Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662933
Furkan Aldemir, Y. S. Dogrusoz
Bayesian Maximum a Posteriori (MAP) estimation has been successfully applied to electrocardiographic imaging (ECGI). However, in most studies, MAP deals only with the measurement noise and ignores the forward model errors. In this study, we incorporated model uncertainty in the MAP formulation to improve the inverse reconstructions. Measured electrograms (EGM) from the University of Utah were used to form training and test datasets. Body surface potential (BSP) measurements were simulated at 30 dB SNR. The inverse problem was solved using MAP estimation. The training dataset was used to define the prior probability function (pdf). Both the measurement noise and model error were assumed to be uncorrelated with the EGMs. Model error was introduced as shift in the heart position and scaling of the heart size. Three model error pdfs were considered: no compensation (model error is assumed as zero in the solution); model error is modeled as independent and identically distributed (IID) and correlated across leads (CORR). For IID and CORR, pdf was estimated based on all geometry disturbances. Results were evaluated using spatial (sCC) and temporal (tCC) correlation coefficients. These results showed that including model errors in the MAP formulation, even in a simple form such as the IID, improved the reconstructions over ignoring them.
{"title":"Compensation of Model Errors in Electrocardiographic Imaging Using Bayesian Estimation","authors":"Furkan Aldemir, Y. S. Dogrusoz","doi":"10.23919/cinc53138.2021.9662933","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662933","url":null,"abstract":"Bayesian Maximum a Posteriori (MAP) estimation has been successfully applied to electrocardiographic imaging (ECGI). However, in most studies, MAP deals only with the measurement noise and ignores the forward model errors. In this study, we incorporated model uncertainty in the MAP formulation to improve the inverse reconstructions. Measured electrograms (EGM) from the University of Utah were used to form training and test datasets. Body surface potential (BSP) measurements were simulated at 30 dB SNR. The inverse problem was solved using MAP estimation. The training dataset was used to define the prior probability function (pdf). Both the measurement noise and model error were assumed to be uncorrelated with the EGMs. Model error was introduced as shift in the heart position and scaling of the heart size. Three model error pdfs were considered: no compensation (model error is assumed as zero in the solution); model error is modeled as independent and identically distributed (IID) and correlated across leads (CORR). For IID and CORR, pdf was estimated based on all geometry disturbances. Results were evaluated using spatial (sCC) and temporal (tCC) correlation coefficients. These results showed that including model errors in the MAP formulation, even in a simple form such as the IID, improved the reconstructions over ignoring them.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115005733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662896
Andony Arrieula, H. Cochet, P. Jaïs, M. Haïssaguerre, N. Zemzemi, M. Potse
Premature ventricular contraction (PVC) can induce ventricular tachycardia or ventricular fibrillation. Drug-resistant PVCs can be cured by catheter ablation, but the accurate localization that this requires can be difficult and time-consuming. An accurate pre-procedural estimate of the origin could make the procedure more efficient. We propose a machine-learning method for accurate pre-procedural origin estimation. It uses a database of paced 12-lead ECGs with known pacing locations and presents its results on an imaging-based model of the patient. The method was tested using 7 realistic heart-torso models with hundreds of PVCs everywhere in the ventricles. We found that increasing the number of patients in the training database increased the accuracy of the predictions. The optimal number of pacing sites per patient in the training dataset was about 25, resulting in a prediction error around 15 mm. We conclude that our method gives a good indication to clinicians to efficiently start a pace-mapping during a catheter ablation procedure. It can be complemented with an intra-procedural method that uses the patient's own paced beats to refine the prediction.
{"title":"In-Silico Data Based Machine Learning Technique Predicts Premature Ventricular Contraction Origin Coordinates","authors":"Andony Arrieula, H. Cochet, P. Jaïs, M. Haïssaguerre, N. Zemzemi, M. Potse","doi":"10.23919/cinc53138.2021.9662896","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662896","url":null,"abstract":"Premature ventricular contraction (PVC) can induce ventricular tachycardia or ventricular fibrillation. Drug-resistant PVCs can be cured by catheter ablation, but the accurate localization that this requires can be difficult and time-consuming. An accurate pre-procedural estimate of the origin could make the procedure more efficient. We propose a machine-learning method for accurate pre-procedural origin estimation. It uses a database of paced 12-lead ECGs with known pacing locations and presents its results on an imaging-based model of the patient. The method was tested using 7 realistic heart-torso models with hundreds of PVCs everywhere in the ventricles. We found that increasing the number of patients in the training database increased the accuracy of the predictions. The optimal number of pacing sites per patient in the training dataset was about 25, resulting in a prediction error around 15 mm. We conclude that our method gives a good indication to clinicians to efficiently start a pace-mapping during a catheter ablation procedure. It can be complemented with an intra-procedural method that uses the patient's own paced beats to refine the prediction.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115117312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662682
Matthieu Scherpf, Hannes Ernst, Leo Misera, H. Malberg, Martin Schmidt
Imaging photoplethysmography (iPPG) is a camera-based approach for the remote measurement of superficial tissue perfusion most commonly applied to facial video recordings. Since only tissue contains information about perfusion, skin detection is a necessary processing step. Several approaches for the detection of skin pixels in video recordings have been developed, e.g. using color thresholds. Within this work we present a deep learning based approach capable of combining color and morphology information, which makes the skin detection robust against different illumination conditions. We evaluated our new approach using two datasets with 182 individuals of different gender, age, skin tone and illumination conditions. Our approach outperformed state-of-the-art algorithms or yielded at least comparable results (mean absolute error of estimated pulse rate improved by up to 68 %). The method presented allows more accurate assessment of superficial tissue perfusion with iPPG.
{"title":"Skin Segmentation for Imaging Photoplethysmography Using a Specialized Deep Learning Approach","authors":"Matthieu Scherpf, Hannes Ernst, Leo Misera, H. Malberg, Martin Schmidt","doi":"10.23919/cinc53138.2021.9662682","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662682","url":null,"abstract":"Imaging photoplethysmography (iPPG) is a camera-based approach for the remote measurement of superficial tissue perfusion most commonly applied to facial video recordings. Since only tissue contains information about perfusion, skin detection is a necessary processing step. Several approaches for the detection of skin pixels in video recordings have been developed, e.g. using color thresholds. Within this work we present a deep learning based approach capable of combining color and morphology information, which makes the skin detection robust against different illumination conditions. We evaluated our new approach using two datasets with 182 individuals of different gender, age, skin tone and illumination conditions. Our approach outperformed state-of-the-art algorithms or yielded at least comparable results (mean absolute error of estimated pulse rate improved by up to 68 %). The method presented allows more accurate assessment of superficial tissue perfusion with iPPG.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115598553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662895
Paul Samuel P. Ignacio
We explore whether specific time-varying shape characteristics of electrocardiograms can be tapped to inform computational approaches in classifying cardiac abnormalities. In particular, we train a random forest classifier on features derived from relative differences between algebraically-computable topological signatures of consecutive segments within ECGs. We convert segments of ECGs as point cloud embeddings in high-dimensional space, extract their topological summaries, and compare these via statistical descriptors and different metrics. As part of the PhysioNet/Computing in Cardiology Challenge 2021, we (Team Cordi-Ak) test this approach across full-and reduced-lead ECGs. Using the Challenge's evaluation metric, our classifiers received scores of -0.06, -0.07, -0.08, -0.08, and -0.10 (consistently ranked 35th out of 39 official entries) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set.
我们探索是否可以利用心电图的特定时变形状特征来通知心脏异常分类的计算方法。特别是，我们训练了一个随机森林分类器，该分类器的特征来源于ecg内连续段的代数可计算拓扑特征之间的相对差异。我们将脑电图片段转换为高维空间中的点云嵌入，提取其拓扑摘要，并通过统计描述符和不同度量对其进行比较。作为PhysioNet/Computing in Cardiology Challenge 2021的一部分，我们(Team Cordi-Ak)在全导联和低导联心电图上测试了这种方法。使用挑战的评估指标，我们的分类器在隐藏测试集的12导、6导、4导、3导和2导版本中获得了-0.06、-0.07、-0.08、-0.08和-0.10的分数(在39个正式参赛作品中始终排名第35位)。
{"title":"Leveraging Period-Specific Variations in ECG Topology for Classification Tasks","authors":"Paul Samuel P. Ignacio","doi":"10.23919/cinc53138.2021.9662895","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662895","url":null,"abstract":"We explore whether specific time-varying shape characteristics of electrocardiograms can be tapped to inform computational approaches in classifying cardiac abnormalities. In particular, we train a random forest classifier on features derived from relative differences between algebraically-computable topological signatures of consecutive segments within ECGs. We convert segments of ECGs as point cloud embeddings in high-dimensional space, extract their topological summaries, and compare these via statistical descriptors and different metrics. As part of the PhysioNet/Computing in Cardiology Challenge 2021, we (Team Cordi-Ak) test this approach across full-and reduced-lead ECGs. Using the Challenge's evaluation metric, our classifiers received scores of -0.06, -0.07, -0.08, -0.08, and -0.10 (consistently ranked 35th out of 39 official entries) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115647198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662899
P. Sundararajan, Kevin Moses, C. Potes, S. Parvaneh
ECG is an essential tool for the clinical diagnosis of cardiac electrical abnormalities. As part of the PhysioNet/Computing in Cardiology Challenge 2021, eight and two folds from the 10-folds iterative splitting of public training data set were used as in-house training and internal validation sets. We used extracted features from RandOm Convolutional KErnel Transforms (ROCKETs) with a multilabel classification using XGBoost to predict cardiac abnormalities. Our team, LINC, developed an approach with minimal pre-processing (e.g., resampling data to 500Hz) and with no QRS detection or deep neural network design, which led to promising performance on the internal validation set. We didn't receive the official scores for the validation and test sets, because our entry failed during training in the official phase as we submitted an incomplete entry. Our classifiers received scores of 0.504, 0.466, 0.459, 0.458, and 0.438 for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions on the internal validation set with the challenge evaluation metric (10 seconds ECG).
心电图是临床诊断心电异常的重要工具。作为PhysioNet/Computing in Cardiology Challenge 2021的一部分，公共训练数据集的10倍迭代分割中的8倍和2倍被用作内部训练和内部验证集。我们使用从随机卷积核变换(RandOm Convolutional KErnel Transforms, ROCKETs)中提取的特征，并使用XGBoost进行多标签分类来预测心脏异常。我们的团队，LINC，开发了一种预处理最少的方法(例如，将数据重新采样到500Hz)，没有QRS检测或深度神经网络设计，这导致了内部验证集上有希望的性能。我们没有收到验证和测试集的官方分数，因为我们在官方阶段的训练中提交了一个不完整的条目，导致我们的条目失败。在挑战评估指标(10秒ECG)的内部验证集上，我们的分类器对12导联、6导联、4导联、3导联和2导联版本的评分分别为0.504、0.466、0.459、0.458和0.438。
{"title":"Automatic Diagnosis of Cardiac Disease from Twelve-Lead and Reduced-Lead ECGs Using Multilabel Classification","authors":"P. Sundararajan, Kevin Moses, C. Potes, S. Parvaneh","doi":"10.23919/cinc53138.2021.9662899","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662899","url":null,"abstract":"ECG is an essential tool for the clinical diagnosis of cardiac electrical abnormalities. As part of the PhysioNet/Computing in Cardiology Challenge 2021, eight and two folds from the 10-folds iterative splitting of public training data set were used as in-house training and internal validation sets. We used extracted features from RandOm Convolutional KErnel Transforms (ROCKETs) with a multilabel classification using XGBoost to predict cardiac abnormalities. Our team, LINC, developed an approach with minimal pre-processing (e.g., resampling data to 500Hz) and with no QRS detection or deep neural network design, which led to promising performance on the internal validation set. We didn't receive the official scores for the validation and test sets, because our entry failed during training in the official phase as we submitted an incomplete entry. Our classifiers received scores of 0.504, 0.466, 0.459, 0.458, and 0.438 for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions on the internal validation set with the challenge evaluation metric (10 seconds ECG).","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116986286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662743
Eduardo Mineo, A. Assunção, T. Morais, S.F.C. Camara, H. Ribeiro, J. Sims, C. Nomura
Identifying the insertion zone of transcatheter heart valves can be time-consuming and suffers from variability and reproducibility problems. We present a deep leaning approach in CTA images to locate the midpoint of the insertion zone. A U-Net neural network is implemented to automatically segment the aortic valve on axial projection. The insertion zone midpoint is calculated based on the range of slices with the more concentrated area of activated pixels. We found a very low systematic error with a median computed error of 0.38mm and interquartile range of 0.15 – 0.75mm. The proposed model was shown to be a robust and powerful tool to automatically locate the insertion zone midpoint and we believe it will play a critical role on automated assessment of aortic stenosis.
{"title":"U-Net Neural Network for Locating Midpoint of Insertion Zone of Transcatheter Aortic Valves in CTA Images","authors":"Eduardo Mineo, A. Assunção, T. Morais, S.F.C. Camara, H. Ribeiro, J. Sims, C. Nomura","doi":"10.23919/cinc53138.2021.9662743","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662743","url":null,"abstract":"Identifying the insertion zone of transcatheter heart valves can be time-consuming and suffers from variability and reproducibility problems. We present a deep leaning approach in CTA images to locate the midpoint of the insertion zone. A U-Net neural network is implemented to automatically segment the aortic valve on axial projection. The insertion zone midpoint is calculated based on the range of slices with the more concentrated area of activated pixels. We found a very low systematic error with a median computed error of 0.38mm and interquartile range of 0.15 – 0.75mm. The proposed model was shown to be a robust and powerful tool to automatically locate the insertion zone midpoint and we believe it will play a critical role on automated assessment of aortic stenosis.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127181216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662742
M. Alkhodari, G. Apostolidis, Charilaos A. Zisou, L. Hadjileontiadis, A. Khandoker
The standard screening tool for cardiac arrhythmias remains to be the 12-lead electrocardiography (ECG). Despite carrying rich information about different types of arrhythmias, it is considered bulky, high-cost, and often hard to use. In this study, we sought to investigate the efficiency of using 6-lead, 4-lead, 3 -lead, and 2-lead ECG in discriminating between 26 arrhythmia types and compare them with the standard 12-lead ECG. as part of PhysioNet/Computing in Cardiology 2021 Challenge. Our team, Care4MyHeart, developed a deep learning approach based on residual convolutional neural networks and Bi-directional long short term memory (ResNet-BiLSTM) to extract deep-activated features from ECG oscillatory components obtained using a novel swarm decomposition (SWD) algorithm. Alongside age and sex, these automated features were combined with hand-crafted features from heart rate variability and SWD components for training and classification. Our approach achieved a challenge score of 0.45, 0.43, 0.44, 0.43, and 0.42 using 10-fold cross-validation using the training set and 0.25, 0.23, 0.24, 0.22, and 0.20 using the hidden test set for 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead, respectively. Our team was ranked the 31/38 with an average all-lead test score of 0.22.
心律失常的标准筛查工具仍然是12导联心电图(ECG)。尽管携带了关于不同类型心律失常的丰富信息，但它被认为体积庞大，成本高，而且通常难以使用。在这项研究中，我们试图探讨使用6导联、4导联、3导联和2导联心电图区分26种心律失常类型的效率，并将其与标准12导联心电图进行比较。作为PhysioNet/Computing in Cardiology 2021挑战赛的一部分。我们的团队Care4MyHeart开发了一种基于残差卷积神经网络和双向长短期记忆(ResNet-BiLSTM)的深度学习方法，从使用新型群分解(SWD)算法获得的ECG振荡分量中提取深度激活特征。除了年龄和性别之外，这些自动特征还与心率变异性和SWD组件的手工特征相结合，用于训练和分类。我们的方法使用训练集进行10倍交叉验证，获得了0.45、0.43、0.44、0.43和0.42的挑战得分，使用隐藏测试集分别为0.25、0.23、0.24、0.22和0.20，分别为12导联、6导联、4导联、3导联和2导联。我们队全铅测试平均成绩为0.22，排名第31/38。
{"title":"Swarm Decomposition Enhances the Discrimination of Cardiac Arrhythmias in Varied-Lead ECG Using ResNet-BiLSTM Network Activations","authors":"M. Alkhodari, G. Apostolidis, Charilaos A. Zisou, L. Hadjileontiadis, A. Khandoker","doi":"10.23919/cinc53138.2021.9662742","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662742","url":null,"abstract":"The standard screening tool for cardiac arrhythmias remains to be the 12-lead electrocardiography (ECG). Despite carrying rich information about different types of arrhythmias, it is considered bulky, high-cost, and often hard to use. In this study, we sought to investigate the efficiency of using 6-lead, 4-lead, 3 -lead, and 2-lead ECG in discriminating between 26 arrhythmia types and compare them with the standard 12-lead ECG. as part of PhysioNet/Computing in Cardiology 2021 Challenge. Our team, Care4MyHeart, developed a deep learning approach based on residual convolutional neural networks and Bi-directional long short term memory (ResNet-BiLSTM) to extract deep-activated features from ECG oscillatory components obtained using a novel swarm decomposition (SWD) algorithm. Alongside age and sex, these automated features were combined with hand-crafted features from heart rate variability and SWD components for training and classification. Our approach achieved a challenge score of 0.45, 0.43, 0.44, 0.43, and 0.42 using 10-fold cross-validation using the training set and 0.25, 0.23, 0.24, 0.22, and 0.20 using the hidden test set for 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead, respectively. Our team was ranked the 31/38 with an average all-lead test score of 0.22.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115194675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662881
Y. S. Dogrusoz, R. Dubois, E. Abell, M. Cluitmans, L. Bear
Background: Electrocardiographic imaging (ECGI) has potential to guide physicians to plan treatment strategies. Previously, Bayesian maximum a posteriori (MAP) estimation has been successfully applied to solve this inverse problem for paced data. In this study, we evaluate its effectiveness using experimental data in reconstructing sinus rhythm. Methods: Four datasets from Langendorff-perfused pig hearts, suspended in a human-shaped torso-tank, were used. Each experiment included 3–5 simultaneous electrogram (EGM) and body surface potential (BSP) recordings of 10 beats, in baseline and under dofetilide and pinacidil perfusion. Bayesian MAP estimation and Tikhonov regularization were used to solve the inverse problem. Prior models in MAP were generated using beats from the same recording but excluding the test beat. Pearson's correlation was used to evaluate EGM reconstructions, activation time (AT) maps, and gradient of ATs. Results: In almost all quantitative evaluations and qualitative comparisons of AT maps and epicardial breakthrough sites, MAP outperformed substantially better than Tikhonov regularization. Conclusion: These preliminary results showed that with a “good” prior model, MAP improves over Tikhonov regularization in terms of preventing misdiagnosis of conduction abnormalities associated with arrhythmogenic substrates and identifying epicardial breakthrough sites.
{"title":"Electrocardiographic Imaging of Sinus Rhythm in Pig Hearts Using Bayesian Maximum A Posteriori Estimation","authors":"Y. S. Dogrusoz, R. Dubois, E. Abell, M. Cluitmans, L. Bear","doi":"10.23919/cinc53138.2021.9662881","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662881","url":null,"abstract":"Background: Electrocardiographic imaging (ECGI) has potential to guide physicians to plan treatment strategies. Previously, Bayesian maximum a posteriori (MAP) estimation has been successfully applied to solve this inverse problem for paced data. In this study, we evaluate its effectiveness using experimental data in reconstructing sinus rhythm. Methods: Four datasets from Langendorff-perfused pig hearts, suspended in a human-shaped torso-tank, were used. Each experiment included 3–5 simultaneous electrogram (EGM) and body surface potential (BSP) recordings of 10 beats, in baseline and under dofetilide and pinacidil perfusion. Bayesian MAP estimation and Tikhonov regularization were used to solve the inverse problem. Prior models in MAP were generated using beats from the same recording but excluding the test beat. Pearson's correlation was used to evaluate EGM reconstructions, activation time (AT) maps, and gradient of ATs. Results: In almost all quantitative evaluations and qualitative comparisons of AT maps and epicardial breakthrough sites, MAP outperformed substantially better than Tikhonov regularization. Conclusion: These preliminary results showed that with a “good” prior model, MAP improves over Tikhonov regularization in terms of preventing misdiagnosis of conduction abnormalities associated with arrhythmogenic substrates and identifying epicardial breakthrough sites.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114462697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662782
P. Priya, Srinivasan Jayaraman
Hydroxychloroquine (HCQ) has been widely used, irrespective of pre reported cardiotoxicity. This demands further investigation on the mechanisms of HCQ interaction under hypoxia without and with a pro-arrhythmic comor-bidity like hypokalemia in the ventricular tissue as well as its effects when excited with premature beats (PBs) to understand the possibility of arrhythmic occurrence. This is made possible by configuring a 2D transmural anisotropic ventricular tissue model consisting of endocardial, mid-myocardial and epicardial myocytes for mild and severe hypoxia, hypokalemia and HCQ conditions. Results show that along with a QT interval reduction, low amplitude or T-wave inversion is observed in mild and severe hypoxia conditions respectively. No significant adverse effect of HCQ is observed in both cases. Under hypokalemia, mild hypoxia creates notched T-waves. Including HCQ has the effect of increasing the QT interval and T-peak. In presence of PBs, arrhythmia is generated only in presence of hypokalemia. Further, severe hypoxia causes inverted T-waves and a shortened QT-interval in hypokalemic comor-bid configuration. In presence of PBs, reentry is created only on addition of hypokalemia. When treated with HCQ, no notable changes occurred. This in-silico ventricular model indicates that HCQ treatment has no significant adverse effect in presence of hypokalemia and hypoxia, except in the combination of mild hypoxia with hypokalemia condition where it initiated a re-entrant arrhythmia pattern. These results could help guide treatment with HCQ.
{"title":"Hydroxychloroquine's Influence on Hypoxic and Hypokalemic ventricle: An Insilico Perspective","authors":"P. Priya, Srinivasan Jayaraman","doi":"10.23919/cinc53138.2021.9662782","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662782","url":null,"abstract":"Hydroxychloroquine (HCQ) has been widely used, irrespective of pre reported cardiotoxicity. This demands further investigation on the mechanisms of HCQ interaction under hypoxia without and with a pro-arrhythmic comor-bidity like hypokalemia in the ventricular tissue as well as its effects when excited with premature beats (PBs) to understand the possibility of arrhythmic occurrence. This is made possible by configuring a 2D transmural anisotropic ventricular tissue model consisting of endocardial, mid-myocardial and epicardial myocytes for mild and severe hypoxia, hypokalemia and HCQ conditions. Results show that along with a QT interval reduction, low amplitude or T-wave inversion is observed in mild and severe hypoxia conditions respectively. No significant adverse effect of HCQ is observed in both cases. Under hypokalemia, mild hypoxia creates notched T-waves. Including HCQ has the effect of increasing the QT interval and T-peak. In presence of PBs, arrhythmia is generated only in presence of hypokalemia. Further, severe hypoxia causes inverted T-waves and a shortened QT-interval in hypokalemic comor-bid configuration. In presence of PBs, reentry is created only on addition of hypokalemia. When treated with HCQ, no notable changes occurred. This in-silico ventricular model indicates that HCQ treatment has no significant adverse effect in presence of hypokalemia and hypoxia, except in the combination of mild hypoxia with hypokalemia condition where it initiated a re-entrant arrhythmia pattern. These results could help guide treatment with HCQ.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117024925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662806
Tomáš Vičar, Petra Novotna, Jakub Hejc, O. Janousek, M. Ronzhina
In this work, we present an algorithm for automatically identifying the cardiac abnormalities in ECG records with the various number of leads. The algorithm is based on the modified ResNet convolutional neural network with the attention layer. The network input is modified to allow using a single network for different lead subsets. In an official phase challenge entry, our BUTTeam reached the 15th place. In our test challenge entry, we have achieved 0.470, 0.460, 0.470, 0.460, and 0.460 of the challenge metric for 12,6,4,3 and 2 leads with ranking 14th, 14th, 11th, 15th and 11 th place, respectively. From additional evaluation of other lead subsets, the leads representing a common heart axis orientation achieved the best detection results. However, all lead subsets performed very similarly.
{"title":"Cardiac Abnormalities Recognition in ECG Using a Convolutional Network with Attention and Input with an Adaptable Number of Leads","authors":"Tomáš Vičar, Petra Novotna, Jakub Hejc, O. Janousek, M. Ronzhina","doi":"10.23919/cinc53138.2021.9662806","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662806","url":null,"abstract":"In this work, we present an algorithm for automatically identifying the cardiac abnormalities in ECG records with the various number of leads. The algorithm is based on the modified ResNet convolutional neural network with the attention layer. The network input is modified to allow using a single network for different lead subsets. In an official phase challenge entry, our BUTTeam reached the 15th place. In our test challenge entry, we have achieved 0.470, 0.460, 0.470, 0.460, and 0.460 of the challenge metric for 12,6,4,3 and 2 leads with ranking 14th, 14th, 11th, 15th and 11 th place, respectively. From additional evaluation of other lead subsets, the leads representing a common heart axis orientation achieved the best detection results. However, all lead subsets performed very similarly.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128274554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：