S. Moharreri, Shahab Rezaei, N. Jafarnia Dabanloo, S. Parvaneh
{"title":"Automatic Emotions Assessment Using Heart Rate Variability Analysis and 2D Regression Model of Emotions","authors":"S. Moharreri, Shahab Rezaei, N. Jafarnia Dabanloo, S. Parvaneh","doi":"10.22489/cinc.2019.356","DOIUrl":"https://doi.org/10.22489/cinc.2019.356","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74387436","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}
In this paper, we proposed a framework for left atrium (LA) segmentation on CT with combined detection network and level set model. The proposed framework consists of two steps. Firstly, we trained a Faster RCNN to generate location boxes for LA. The obtained location box can remove unrelated regions to reduce the interference of background and similarity tissues. Secondly, we utilized a self-adapted threshold on the location box to get the initialization for the level set model, which is nearer the LA and more robust than the random and fixed initialization. Then we proposed a 3D level set model with a new edge indicator based on DRLSE for the final LA segmentation. This edge indicator incorporated both numerical and direction information of the data gradient. Hence, the proposed level set model can guide the contour to the correct boundary when there are many boundaries surrounded the object. The framework was trained and evaluated on MICCAI 2013 LA segmentation challenge. The proposed segmentation method achieved the Dice score of 86.46%. Comparing to the original DRLSE, it achieved a 2.72% improvement on the Dice score.
{"title":"A Framework of Left Atrium Segmentation on CT Images with Combined Detection Network and Level Set Model","authors":"Yashu Liu, Kuanquan Wang, Gongning Luo, Henggui Zhang","doi":"10.22489/cinc.2019.240","DOIUrl":"https://doi.org/10.22489/cinc.2019.240","url":null,"abstract":"In this paper, we proposed a framework for left atrium (LA) segmentation on CT with combined detection network and level set model. The proposed framework consists of two steps. Firstly, we trained a Faster RCNN to generate location boxes for LA. The obtained location box can remove unrelated regions to reduce the interference of background and similarity tissues. Secondly, we utilized a self-adapted threshold on the location box to get the initialization for the level set model, which is nearer the LA and more robust than the random and fixed initialization. Then we proposed a 3D level set model with a new edge indicator based on DRLSE for the final LA segmentation. This edge indicator incorporated both numerical and direction information of the data gradient. Hence, the proposed level set model can guide the contour to the correct boundary when there are many boundaries surrounded the object. The framework was trained and evaluated on MICCAI 2013 LA segmentation challenge. The proposed segmentation method achieved the Dice score of 86.46%. Comparing to the original DRLSE, it achieved a 2.72% improvement on the Dice score.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78123947","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}
In heart pathological conditions, fibroblasts proliferate and differentiate into myofibroblasts (Mfbs). This study aimed to investigate the role of Mfbs on the mechanical contraction of cardiac fiber. Mathematical modeling was done using a combination of (1) the Maleckar et al. model of the human atrial myocyte, (2) the MacCannell et al. active model of the human cardiac Mfb, (3) our formulation of INa_myofb based upon experimental findings from Chatelier et al., and (4) the Hill three-element rheological scheme of a single segment of cardiac fiber. For Mfb-myocyte coupling, different ratios of myocytes to Mfbs and gap-junctional conductances were set based on available physiological data. Both isometric contraction and isotonic contraction were considered to illustrate the effect of Mfbs on cardiac fiber’s tension and strain. The results showed that (1) Mfbs decreased APD50 and increased Vrest depolarization, (2) Mfbs regulated myocyte peak force and (3) Mfbs reduced the fiber peak force in isometric contraction and the fiber peak strain in isotonic contraction. The identified effects demonstrated that Mfbs play an important role of modulating cardiac mechanical behavior. It should be considered in future pathological cardiac mathematical modeling, such as atrial fibrillation and cardiac fibrosis.
{"title":"Myofibroblasts Alter Tension and Strain of Cardiac Fiber: A Computational Study","authors":"Zhan Heqing, Zhang Jingtao","doi":"10.22489/cinc.2019.007","DOIUrl":"https://doi.org/10.22489/cinc.2019.007","url":null,"abstract":"In heart pathological conditions, fibroblasts proliferate and differentiate into myofibroblasts (Mfbs). This study aimed to investigate the role of Mfbs on the mechanical contraction of cardiac fiber. Mathematical modeling was done using a combination of (1) the Maleckar et al. model of the human atrial myocyte, (2) the MacCannell et al. active model of the human cardiac Mfb, (3) our formulation of INa_myofb based upon experimental findings from Chatelier et al., and (4) the Hill three-element rheological scheme of a single segment of cardiac fiber. For Mfb-myocyte coupling, different ratios of myocytes to Mfbs and gap-junctional conductances were set based on available physiological data. Both isometric contraction and isotonic contraction were considered to illustrate the effect of Mfbs on cardiac fiber’s tension and strain. The results showed that (1) Mfbs decreased APD50 and increased Vrest depolarization, (2) Mfbs regulated myocyte peak force and (3) Mfbs reduced the fiber peak force in isometric contraction and the fiber peak strain in isotonic contraction. The identified effects demonstrated that Mfbs play an important role of modulating cardiac mechanical behavior. It should be considered in future pathological cardiac mathematical modeling, such as atrial fibrillation and cardiac fibrosis.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90510055","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}
Wei Wei Heng, Eileen Su Lee Ming, Ahmad Nizar Jamaluddin, Fauzan Khairi Che Harun, Nurul Ashikin Abdul-Kadir, Che Fai Yeong
Prediction of malignant ventricular arrhythmia (mVA) is essential to prevent sudden cardiac death. There were mainly three research clusters on mVA prediction using electrocardiogram (ECG): prediction using CUDB, SDDB and private databases. Comparability and generalization issue arose due to the different usage of arrhythmic datasets for analysis. Very few studies attempted short-term prediction of mVA using multiple databases, and those studies achieved low prediction performance. Our study aims to improve the prediction performance involving multiple databases and to promote the algorithm comparability by performing more comprehensive comparability study while including a more complete set of data available from the public databases. In our study, eight statistical box count features derived from phase space reconstruction on ECG signal were classified using maximum thresholding method. This was followed by performance benchmarking against the first two clusters of existing research and a performance evaluation using the combined set of databases. Our algorithm using box count coefficient of mean absolute deviation achieved over 90% of accuracy and over 4-minutes prediction time for all the three set of performance evaluations. This algorithm outperforms the existing work by introducing lower computational efforts.
{"title":"Prediction Algorithm of Malignant Ventricular Arrhythmia Validated across Multiple Online Public Databases","authors":"Wei Wei Heng, Eileen Su Lee Ming, Ahmad Nizar Jamaluddin, Fauzan Khairi Che Harun, Nurul Ashikin Abdul-Kadir, Che Fai Yeong","doi":"10.22489/cinc.2019.295","DOIUrl":"https://doi.org/10.22489/cinc.2019.295","url":null,"abstract":"Prediction of malignant ventricular arrhythmia (mVA) is essential to prevent sudden cardiac death. There were mainly three research clusters on mVA prediction using electrocardiogram (ECG): prediction using CUDB, SDDB and private databases. Comparability and generalization issue arose due to the different usage of arrhythmic datasets for analysis. Very few studies attempted short-term prediction of mVA using multiple databases, and those studies achieved low prediction performance. Our study aims to improve the prediction performance involving multiple databases and to promote the algorithm comparability by performing more comprehensive comparability study while including a more complete set of data available from the public databases. In our study, eight statistical box count features derived from phase space reconstruction on ECG signal were classified using maximum thresholding method. This was followed by performance benchmarking against the first two clusters of existing research and a performance evaluation using the combined set of databases. Our algorithm using box count coefficient of mean absolute deviation achieved over 90% of accuracy and over 4-minutes prediction time for all the three set of performance evaluations. This algorithm outperforms the existing work by introducing lower computational efforts.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90845629","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}
Motivation: Many software tools for ECG processing are commercial. New innovative and alternative features for heart rate variability analysis (HRV) and improved methods in ECG preprocessing cannot be incorporated. Moreover, software manuals are lacking of clarity and often conceal the exact calculation methods that makes clinical interpretation difficult, and reproducibility is reduced. Software description: HRVTool provides an opensource and intuitive user-friendly environment for the HRV analysis in Matlab. The software is available at http://marcusvollmer.github.io/HRV and supports the processing of ECG, pulsatile waveforms and RR intervals from various sources (mat and text files containing raw data, Polar, PhysioNet, Hexoskin, BIOPAC, European Data Format, ISHNE Holter Standard Format, and Machine-Independent Beat files). An integrated heart beat detector locates R peaks or pulse waves. Visual inspection, and manual adjustments of beat locations are possible and the corresponding annotation file can be saved in a standard Matlab format or as a delimited text file. HRV statistics are computed in a sliding window to evaluate the alteration over time. HRV metrics can be exported. An animation of intervals supports pattern identification. Moreover the Matlab class (HRV.m) includes functions for windowed HRV computation that can be used for batch processing.
{"title":"HRVTool - an Open-Source Matlab Toolbox for Analyzing Heart Rate Variability","authors":"M. Vollmer","doi":"10.22489/cinc.2019.032","DOIUrl":"https://doi.org/10.22489/cinc.2019.032","url":null,"abstract":"Motivation: Many software tools for ECG processing are commercial. New innovative and alternative features for heart rate variability analysis (HRV) and improved methods in ECG preprocessing cannot be incorporated. Moreover, software manuals are lacking of clarity and often conceal the exact calculation methods that makes clinical interpretation difficult, and reproducibility is reduced. Software description: HRVTool provides an opensource and intuitive user-friendly environment for the HRV analysis in Matlab. The software is available at http://marcusvollmer.github.io/HRV and supports the processing of ECG, pulsatile waveforms and RR intervals from various sources (mat and text files containing raw data, Polar, PhysioNet, Hexoskin, BIOPAC, European Data Format, ISHNE Holter Standard Format, and Machine-Independent Beat files). An integrated heart beat detector locates R peaks or pulse waves. Visual inspection, and manual adjustments of beat locations are possible and the corresponding annotation file can be saved in a standard Matlab format or as a delimited text file. HRV statistics are computed in a sliding window to evaluate the alteration over time. HRV metrics can be exported. An animation of intervals supports pattern identification. Moreover the Matlab class (HRV.m) includes functions for windowed HRV computation that can be used for batch processing.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84975268","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}
Sara Rocher, L. Martinez, Alejandro López, A. Ferrer, D. Sánchez-Quintana, J. Saiz
{"title":"A Three-Dimensional Model of the Human Atria With Heterogeneous Thickness and Fibre Transmurality - A Realistic Platform for the Study of Atrial Fibrillation","authors":"Sara Rocher, L. Martinez, Alejandro López, A. Ferrer, D. Sánchez-Quintana, J. Saiz","doi":"10.22489/cinc.2019.380","DOIUrl":"https://doi.org/10.22489/cinc.2019.380","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88700729","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}
Mengsha Fu, Jiabin Yuan, Menglin Lu, Pengfei Hong, M. Zeng
Sepsis is a life-threatening disease with high mortality and expensive cost of treatment. In order to improve the outcomes of patients, it is important to detect atrisk patients with sepsis at an early stage. The PhysioNet/Computing in Cardiology Challenge 2019 focused on improving predicting sepsis six hours before the clinical diagnosis by using the latest definition of Sepsis-3. A total of 40,336 ICU patients were provided as public training data, A hidden test dataset was used to evaluate. An ensemble model, which combined boosting and bagging tree models (lightgbm, xgboost and random forest ) were designed to predict sepsis based on the records of the patient’s hourly data. We compared the ensemble model and each single model of evaluation metrics results on selected inner test data Offline, the best performance was achieved AUC of 0.792, ACC of 0.727. Finally, the proposed model was evaluated on the full test sets received an official utility score, defined by the organizers, was 0.087, ranked 75/105 (our team name: cinc sepsis pass). While the single model of lightgbm only received a utility score of -0.036. The ensemble model utilized the preprocessing data and achieved better performance than a single tree-based model.
败血症是一种危及生命的疾病，死亡率高，治疗费用昂贵。为了改善患者的预后，早期发现脓毒症患者的危险是很重要的。2019年PhysioNet/Computing in Cardiology挑战赛的重点是通过使用败血症-3的最新定义，在临床诊断前6小时提高对败血症的预测。共提供40336例ICU患者作为公开训练数据，采用隐式测试数据集进行评估。设计了一个集合模型，结合了增强和bagging树模型(lightgbm, xgboost和random forest)，根据患者每小时的数据记录来预测脓毒症。在选取的内部测试数据上，将集成模型与各单一模型的评价指标结果进行了离线比较，获得了最佳性能的AUC为0.792,ACC为0.727。最后，提出的模型在完整的测试集上进行评估，得到由组织者定义的官方效用得分，为0.087，排名75/105(我们的团队名称:cinc sepsis pass)。而光基单模型的效用得分仅为-0.036。该集成模型利用了预处理数据，比单一的基于树的模型取得了更好的性能。
{"title":"An Ensemble Machine Learning Model for the Early Detection of Sepsis from Clinical Data","authors":"Mengsha Fu, Jiabin Yuan, Menglin Lu, Pengfei Hong, M. Zeng","doi":"10.22489/cinc.2019.317","DOIUrl":"https://doi.org/10.22489/cinc.2019.317","url":null,"abstract":"Sepsis is a life-threatening disease with high mortality and expensive cost of treatment. In order to improve the outcomes of patients, it is important to detect atrisk patients with sepsis at an early stage. The PhysioNet/Computing in Cardiology Challenge 2019 focused on improving predicting sepsis six hours before the clinical diagnosis by using the latest definition of Sepsis-3. A total of 40,336 ICU patients were provided as public training data, A hidden test dataset was used to evaluate. An ensemble model, which combined boosting and bagging tree models (lightgbm, xgboost and random forest ) were designed to predict sepsis based on the records of the patient’s hourly data. We compared the ensemble model and each single model of evaluation metrics results on selected inner test data Offline, the best performance was achieved AUC of 0.792, ACC of 0.727. Finally, the proposed model was evaluated on the full test sets received an official utility score, defined by the organizers, was 0.087, ranked 75/105 (our team name: cinc sepsis pass). While the single model of lightgbm only received a utility score of -0.036. The ensemble model utilized the preprocessing data and achieved better performance than a single tree-based model.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84154101","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}
Early prediction of sepsis is critical in clinical practice since each hour of delayed treatment has been associated with an increase in mortality due to irreversible organ damage. This study aimed to develop an algorithm for accurately predicting the onset of sepsis in the proceeding of six hours. Firstly, we selected 37 available variates features after data pre-processing, and then extracted three kinds of features as well in this paper, including 62 missing value features, 8 scoring quantified features and 61 time series features. After that, a multi-feature fusion based XGBoost classification model was developed and was further improved by a Bayesian optimizer and an ensemble learning framework. Analysis was performed on the PhysioNet/Computing in Cardiology Challenge 2019, which provided a publicly available sepsis data sourced from 40,336 ICU patients. Finally, after searching an optimized predicted risk threshold of 0.522 through the official submissions, our team “SailOcean” applied the developed model on the full hidden test set of 24,819 ICU patients from three hospital systems and obtained a final Unormalized score (U-Score) defined by the organizers of 0.364, which was the highest unofficial score.
脓毒症的早期预测在临床实践中至关重要，因为由于不可逆的器官损伤，每延迟治疗一个小时，死亡率就会增加。本研究旨在开发一种算法来准确预测6小时内脓毒症的发生。首先，在数据预处理后，我们选择了37个可用的变量特征，然后在本文中提取了三种特征，其中缺失值特征62个，评分量化特征8个，时间序列特征61个。在此基础上，建立了基于多特征融合的XGBoost分类模型，并通过贝叶斯优化器和集成学习框架对其进行了进一步改进。对PhysioNet/Computing in Cardiology Challenge 2019进行了分析，该挑战赛提供了来自40,336名ICU患者的公开可用败血症数据。最后，我们的团队“SailOcean”在官方提交的文件中搜索到优化后的预测风险阈值0.522，并将开发的模型应用于三个医院系统的24,819名ICU患者的全隐测试集，最终得到由组织者定义的非规范化评分(U-Score) 0.364，这是最高的非官方得分。
{"title":"Early Prediction of Sepsis Using Multi-Feature Fusion Based XGBoost Learning and Bayesian Optimization","authors":"Meicheng Yang, Xingyao Wang, Hongxiang Gao, Yuwen Li, Xing Liu, Jianqing Li, Chengyu Liu","doi":"10.22489/cinc.2019.020","DOIUrl":"https://doi.org/10.22489/cinc.2019.020","url":null,"abstract":"Early prediction of sepsis is critical in clinical practice since each hour of delayed treatment has been associated with an increase in mortality due to irreversible organ damage. This study aimed to develop an algorithm for accurately predicting the onset of sepsis in the proceeding of six hours. Firstly, we selected 37 available variates features after data pre-processing, and then extracted three kinds of features as well in this paper, including 62 missing value features, 8 scoring quantified features and 61 time series features. After that, a multi-feature fusion based XGBoost classification model was developed and was further improved by a Bayesian optimizer and an ensemble learning framework. Analysis was performed on the PhysioNet/Computing in Cardiology Challenge 2019, which provided a publicly available sepsis data sourced from 40,336 ICU patients. Finally, after searching an optimized predicted risk threshold of 0.522 through the official submissions, our team “SailOcean” applied the developed model on the full hidden test set of 24,819 ICU patients from three hospital systems and obtained a final Unormalized score (U-Score) defined by the organizers of 0.364, which was the highest unofficial score.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78330083","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}
{"title":"A New Graphical Method for Reporting Performance Results of a Diagnostic Test","authors":"Wang C John","doi":"10.22489/cinc.2019.409","DOIUrl":"https://doi.org/10.22489/cinc.2019.409","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74595457","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：