Objective: To evaluate accuracy and reproducibility of 2D echocardiography (2DE) left ventricular... more Objective: To evaluate accuracy and reproducibility of 2D echocardiography (2DE) left ventricular (LV) volumes and ejection fraction (LVEF) estimates by Deep Learning (DL) vs. manual contouring and against CMR. Background: 2DE LV manual segmentation for LV volumes and LVEF calculation is time consuming and operator dependent. Methods: A DL-based convolutional network (DL1) was trained on 2DE data from centre A, then evaluated on 171 subjects with a wide range of cardiac conditions (49 healthy) – 31 subjects from centre A (18%) and 140 subjects from centre B (82%) – who underwent 2DE and CMR on the same day. Two senior (A 1 and B 1 ) and one junior (A 2 ) cardiologists manually contoured 2DE end-diastolic (ED) and end-systolic (ES) endocardial borders in the cycle and frames of their choice. Selected frames were automatically segmented by DL1 and two DL algorithms from the literature (DL2 and DL3), applied without adaptation to verify their generalizability to unseen data. Interobser...
Background: Pulmonary transit time (PTT) from first-pass perfusion imaging is a novel parameter t... more Background: Pulmonary transit time (PTT) from first-pass perfusion imaging is a novel parameter to evaluate hemodynamic congestion by cardiac magnetic resonance (cMR). We sought to evaluate the additional prognostic value of PTT in heart failure with reduced ejection fraction over other well-validated predictors of risk including the Meta-Analysis Global Group in Chronic Heart Failure risk score and ischemic cause. Methods: We prospectively followed 410 patients with chronic heart failure with reduced ejection fraction (61±13 years, left ventricular (LV) ejection fraction 24±7%) who underwent a clinical cMR to assess the prognostic value of PTT for a primary endpoint of overall mortality and secondary composite endpoint of cardiovascular death and heart failure hospitalization. Normal reference values of PTT were evaluated in a population of 40 asymptomatic volunteers free of cardiovascular disease. Results PTT was significantly increased in patients with heart failure with reduced ...
European Heart Journal - Cardiovascular Imaging, 2020
Funding Acknowledgements Fondation de Recherche Scientifique Belge FRSM PDR 19488731 BACKGROUND 2... more Funding Acknowledgements Fondation de Recherche Scientifique Belge FRSM PDR 19488731 BACKGROUND 2D-speckle-tracking (ST) echocardiography is currently widely used for estimation of global (G) and regional myocardial deformation. In previous works, we showed good correlation between global longitudinal (LS) and circumferential strain (CS) from one 2DST vendor with cMR-Tagging, however with significant bias between both methods. Also, we found poorer agreement between 2DST and cMR-Tagging on regional basis. However it is unknown how 2DST from other vendors would comparte to cMR tagging. PURPOSE To asssess vendor differences in global and regional strain assessment and compare 1) the agreement of 2 different 2DST softwares for global and regional LS and CS among each other and against cMR-Tagging as reference; and 2) the accuracy of both softwares to detect infarcted segments. METHODS 100 subjects with different cardiac disease (among which 31 with chronic infarct) underwent 2DST and t...
La pratique clinique a été profondément transformée par l'explosion technologique, ces derniè... more La pratique clinique a été profondément transformée par l'explosion technologique, ces dernières décades, des techniques d'imagerie médicale. L'expansion de la radiologie interventionnelle a ainsi rendu possible des procédures dites minimalement invasives au cours desquelles la thérapie est délivrée directement au niveau de la région pathologique via des micro-outils guidés par imagerie à travers le système vasculaire. Des systèmes dits C-arm , générant une imagerie rayons X planaire temps-réelle en faible dose, sont utilisés pour le guidage. Ils ont offert plus récemment la possibilité d'une visualisation tridimensionnelle par le biais d'acquisitions tomographiques. C'est dans ce contexte de reconstruction tomographique que s'inscrivent ces travaux de thèse. Ils s'attèlent en particulier à corriger les artefacts de mouvement dus aux variations temporelles des vaisseaux injectés et se concentrent sur un aspect central de la tomographie, à savoir l'...
Additional file 2: Figure S2. Receiver operating characteristics curve analysis comparing diagnos... more Additional file 2: Figure S2. Receiver operating characteristics curve analysis comparing diagnostic abilities of detection of different degrees ≥ 25%, ≥ 50%, ≥ 75% LGE) of infarcted segments by regional LS, CS, and RS by tagging and the 3 FT software.
allows reconstruction of three-dimensional vascular structures from two spins: the contrast is ac... more allows reconstruction of three-dimensional vascular structures from two spins: the contrast is acquired after injecting vessels with a contrast medium, whereas the mask is acquired in the absence of injection. The vessels are then detected by subtraction of the mask from the contrast. Standard DSRA protocol samples the same set of equiangular-spaced positions for both spins. Due to technical limitations of C-arm systems, streak artifacts degrade the quality of all three reconstructed volumes. Recent developments of compressed sensing have demonstrated that it is possible to recover a signal that is sparse in some basis under limited sampling conditions. In this paper, we propose to improve the reconstruction quality of non-sparse volumes when there exists a sparse combination of these volumes. To this purpose, we develop an extension of iterative filtered backprojection that jointly reconstructs the mask and contrast volumes via ℓ1-minimization of sparse priors. A dedicated protocol...
Few data exist concerning the right ventricular (RV) physiological adaptation in Americanstyle fo... more Few data exist concerning the right ventricular (RV) physiological adaptation in Americanstyle football (ASF) athletes. We aimed to analyze the RV global and regional responses among ASF-trained athletes. Fifty-nine (20 linemen and 39 non-linemen) ASF athletes were studied before and after inter-seasonal training. During this period, which lasted 7 months, all athletes were exposed to combined dynamic and static exercises. Cardiac longitudinal changes were examined using threedimensional transthoracic echocardiography. A computational method based on geodesic distances was applied to volumetrically parcellate the RV into apical, outlet, and inlet regions. RV global and regional end-diastolic volumes increased significantly and similarly in linemen and non-linemen after training, with predominant changes in the apex and outlet regions. RV global and regional ejection fractions were preserved. Morphological changes were uniformly distributed among the four cardiac chambers, and it was...
Functional Imaging and Modelling of the Heart, 2017
In this paper, we capture patterns of response to cardiac stress-testing using a multiview dimens... more In this paper, we capture patterns of response to cardiac stress-testing using a multiview dimensionality reduction technique that allows the compact representation of patient response to stress, regarding multiple features over consecutive cycles, as a low-dimensional trajectory. In this low-dimensional space, patients can be compared and clustered in distinct healthy and pathological responses, and the patterns that characterize each of them can be reconstructed. Experiments were performed on (a) synthetic data simulating different types of response and (b) a real acquisition during a cold pressor test. Results show that the proposed approach allows the clustering of healthy and pathological responses, as well as the reconstruction of characteristic patterns of such responses, in terms of multiple features of interest.
Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges, 2018
The availability of large scale databases containing imaging and non-imaging data, such as the UK... more The availability of large scale databases containing imaging and non-imaging data, such as the UK Biobank, represents an opportunity to improve our understanding of healthy and diseased bodily function. Cardiac motion atlases provide a space of reference in which the motion fields of a cohort of subjects can be directly compared. In this work, a cardiac motion atlas is built from cine MR data from the UK Biobank (≈ 6000 subjects). Two automated quality control strategies are proposed to reject subjects with insufficient image quality. Based on the atlas, three dimensionality reduction algorithms are evaluated to learn data-driven cardiac motion descriptors, and statistical methods used to study the association between these descriptors and non-imaging data. Results show a positive correlation between the atlas motion descriptors and body fat percentage, basal metabolic rate, hypertension, smoking status and alcohol intake frequency. The proposed method outperforms the ability to identify changes in cardiac function due to these known cardiovascular risk factors compared to ejection fraction, the most commonly used descriptor of cardiac function. In conclusion, this work represents a framework for further investigation of the factors influencing cardiac health.
European Heart Journal - Cardiovascular Imaging, 2020
Funding Acknowledgements Philips BACKGROUND Developing new training tools for TransThoracic Echoc... more Funding Acknowledgements Philips BACKGROUND Developing new training tools for TransThoracic Echocardiography (TTE) is more important than ever, as the use of ultrasound expands with the advent of mobile devices, both reducing costs and increasing the number of sites and operators. Two major challenges are the lack of experts to meet the growing demand for training and the risk of unnecessary examinations and misdiagnosis by users who lack proper training. PURPOSE To evaluate Artificial Intelligence (AI)-assisted TTE for assessing and improving novices" echocardiography skills. METHODS AI-assisted TTE relies on real-time analysis of the ultrasound stream by AI algorithms (e.g. for automated view recognition) to provide adaptive feedback to the user. It was compared to standard TTE in a prospective study including 40 medical students with no prior ultrasound experience ("novices") and 40 healthy volunteers of varying echogenicity. Novices received a standardized 10-minu...
European Heart Journal - Cardiovascular Imaging, 2020
Funding Acknowledgements EU Horizon 2020 (642676-Cardiofunxion); Spanish Ministry of Economy and ... more Funding Acknowledgements EU Horizon 2020 (642676-Cardiofunxion); Spanish Ministry of Economy and Competitiveness (TIN2014-52923-R); Maria de Maeztu Programme (MDM-2015-0502) Background Although clinical guidelines provide valuable help in the management of aortic stenosis (AS), uncertainty remains regarding their strict application in the assessment of stenosis severity, prognosis, and indication for valve intervention, in particular in low-gradient or asymptomatic AS. Evidence regarding the threshold values for aortic valve area (AVA), peak transvalvular velocity (Vmax), and mean transaortic pressure gradient (ΔPm) remains discordant. Interpretable machine learning (ML) approaches have the potential to generate guideline recommendations directly based on (location-specific) data. Purpose To evaluate the use of interpretable ML for risk stratification of AS, in particular to assess the expected improvement with aortic valve intervention (AVI). Methods We conducted a retrospective an...
IEEE Transactions on Knowledge and Data Engineering, 2020
Clinical decision requires reasoning in the presence of imperfect data. DTs are a well-known deci... more Clinical decision requires reasoning in the presence of imperfect data. DTs are a well-known decision support tool, owing to their interpretability, fundamental in safety-critical contexts such as medical diagnosis. However, learning DTs from uncertain data leads to poor generalization, and generating predictions for uncertain data hinders prediction accuracy. Several methods have suggested the potential of probabilistic decisions at the internal nodes in making DTs robust to uncertainty. Some approaches only employ probabilistic thresholds during evaluation. Others also consider the uncertainty in the learning phase, at the expense of increased computational complexity or reduced interpretability. The existing methods have not clarified the merit of a probabilistic approach in the distinct phases of DT learning, nor when the uncertainty is present in the training or the test data. We present a probabilistic DT approach that models measurement uncertainty as a noise distribution, independently realized: (1) when searching for the split thresholds, (2) when splitting the training instances, and (3) when generating predictions for unseen data. The soft training approaches (1, 2) achieved a regularizing effect, leading to significant reductions in DT size, while maintaining accuracy, for increased noise. Soft evaluation (3) showed no benefit in handling noise.
If citing, it is advised that you check and use the publisher's definitive version for pagination... more If citing, it is advised that you check and use the publisher's definitive version for pagination, volume/issue, and date of publication details. And where the final published version is provided on the Research Portal, if citing you are again advised to check the publisher's website for any subsequent corrections.
European Heart Journal - Cardiovascular Imaging, 2019
Funding Acknowledgements: Fond national de la recherche scientifique (FNRS) Background: Right ven... more Funding Acknowledgements: Fond national de la recherche scientifique (FNRS) Background: Right ventricular (RV) ejection fraction and hemodynamic congestion are known as powerful predictor of mortality in HF-rEF. Pulmonary transit time (PTT) assessed by cMR is a novel parameter, which reflects multiple indicators of cardiopulmonary status, including not only left ventricular(LV) and RV function but also hemodynamic congestion. Purpose: We sought to explore the prognostic value of the PTT above well-known risk factor for predicting outcomes in HF-rEF in direct comparison with cardiac function assessed either by the conventional cMR-systolic parameters or by cMR-feature tracking (FT). Methods: 401 patients in sinus rhythm with a LVEF< 35% (age 61 ± 13 years; 25% female) underwent a cMR and an echocardiography. Patients were followed for a composite endpoint of CV death and HF hospitalization. Results: Average cMR-LVEF was 23% ± 7%, average cMR-RVEF was 43 ± 15%, average cMR-FT-RVGLS was-12 ± 4.4%, average cMR-FT-LVGLS was-6.5 ± 2.5% average estimated systolic pulmonary pressure (eSPAP) was 33 ± 12mmHg and PTT was 11± 6s. After a median follow-up of 6 years, 191 (48%) patients reached the composite endpoint. In univariate cox regression, age, female sex, ischemic cardiomyopathy, diabetes, NYHA class III-IV, eSPAP> 40mmHg, E/A ratio, e/e'ratio, cMR-RVEF, LVEF, LV scar, PTT, GFR, beta blockers and diuretics were associated with the composite endpoint. For the multivariate analysis, a baseline model was created where age, female sex, ischemic etiology, diabetes, eSPAP > 40mmHg, diuretics, beta blockers were found to be significantly associated with the endpoint.
2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), 2012
Digital Subtraction Rotational Angiography (DSRA) is a clinical protocol that allows three-dimens... more Digital Subtraction Rotational Angiography (DSRA) is a clinical protocol that allows three-dimensional (3D) visualization of vasculature during minimally invasive procedures. C-arm systems that are used to generate 3D reconstructions in interventional radiology have limited sampling rate and thus, contrast resolution. To address this particular subsampling problem, we propose a novel iterative reconstruction algorithm based on compressed sensing. To this purpose, we exploit both spatial and temporal sparsity of DSRA. For computational efficiency, we use a proximal implementation that accommodates multiple 1-penalties. Experiments on both simulated and clinical data confirm the relevance of our strategy for reducing subsampling streak artifacts.
Additional file 1: Figure S1. Bullseye graphs showing the absolute bias at regional level between... more Additional file 1: Figure S1. Bullseye graphs showing the absolute bias at regional level between FT and Tagging for LS (a) CS (b) and RS (c) in the study population.
In this paper, we address three-dimensional tomographic reconstruction of rotational angiography ... more In this paper, we address three-dimensional tomographic reconstruction of rotational angiography acquisitions. In clinical routine, angular subsampling commonly occurs, due to the technical limitations of C-arm systems or possible improper injection. Standard methods such as filtered backprojection yield a reconstruction that is deteriorated by sampling artifacts, which potentially hampers medical interpretation. Recent developments of compressed sensing have demonstrated that it is possible to significantly improve reconstruction of subsampled datasets by generating sparse approximations through l1-penalized minimization. Based on these results, we present an extension of the iterative filtered backprojection that includes a sparsity constraint called soft background subtraction. This approach is shown to provide sampling artifact reduction when reconstructing sparse objects, and more interestingly, when reconstructing sparse objects over a non-sparse background. The relevance of o...
Digital Subtraction Rotational Angiography (DSRA) allows reconstruction of three-dimensional vasc... more Digital Subtraction Rotational Angiography (DSRA) allows reconstruction of three-dimensional vascular structures from two spins: the contrast is acquired after injecting vessels with a contrast medium, whereas the mask is acquired in the absence of injection. The vessels are then detected by subtraction of the mask from the contrast. Standard DSRA protocol samples the same set of equiangular-spaced positions for both spins. Due to technical limitations of C-arm systems, streak artifacts degrade the quality of all three reconstructed volumes. Recent developments of compressed sensing have demonstrated that it is possible to recover a signal that is sparse in some basis under limited sampling conditions. In this paper, we propose to improve the reconstruction quality of non-sparse volumes when there exists a sparse combination of these volumes. To this purpose, we develop an extension of iterative filtered backprojection that jointly reconstructs the mask and contrast volumes via '...
Objective: To evaluate accuracy and reproducibility of 2D echocardiography (2DE) left ventricular... more Objective: To evaluate accuracy and reproducibility of 2D echocardiography (2DE) left ventricular (LV) volumes and ejection fraction (LVEF) estimates by Deep Learning (DL) vs. manual contouring and against CMR. Background: 2DE LV manual segmentation for LV volumes and LVEF calculation is time consuming and operator dependent. Methods: A DL-based convolutional network (DL1) was trained on 2DE data from centre A, then evaluated on 171 subjects with a wide range of cardiac conditions (49 healthy) – 31 subjects from centre A (18%) and 140 subjects from centre B (82%) – who underwent 2DE and CMR on the same day. Two senior (A 1 and B 1 ) and one junior (A 2 ) cardiologists manually contoured 2DE end-diastolic (ED) and end-systolic (ES) endocardial borders in the cycle and frames of their choice. Selected frames were automatically segmented by DL1 and two DL algorithms from the literature (DL2 and DL3), applied without adaptation to verify their generalizability to unseen data. Interobser...
Background: Pulmonary transit time (PTT) from first-pass perfusion imaging is a novel parameter t... more Background: Pulmonary transit time (PTT) from first-pass perfusion imaging is a novel parameter to evaluate hemodynamic congestion by cardiac magnetic resonance (cMR). We sought to evaluate the additional prognostic value of PTT in heart failure with reduced ejection fraction over other well-validated predictors of risk including the Meta-Analysis Global Group in Chronic Heart Failure risk score and ischemic cause. Methods: We prospectively followed 410 patients with chronic heart failure with reduced ejection fraction (61±13 years, left ventricular (LV) ejection fraction 24±7%) who underwent a clinical cMR to assess the prognostic value of PTT for a primary endpoint of overall mortality and secondary composite endpoint of cardiovascular death and heart failure hospitalization. Normal reference values of PTT were evaluated in a population of 40 asymptomatic volunteers free of cardiovascular disease. Results PTT was significantly increased in patients with heart failure with reduced ...
European Heart Journal - Cardiovascular Imaging, 2020
Funding Acknowledgements Fondation de Recherche Scientifique Belge FRSM PDR 19488731 BACKGROUND 2... more Funding Acknowledgements Fondation de Recherche Scientifique Belge FRSM PDR 19488731 BACKGROUND 2D-speckle-tracking (ST) echocardiography is currently widely used for estimation of global (G) and regional myocardial deformation. In previous works, we showed good correlation between global longitudinal (LS) and circumferential strain (CS) from one 2DST vendor with cMR-Tagging, however with significant bias between both methods. Also, we found poorer agreement between 2DST and cMR-Tagging on regional basis. However it is unknown how 2DST from other vendors would comparte to cMR tagging. PURPOSE To asssess vendor differences in global and regional strain assessment and compare 1) the agreement of 2 different 2DST softwares for global and regional LS and CS among each other and against cMR-Tagging as reference; and 2) the accuracy of both softwares to detect infarcted segments. METHODS 100 subjects with different cardiac disease (among which 31 with chronic infarct) underwent 2DST and t...
La pratique clinique a été profondément transformée par l'explosion technologique, ces derniè... more La pratique clinique a été profondément transformée par l'explosion technologique, ces dernières décades, des techniques d'imagerie médicale. L'expansion de la radiologie interventionnelle a ainsi rendu possible des procédures dites minimalement invasives au cours desquelles la thérapie est délivrée directement au niveau de la région pathologique via des micro-outils guidés par imagerie à travers le système vasculaire. Des systèmes dits C-arm , générant une imagerie rayons X planaire temps-réelle en faible dose, sont utilisés pour le guidage. Ils ont offert plus récemment la possibilité d'une visualisation tridimensionnelle par le biais d'acquisitions tomographiques. C'est dans ce contexte de reconstruction tomographique que s'inscrivent ces travaux de thèse. Ils s'attèlent en particulier à corriger les artefacts de mouvement dus aux variations temporelles des vaisseaux injectés et se concentrent sur un aspect central de la tomographie, à savoir l'...
Additional file 2: Figure S2. Receiver operating characteristics curve analysis comparing diagnos... more Additional file 2: Figure S2. Receiver operating characteristics curve analysis comparing diagnostic abilities of detection of different degrees ≥ 25%, ≥ 50%, ≥ 75% LGE) of infarcted segments by regional LS, CS, and RS by tagging and the 3 FT software.
allows reconstruction of three-dimensional vascular structures from two spins: the contrast is ac... more allows reconstruction of three-dimensional vascular structures from two spins: the contrast is acquired after injecting vessels with a contrast medium, whereas the mask is acquired in the absence of injection. The vessels are then detected by subtraction of the mask from the contrast. Standard DSRA protocol samples the same set of equiangular-spaced positions for both spins. Due to technical limitations of C-arm systems, streak artifacts degrade the quality of all three reconstructed volumes. Recent developments of compressed sensing have demonstrated that it is possible to recover a signal that is sparse in some basis under limited sampling conditions. In this paper, we propose to improve the reconstruction quality of non-sparse volumes when there exists a sparse combination of these volumes. To this purpose, we develop an extension of iterative filtered backprojection that jointly reconstructs the mask and contrast volumes via ℓ1-minimization of sparse priors. A dedicated protocol...
Few data exist concerning the right ventricular (RV) physiological adaptation in Americanstyle fo... more Few data exist concerning the right ventricular (RV) physiological adaptation in Americanstyle football (ASF) athletes. We aimed to analyze the RV global and regional responses among ASF-trained athletes. Fifty-nine (20 linemen and 39 non-linemen) ASF athletes were studied before and after inter-seasonal training. During this period, which lasted 7 months, all athletes were exposed to combined dynamic and static exercises. Cardiac longitudinal changes were examined using threedimensional transthoracic echocardiography. A computational method based on geodesic distances was applied to volumetrically parcellate the RV into apical, outlet, and inlet regions. RV global and regional end-diastolic volumes increased significantly and similarly in linemen and non-linemen after training, with predominant changes in the apex and outlet regions. RV global and regional ejection fractions were preserved. Morphological changes were uniformly distributed among the four cardiac chambers, and it was...
Functional Imaging and Modelling of the Heart, 2017
In this paper, we capture patterns of response to cardiac stress-testing using a multiview dimens... more In this paper, we capture patterns of response to cardiac stress-testing using a multiview dimensionality reduction technique that allows the compact representation of patient response to stress, regarding multiple features over consecutive cycles, as a low-dimensional trajectory. In this low-dimensional space, patients can be compared and clustered in distinct healthy and pathological responses, and the patterns that characterize each of them can be reconstructed. Experiments were performed on (a) synthetic data simulating different types of response and (b) a real acquisition during a cold pressor test. Results show that the proposed approach allows the clustering of healthy and pathological responses, as well as the reconstruction of characteristic patterns of such responses, in terms of multiple features of interest.
Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges, 2018
The availability of large scale databases containing imaging and non-imaging data, such as the UK... more The availability of large scale databases containing imaging and non-imaging data, such as the UK Biobank, represents an opportunity to improve our understanding of healthy and diseased bodily function. Cardiac motion atlases provide a space of reference in which the motion fields of a cohort of subjects can be directly compared. In this work, a cardiac motion atlas is built from cine MR data from the UK Biobank (≈ 6000 subjects). Two automated quality control strategies are proposed to reject subjects with insufficient image quality. Based on the atlas, three dimensionality reduction algorithms are evaluated to learn data-driven cardiac motion descriptors, and statistical methods used to study the association between these descriptors and non-imaging data. Results show a positive correlation between the atlas motion descriptors and body fat percentage, basal metabolic rate, hypertension, smoking status and alcohol intake frequency. The proposed method outperforms the ability to identify changes in cardiac function due to these known cardiovascular risk factors compared to ejection fraction, the most commonly used descriptor of cardiac function. In conclusion, this work represents a framework for further investigation of the factors influencing cardiac health.
European Heart Journal - Cardiovascular Imaging, 2020
Funding Acknowledgements Philips BACKGROUND Developing new training tools for TransThoracic Echoc... more Funding Acknowledgements Philips BACKGROUND Developing new training tools for TransThoracic Echocardiography (TTE) is more important than ever, as the use of ultrasound expands with the advent of mobile devices, both reducing costs and increasing the number of sites and operators. Two major challenges are the lack of experts to meet the growing demand for training and the risk of unnecessary examinations and misdiagnosis by users who lack proper training. PURPOSE To evaluate Artificial Intelligence (AI)-assisted TTE for assessing and improving novices" echocardiography skills. METHODS AI-assisted TTE relies on real-time analysis of the ultrasound stream by AI algorithms (e.g. for automated view recognition) to provide adaptive feedback to the user. It was compared to standard TTE in a prospective study including 40 medical students with no prior ultrasound experience ("novices") and 40 healthy volunteers of varying echogenicity. Novices received a standardized 10-minu...
European Heart Journal - Cardiovascular Imaging, 2020
Funding Acknowledgements EU Horizon 2020 (642676-Cardiofunxion); Spanish Ministry of Economy and ... more Funding Acknowledgements EU Horizon 2020 (642676-Cardiofunxion); Spanish Ministry of Economy and Competitiveness (TIN2014-52923-R); Maria de Maeztu Programme (MDM-2015-0502) Background Although clinical guidelines provide valuable help in the management of aortic stenosis (AS), uncertainty remains regarding their strict application in the assessment of stenosis severity, prognosis, and indication for valve intervention, in particular in low-gradient or asymptomatic AS. Evidence regarding the threshold values for aortic valve area (AVA), peak transvalvular velocity (Vmax), and mean transaortic pressure gradient (ΔPm) remains discordant. Interpretable machine learning (ML) approaches have the potential to generate guideline recommendations directly based on (location-specific) data. Purpose To evaluate the use of interpretable ML for risk stratification of AS, in particular to assess the expected improvement with aortic valve intervention (AVI). Methods We conducted a retrospective an...
IEEE Transactions on Knowledge and Data Engineering, 2020
Clinical decision requires reasoning in the presence of imperfect data. DTs are a well-known deci... more Clinical decision requires reasoning in the presence of imperfect data. DTs are a well-known decision support tool, owing to their interpretability, fundamental in safety-critical contexts such as medical diagnosis. However, learning DTs from uncertain data leads to poor generalization, and generating predictions for uncertain data hinders prediction accuracy. Several methods have suggested the potential of probabilistic decisions at the internal nodes in making DTs robust to uncertainty. Some approaches only employ probabilistic thresholds during evaluation. Others also consider the uncertainty in the learning phase, at the expense of increased computational complexity or reduced interpretability. The existing methods have not clarified the merit of a probabilistic approach in the distinct phases of DT learning, nor when the uncertainty is present in the training or the test data. We present a probabilistic DT approach that models measurement uncertainty as a noise distribution, independently realized: (1) when searching for the split thresholds, (2) when splitting the training instances, and (3) when generating predictions for unseen data. The soft training approaches (1, 2) achieved a regularizing effect, leading to significant reductions in DT size, while maintaining accuracy, for increased noise. Soft evaluation (3) showed no benefit in handling noise.
If citing, it is advised that you check and use the publisher's definitive version for pagination... more If citing, it is advised that you check and use the publisher's definitive version for pagination, volume/issue, and date of publication details. And where the final published version is provided on the Research Portal, if citing you are again advised to check the publisher's website for any subsequent corrections.
European Heart Journal - Cardiovascular Imaging, 2019
Funding Acknowledgements: Fond national de la recherche scientifique (FNRS) Background: Right ven... more Funding Acknowledgements: Fond national de la recherche scientifique (FNRS) Background: Right ventricular (RV) ejection fraction and hemodynamic congestion are known as powerful predictor of mortality in HF-rEF. Pulmonary transit time (PTT) assessed by cMR is a novel parameter, which reflects multiple indicators of cardiopulmonary status, including not only left ventricular(LV) and RV function but also hemodynamic congestion. Purpose: We sought to explore the prognostic value of the PTT above well-known risk factor for predicting outcomes in HF-rEF in direct comparison with cardiac function assessed either by the conventional cMR-systolic parameters or by cMR-feature tracking (FT). Methods: 401 patients in sinus rhythm with a LVEF< 35% (age 61 ± 13 years; 25% female) underwent a cMR and an echocardiography. Patients were followed for a composite endpoint of CV death and HF hospitalization. Results: Average cMR-LVEF was 23% ± 7%, average cMR-RVEF was 43 ± 15%, average cMR-FT-RVGLS was-12 ± 4.4%, average cMR-FT-LVGLS was-6.5 ± 2.5% average estimated systolic pulmonary pressure (eSPAP) was 33 ± 12mmHg and PTT was 11± 6s. After a median follow-up of 6 years, 191 (48%) patients reached the composite endpoint. In univariate cox regression, age, female sex, ischemic cardiomyopathy, diabetes, NYHA class III-IV, eSPAP> 40mmHg, E/A ratio, e/e'ratio, cMR-RVEF, LVEF, LV scar, PTT, GFR, beta blockers and diuretics were associated with the composite endpoint. For the multivariate analysis, a baseline model was created where age, female sex, ischemic etiology, diabetes, eSPAP > 40mmHg, diuretics, beta blockers were found to be significantly associated with the endpoint.
2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), 2012
Digital Subtraction Rotational Angiography (DSRA) is a clinical protocol that allows three-dimens... more Digital Subtraction Rotational Angiography (DSRA) is a clinical protocol that allows three-dimensional (3D) visualization of vasculature during minimally invasive procedures. C-arm systems that are used to generate 3D reconstructions in interventional radiology have limited sampling rate and thus, contrast resolution. To address this particular subsampling problem, we propose a novel iterative reconstruction algorithm based on compressed sensing. To this purpose, we exploit both spatial and temporal sparsity of DSRA. For computational efficiency, we use a proximal implementation that accommodates multiple 1-penalties. Experiments on both simulated and clinical data confirm the relevance of our strategy for reducing subsampling streak artifacts.
Additional file 1: Figure S1. Bullseye graphs showing the absolute bias at regional level between... more Additional file 1: Figure S1. Bullseye graphs showing the absolute bias at regional level between FT and Tagging for LS (a) CS (b) and RS (c) in the study population.
In this paper, we address three-dimensional tomographic reconstruction of rotational angiography ... more In this paper, we address three-dimensional tomographic reconstruction of rotational angiography acquisitions. In clinical routine, angular subsampling commonly occurs, due to the technical limitations of C-arm systems or possible improper injection. Standard methods such as filtered backprojection yield a reconstruction that is deteriorated by sampling artifacts, which potentially hampers medical interpretation. Recent developments of compressed sensing have demonstrated that it is possible to significantly improve reconstruction of subsampled datasets by generating sparse approximations through l1-penalized minimization. Based on these results, we present an extension of the iterative filtered backprojection that includes a sparsity constraint called soft background subtraction. This approach is shown to provide sampling artifact reduction when reconstructing sparse objects, and more interestingly, when reconstructing sparse objects over a non-sparse background. The relevance of o...
Digital Subtraction Rotational Angiography (DSRA) allows reconstruction of three-dimensional vasc... more Digital Subtraction Rotational Angiography (DSRA) allows reconstruction of three-dimensional vascular structures from two spins: the contrast is acquired after injecting vessels with a contrast medium, whereas the mask is acquired in the absence of injection. The vessels are then detected by subtraction of the mask from the contrast. Standard DSRA protocol samples the same set of equiangular-spaced positions for both spins. Due to technical limitations of C-arm systems, streak artifacts degrade the quality of all three reconstructed volumes. Recent developments of compressed sensing have demonstrated that it is possible to recover a signal that is sparse in some basis under limited sampling conditions. In this paper, we propose to improve the reconstruction quality of non-sparse volumes when there exists a sparse combination of these volumes. To this purpose, we develop an extension of iterative filtered backprojection that jointly reconstructs the mask and contrast volumes via '...
Uploads
Papers by Hélène Langet