...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0272011 |
| _version_ | 1828357207676157952 |
|---|---|
| author | Maurice Pradella Constantin Anastasopoulos Shan Yang Manuela Moor Patrick Badertscher Julian E Gehweiler Florian Spies Philip Haaf Michael Zellweger Gregor Sommer Bram Stieltjes Jens Bremerich Stefan Osswald Michael Kühne Christian Sticherling Sven Knecht |
| author_facet | Maurice Pradella Constantin Anastasopoulos Shan Yang Manuela Moor Patrick Badertscher Julian E Gehweiler Florian Spies Philip Haaf Michael Zellweger Gregor Sommer Bram Stieltjes Jens Bremerich Stefan Osswald Michael Kühne Christian Sticherling Sven Knecht |
| author_sort | Maurice Pradella |
| collection | DOAJ |
| description | <h4>Background</h4>Atrial fibrillation (AF) has been linked to left atrial (LA) enlargement. Whereas most studies focused on 2D-based estimation of static LA volume (LAV), we used a fully-automatic convolutional neural network (CNN) for time-resolved (CINE) volumetry of the whole LA on cardiac MRI (cMRI). Aim was to investigate associations between functional parameters from fully-automated, 3D-based analysis of the LA and current classification schemes in AF.<h4>Methods</h4>We retrospectively analyzed consecutive AF patients who underwent cMRI on 1.5T systems including a stack of oblique-axial CINE series covering the whole LA. The LA was automatically segmented by a validated CNN. In the resulting volume-time curves, maximum, minimum and LAV before atrial contraction were automatically identified. Active, passive and total LA emptying fractions (LAEF) were calculated and compared to clinical classifications (AF Burden score (AFBS), increased stroke risk (CHA2DS2VASc≥2), AF type (paroxysmal/persistent), EHRA score, and AF risk factors). Moreover, multivariable linear regression models (mLRM) were used to identify associations with AF risk factors.<h4>Results</h4>Overall, 102 patients (age 61±9 years, 17% female) were analyzed. Active LAEF (LAEF_active) decreased significantly with an increase of AFBS (minimal: 44.0%, mild: 36.2%, moderate: 31.7%, severe: 20.8%, p<0.003) which was primarily caused by an increase of minimum LAV. Likewise, LAEF_active was lower in patients with increased stroke risk (30.7% vs. 38.9%, p = 0.002). AF type and EHRA score did not show significant differences between groups. In mLRM, a decrease of LAEF_active was associated with higher age (per year: -0.3%, p = 0.02), higher AFBS (per category: -4.2%, p<0.03) and heart failure (-12.1%, p<0.04).<h4>Conclusions</h4>Fully-automatic morphometry of the whole LA derived from cMRI showed significant relationships between LAEF_active with increased stroke risk and severity of AFBS. Furthermore, higher age, higher AFBS and presence of heart failure were independent predictors of reduced LAEF_active, indicating its potential usefulness as an imaging biomarker. |
| first_indexed | 2024-04-14T03:12:35Z |
| format | Article |
| id | doaj.art-84a98c817cc1467bb7a4137345a8f80e |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-14T03:12:35Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-84a98c817cc1467bb7a4137345a8f80e2022-12-22T02:15:34ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01178e027201110.1371/journal.pone.0272011Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation.Maurice PradellaConstantin AnastasopoulosShan YangManuela MoorPatrick BadertscherJulian E GehweilerFlorian SpiesPhilip HaafMichael ZellwegerGregor SommerBram StieltjesJens BremerichStefan OsswaldMichael KühneChristian SticherlingSven Knecht<h4>Background</h4>Atrial fibrillation (AF) has been linked to left atrial (LA) enlargement. Whereas most studies focused on 2D-based estimation of static LA volume (LAV), we used a fully-automatic convolutional neural network (CNN) for time-resolved (CINE) volumetry of the whole LA on cardiac MRI (cMRI). Aim was to investigate associations between functional parameters from fully-automated, 3D-based analysis of the LA and current classification schemes in AF.<h4>Methods</h4>We retrospectively analyzed consecutive AF patients who underwent cMRI on 1.5T systems including a stack of oblique-axial CINE series covering the whole LA. The LA was automatically segmented by a validated CNN. In the resulting volume-time curves, maximum, minimum and LAV before atrial contraction were automatically identified. Active, passive and total LA emptying fractions (LAEF) were calculated and compared to clinical classifications (AF Burden score (AFBS), increased stroke risk (CHA2DS2VASc≥2), AF type (paroxysmal/persistent), EHRA score, and AF risk factors). Moreover, multivariable linear regression models (mLRM) were used to identify associations with AF risk factors.<h4>Results</h4>Overall, 102 patients (age 61±9 years, 17% female) were analyzed. Active LAEF (LAEF_active) decreased significantly with an increase of AFBS (minimal: 44.0%, mild: 36.2%, moderate: 31.7%, severe: 20.8%, p<0.003) which was primarily caused by an increase of minimum LAV. Likewise, LAEF_active was lower in patients with increased stroke risk (30.7% vs. 38.9%, p = 0.002). AF type and EHRA score did not show significant differences between groups. In mLRM, a decrease of LAEF_active was associated with higher age (per year: -0.3%, p = 0.02), higher AFBS (per category: -4.2%, p<0.03) and heart failure (-12.1%, p<0.04).<h4>Conclusions</h4>Fully-automatic morphometry of the whole LA derived from cMRI showed significant relationships between LAEF_active with increased stroke risk and severity of AFBS. Furthermore, higher age, higher AFBS and presence of heart failure were independent predictors of reduced LAEF_active, indicating its potential usefulness as an imaging biomarker.https://doi.org/10.1371/journal.pone.0272011 |
| spellingShingle | Maurice Pradella Constantin Anastasopoulos Shan Yang Manuela Moor Patrick Badertscher Julian E Gehweiler Florian Spies Philip Haaf Michael Zellweger Gregor Sommer Bram Stieltjes Jens Bremerich Stefan Osswald Michael Kühne Christian Sticherling Sven Knecht Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation. PLoS ONE |
| title | Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation. |
| title_full | Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation. |
| title_fullStr | Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation. |
| title_full_unstemmed | Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation. |
| title_short | Associations between fully-automated, 3D-based functional analysis of the left atrium and classification schemes in atrial fibrillation. |
| title_sort | associations between fully automated 3d based functional analysis of the left atrium and classification schemes in atrial fibrillation |
| url | https://doi.org/10.1371/journal.pone.0272011 |
| work_keys_str_mv | AT mauricepradella associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT constantinanastasopoulos associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT shanyang associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT manuelamoor associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT patrickbadertscher associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT julianegehweiler associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT florianspies associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT philiphaaf associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT michaelzellweger associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT gregorsommer associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT bramstieltjes associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT jensbremerich associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT stefanosswald associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT michaelkuhne associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT christiansticherling associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation AT svenknecht associationsbetweenfullyautomated3dbasedfunctionalanalysisoftheleftatriumandclassificationschemesinatrialfibrillation |