Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Benchmark of deep learning algorithms for the automatic screening in electrocardiograms transmitted by implantable cardiac devices

  • Gassa, Narimane
  • Sacristan, Benjamin
  • Zemzemi, Nejib
  • Laborde, Maxime
  • Garrido Oliver, Juan
  • Matencio Perabla, Clara
  • Jimenez-Perez, Guillermo
  • Camara, Oscar
  • Ploux, Sylvain
  • Strik, Marc
  • Bordachar, Pierre
  • Dubois, Remi
Comunicació presentada a 2021 Computing in Cardiology (CinC), celebrat del 13 al 15 de setembre de 2021 a Brno, Txèquia., The objective of this work was to benchmark different deep learning architectures for noise detection against cardiac arrhythmia episodes recorded by pacemakers and implantable cardioverter-defibrillators (PM/ICDs) and transmitted for remote monitoring. Up to now, most signal processing from ICD data has been based on classical hand-crafted algorithms, not AI or DL-based ones. The database consist of PM/ICD data from 805 patients representing a total of 10471 recordings from three different channels: the right ventricular (RV), the right atria (RA), and the shock channel. Four deep learning approaches were trained and optimized to classify PM/ICDs' records as actual ventricular signal vs noise episodes. We evaluated the performance of the different models using the F2 score. Results show that the use of 2D representations of 1D signals led to better performances than the direct use of 1D signals, suggesting that the detection of noise takes advantage of a spectral decomposition of the signal, which remains to be confirmed in other contexts. This study proposes deep learning approaches for the analysis of remote monitoring recordings from PM/ICDs. The detection of noise allows efficient management of this large daily flow of data., This Project has received funding from the European Unions Horizon research and innovation programme under the Marie Skodowska-Curie grant agreement No. 860974 and by the French National Research Agency, grant references ANR- 10-IAHU04- LIRYC and ANR-11-EQPX0030.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Electrocardiographic Imaging in Atrial Fibrillation: Selection of the Optimal Tikhonov-Regularization Parameter

  • Molero-Alabau, Rubén
  • Fambuena-Santos, Carlos
  • Andreu M. Climent|||0000-0002-7260-8811
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
[EN] Electrocardiographic imaging (ECGI) allows evaluating the complexity of atrial fibrillation (AF) signals using the Boundary Element Method and Tikhonov regularization. An accurate ECGI reconstruction is dependent on a proper selection of the regularization parameter (¿). In this work, two ranges of ¿ are explored to evaluate the effect of ¿ on the quality of the ECGI reconstruction. ECGIs of 20 AF patients were computed using zero (T0), first (T1) and second (T2) order Tikhonov regularization (TR) for two ranges of ¿: from 10-9 to 102 and 10-12 to 10-4. Dominant frequencies (DF) and the number of rotors obtained with the two ranges and methods were compared. Zero-order Tikhonov showed to be more robust in ¿ selection for different ¿ ranges. For lower ¿ ranges, higher DF was found (T2, p<0.05) and more rotors were detected for T1 and T2 (p<0.01). Differences between TR methods compared by ¿ ranges showed more variability in derived metrics for lower ¿ range (p<0.01). Optimal ranges for ¿ search differ among T0, T1 and T2. Election of lower than optimal ¿ values result in an increased estimated electrical complexity., This work was supported by: Instituto de Salud Carlos III, and Ministerio de Ciencia, Innovación y Universidades (supported by FEDER Fondo Europeo de Desarrollo Regional PI17/01106 and RYC2018-024346B-750), EIT Health (Activity code 19600, EIT Health is supported by EIT, a body of the European Union), Generalitat Valenciana Grants (ACIF/2020/265) and PersonalizeAF project, which received funding from the European Union¿s Horizon 2020 research and innovation programme under the Marie Skodowska-Curie grant agreement No 860974. This publication reflects only the author's view and the Agency is not responsible for any use that maybe made of the information it contains.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Non-invasive Mechanism Classification and Localization in Supraventricular Cardiac Arrhythmias

  • Sandoval, I.
  • Marques, V. G.
  • Sims, J. A.
  • Rodrigo, M.
  • Salinet, J.
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
[EN] In this study, we investigated the most relevant biomarkers for noninvasive classification and mechanism location in atrial tachycardia (AT), flutter (AFL) and fibrillation (AF). Biomarkers were calculated using noninvasive body surface (BSPM) dominant frequency and phase maps. We used 19 simulations of 567 to 64-lead BSPMs, from which were extracted 32 biomarkers. Biomarker ranking was performed with ANOVA, Kendall and Lasso techniques. The best four biomarkers were identified and used to classify the arrhythmias in all combinations, and the best two used for noninvasive driver localization. Arrhythmia classification accuracy was 94.74%. The feature combination which best distinguish AF from non-AF were mean filament displacement and mean OI, while those that best distinguish AFL from AT were mean and SD of SP distribution. There was good agreement across ranking techniques. Mechanism location accuracy was 78.95%, with the most important biomarkers being percentage SPs within each torso division, and SD of filament histogram cluster area. This study highlights that organization related features well identifies AF and spatial SP distribution discriminate AT from AFL and also it¿s localization., VGM is funded by the European Union's Horizon 2020 research and innovation programme under the Marie Skodowska-Curie grant agreement No. 860974. IS, JAS and JS are supported by grant #2018/25606-2, Sao Paulo Research Foundation (FAPESP).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Detection of Atrial Fibrillation Driver Locations Using CNN and Body Surface Potentials

  • Cámara-Vázquez, Miguel Ángel
  • Hernández-Romero, Ismael
  • Morgado-Reyes, Eduardo
  • Barquero-Pérez, Óscar
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
  • Andreu M. Climent|||0000-0002-7260-8811
[EN] Atrial fibrillation (AF) is characterized by complex and irregular propagation patterns, and AF onset locations and drivers responsible for its perpetuation are main targets for ablation procedures. Several Deep Learningbased methods have proposed to detect AF, but the estimation of the atrial area where the drivers are found is a topic where further research is needed. In this work, we propose to estimate the zone where AF drivers are found from body surface potentials (BSPs) and Convolutional Neural Networks (CNN), modeling a supervised classification problem. Accuracy in the test set was 0.89 when using noisy BSPs (SNR=20dB), while the Cohen¿s Kappa was 0.85. Therefore, the proposed method could help to identify target regions for ablation using a non-invasive procedure, and avoiding the use of ECG Imaging (ECGI)., This work has been partially supported by: Ministerio de Ciencia e Innovacion (PID2019-105032GB-I00), Instituto de Salud Carlos III, and Ministerio de Ciencia, Innovacion y Universidades (supported by FEDER Fondo Europeo de Desarrollo Regional PI17/01106 and RYC2018-024346B-750), Consejeria de Ciencia, Universidades e Innovacion of the Comunidad de Madrid through the program RIS3 (S-2020/L2-622), EIT Health (Activity code 19600, EIT Health is supported by EIT, a body of the European Union) and the European Union's Horizon 2020 research and innovation program under the Marie Skodowska-Curie grant agreement No. 860974.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

An evaluation on the clinical outcome prediction of rotor detection in non-invasive phase maps

  • Fambuena-Santos, Carlos
  • Andreu M. Climent|||0000-0002-7260-8811
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
  • Hernández-Romero, Ismael
  • Molero-Alabau, Rubén
[EN] Phase maps obtained from Electrocardiographic imaging (ECGI) have been used in the past for rotor identification and ablation guidance in atrial fibrillation (AF). In this study, we propose a new rotor detection algorithm and evaluate its potential use for prediction of pulmonary vein isolation (PVI) success. The mean precision and recall of the algorithm were evaluated by using manually annotated ECGI phase maps and resulted in 0.82 and 0.75, respectively. Phase singularities and rotors were then quantified on ECGI signals from 29 patients prior to PVI. A significantly higher concentration of phase singularities (PSs) in the pulmonary veins in patients with a successful PVI was found. Our results suggest that rotorrelated metrics obtained from ECGI derived phase maps contain relevant information to predict clinical outcome in PVI patients., This work was supported by PersonalizeAF project. This project has received funding from the European Union's Horizon 2020 research and innovation program under the Marie Skodowska-Curie grant agreement No 860974.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Benchmark of deep learning algorithms for the automatic screening in electrocardiograms transmitted by implantable cardiac devices

  • Gassa, Narimane
  • Sacristan, Benjamin
  • Zemzemi, Nejib
  • Laborde, Maxime
  • Garrido Oliver, Juan
  • Matencio Perabla, Clara
  • Jimenez-Perez, Guillermo
  • Camara, Oscar
  • Ploux, Sylvain
  • Strik, Marc
  • Bordachar, Pierre
  • Dubois, Remi
Comunicació presentada a 2021 Computing in Cardiology (CinC), celebrat del 13 al 15 de setembre de 2021 a Brno, Txèquia., The objective of this work was to benchmark different deep learning architectures for noise detection against cardiac arrhythmia episodes recorded by pacemakers and implantable cardioverter-defibrillators (PM/ICDs) and transmitted for remote monitoring. Up to now, most signal processing from ICD data has been based on classical hand-crafted algorithms, not AI or DL-based ones. The database consist of PM/ICD data from 805 patients representing a total of 10471 recordings from three different channels: the right ventricular (RV), the right atria (RA), and the shock channel. Four deep learning approaches were trained and optimized to classify PM/ICDs' records as actual ventricular signal vs noise episodes. We evaluated the performance of the different models using the F2 score. Results show that the use of 2D representations of 1D signals led to better performances than the direct use of 1D signals, suggesting that the detection of noise takes advantage of a spectral decomposition of the signal, which remains to be confirmed in other contexts. This study proposes deep learning approaches for the analysis of remote monitoring recordings from PM/ICDs. The detection of noise allows efficient management of this large daily flow of data., This Project has received funding from the European Unions Horizon research and innovation programme under the Marie Skodowska-Curie grant agreement No. 860974 and by the French National Research Agency, grant references ANR- 10-IAHU04- LIRYC and ANR-11-EQPX0030.