1
|
Mishra A, Bhusnur S, Mishra SK, Singh P. Comparative analysis of parametric B-spline and Hermite cubic spline based methods for accurate ECG signal modeling. J Electrocardiol 2024; 86:153783. [PMID: 39213712 DOI: 10.1016/j.jelectrocard.2024.153783] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2024] [Revised: 07/22/2024] [Accepted: 08/12/2024] [Indexed: 09/04/2024]
Abstract
Analyzing Electrocardiogram (ECG) signals is imperative for diagnosing cardiovascular diseases. However, evaluating ECG analysis techniques faces challenges due to noise and artifacts in actual signals. Machine learning for automatic diagnosis encounters data acquisition hurdles due to medical data privacy constraints. Addressing these issues, ECG modeling assumes a crucial role in biomedical and parametric spline-based methods have garnered significant attention for their ability to accurately represent the complex temporal dynamics of ECG signals. This study conducts a comparative analysis of two parametric spline-based methods-B-spline and Hermite cubic spline-for ECG modeling, aiming to identify the most effective approach for accurate and reliable ECG representation. The Hermite cubic spline serves as one of the most effective interpolation methods, while B-spline is an approximation method. The comparative analysis includes both qualitative and quantitative evaluations. Qualitative assessment involves visually inspecting the generated spline-based models, comparing their resemblance to the original ECG signals, and employing power spectrum analysis. Quantitative analysis incorporates metrics such as root mean square error (RMSE), Percentage Root Mean Square Difference (PRD) and cross correlation, offering a more objective measure of the model's performance. Preliminary results indicate promising capabilities for both spline-based methods in representing ECG signals. However, the analysis unveils specific strengths and weaknesses for each method. The B-spline method offers greater flexibility and smoothness, while the cubic spline method demonstrates superior waveform capturing abilities with the preservation of control points, a critical aspect in the medical field. Presented research provides valuable insights for researchers and practitioners in selecting the most appropriate method for their specific ECG modeling requirements. Adjustments to control points and parameterization enable the generation of diverse ECG waveforms, enhancing the versatility of this modeling technique. This approach has the potential to extend its utility to other medical signals, presenting a promising avenue for advancing biomedical research.
Collapse
Affiliation(s)
- Alka Mishra
- Bhilai Institute of Technology, Bhilai House, Durg, Chhattisgarh 491001, India.
| | - Surekha Bhusnur
- Bhilai Institute of Technology, Bhilai House, Durg, Chhattisgarh 491001, India
| | | | - Pushpendra Singh
- Bhilai Institute of Technology, Bhilai House, Durg, Chhattisgarh 491001, India
| |
Collapse
|
2
|
Yoon N, Kim K, Lee S, Bai JH, Kim H. Adaptive Sensing Data Augmentation for Drones Using Attention-Based GAN. SENSORS (BASEL, SWITZERLAND) 2024; 24:5451. [PMID: 39205144 PMCID: PMC11359813 DOI: 10.3390/s24165451] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/04/2024] [Revised: 08/10/2024] [Accepted: 08/20/2024] [Indexed: 09/04/2024]
Abstract
Drones have become essential tools across various industries due to their ability to provide real-time data and perform automated tasks. However, integrating multiple sensors on a single drone poses challenges such as payload limitations and data management issues. This paper proposes a comprehensive system that leverages advanced deep learning techniques, specifically an attention-based generative adversarial network (GAN), to address data scarcity in drone-collected time-series sensor data. By adjusting sensing frequency based on operational conditions while maintaining data resolution, our system ensures consistent and high-quality data collection. The spatiotemporal The attention mechanism within the GAN enhances the generation of synthetic data, filling gaps caused by reduced sensing frequency with realistic data. This approach improves the efficiency and performance of various applications, such as precision agriculture, environmental monitoring, and surveillance. The experimental results demonstrated the effectiveness of our methodology in extending the operational range and duration of drones and providing reliable augmented data utilizing a variety of evaluation metrics. Furthermore, the superior performance of the proposed system was verified by comparing it with various comparative GAN models.
Collapse
Affiliation(s)
- Namkyung Yoon
- School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea; (N.Y.); (K.K.); (S.L.)
| | - Kiseok Kim
- School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea; (N.Y.); (K.K.); (S.L.)
| | - Sangmin Lee
- School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea; (N.Y.); (K.K.); (S.L.)
| | - Jin Hyoung Bai
- Digital Convergence Department, KEPCO E&C, Gimcheon 39660, Republic of Korea;
| | - Hwangnam Kim
- School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea; (N.Y.); (K.K.); (S.L.)
| |
Collapse
|
3
|
Kulyabin M, Zhdanov A, Maier A, Loh L, Estevez JJ, Constable PA. Generating Synthetic Light-Adapted Electroretinogram Waveforms Using Artificial Intelligence to Improve Classification of Retinal Conditions in Under-Represented Populations. J Ophthalmol 2024; 2024:1990419. [PMID: 39045382 PMCID: PMC11265936 DOI: 10.1155/2024/1990419] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2024] [Revised: 05/27/2024] [Accepted: 06/25/2024] [Indexed: 07/25/2024] Open
Abstract
Visual electrophysiology is often used clinically to determine the functional changes associated with retinal or neurological conditions. The full-field flash electroretinogram (ERG) assesses the global contribution of the outer and inner retinal layers initiated by the rods and cone pathways depending on the state of retinal adaptation. Within clinical centers, reference normative data are used to compare clinical cases that may be rare or underpowered within a specific demographic. To bolster either the reference dataset or the case dataset, the application of synthetic ERG waveforms may offer benefits to disease classification and case-control studies. In this study and as a proof of concept, artificial intelligence (AI) to generate synthetic signals using generative adversarial networks is deployed to upscale male participants within an ISCEV reference dataset containing 68 participants, with waveforms from the right and left eye. Random forest classifiers further improved classification for sex within the group from a balanced accuracy of 0.72-0.83 with the added synthetic male waveforms. This is the first study to demonstrate the generation of synthetic ERG waveforms to improve machine learning classification modelling with electroretinogram waveforms.
Collapse
Affiliation(s)
- Mikhail Kulyabin
- Pattern Recognition LabDepartment of Computer ScienceFriedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Aleksei Zhdanov
- Engineering School of Information TechnologiesTelecommunications and Control SystemsUral Federal University, Yekaterinburg, Russia
| | - Andreas Maier
- Pattern Recognition LabDepartment of Computer ScienceFriedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Lynne Loh
- Flinders UniversityCollege of Nursing and Health SciencesCaring Futures Institute, Adelaide, South Australia, Australia
| | - Jose J. Estevez
- Flinders UniversityCollege of Nursing and Health SciencesCaring Futures Institute, Adelaide, South Australia, Australia
| | - Paul A. Constable
- Flinders UniversityCollege of Nursing and Health SciencesCaring Futures Institute, Adelaide, South Australia, Australia
| |
Collapse
|
4
|
Li L. Toward Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:2466-2478. [PMID: 38373128 PMCID: PMC7616288 DOI: 10.1109/tmi.2024.3367409] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/21/2024]
Abstract
Cardiac digital twins (CDTs) have the potential to offer individualized evaluation of cardiac function in a non-invasive manner, making them a promising approach for personalized diagnosis and treatment planning of myocardial infarction (MI). The inference of accurate myocardial tissue properties is crucial in creating a reliable CDT of MI. In this work, we investigate the feasibility of inferring myocardial tissue properties from the electrocardiogram (ECG) within a CDT platform. The platform integrates multi-modal data, such as cardiac MRI and ECG, to enhance the accuracy and reliability of the inferred tissue properties. We perform a sensitivity analysis based on computer simulations, systematically exploring the effects of infarct location, size, degree of transmurality, and electrical activity alteration on the simulated QRS complex of ECG, to establish the limits of the approach. We subsequently present a novel deep computational model, comprising a dual-branch variational autoencoder and an inference model, to infer infarct location and distribution from the simulated QRS. The proposed model achieves mean Dice scores of 0.457 ±0.317 and 0.302 ±0.273 for the inference of left ventricle scars and border zone, respectively. The sensitivity analysis enhances our understanding of the complex relationship between infarct characteristics and electrophysiological features. The in silico experimental results show that the model can effectively capture the relationship for the inverse inference, with promising potential for clinical application in the future. The code is available at https://github.com/lileitech/MI_inverse_inference.
Collapse
Affiliation(s)
- Lei Li
- Department of Engineering Science, Institute of Biomedical
Engineering, University of Oxford, OX3 7DQ,
Oxford, U.K.
| |
Collapse
|
5
|
Mishra A, Bhusnur S, Mishra SK, Singh P. Exploring a new frontier in cardiac diagnosis: ECG analysis enhanced by machine learning and parametric quartic spline modeling. J Electrocardiol 2024; 85:19-24. [PMID: 38815401 DOI: 10.1016/j.jelectrocard.2024.05.086] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2024] [Revised: 05/10/2024] [Accepted: 05/15/2024] [Indexed: 06/01/2024]
Abstract
The heart's study holds paramount importance in human physiology, driving valuable research in cardiovascular health. However, assessing Electrocardiogram (ECG) analysis techniques poses challenges due to noise and artifacts in authentic recordings. The advent of machine learning systems for automated diagnosis has heightened the demand for extensive data, yet accessing medical data is hindered by privacy concerns. Consequently, generating artificial ECG signals faithful to real ones is a formidable task in biomedical signal processing. This paper introduces a method for ECG signal modeling using parametric quartic splines and generating a new dataset based on the modeled signals. Additionally, it explores ECG classification using three machine learning techniques facilitated by Orange software, addressing both normal and abnormal sinus rhythms. The classification enables early detection and prediction of heart-related ailments, facilitating timely clinical interventions and improving patient outcomes. The assessment of synthetic signal quality is conducted through power spectrum analysis and cross-correlation analysis, power spectrum analysis of both real and synthetic ECG waves provides a quantitative assessment of their frequency content, aiding in the validation and evaluation of synthetic ECG signal generation techniques. Cross-correlation analysis revealing a robust correlation coefficient of 0.974 and precise alignment with a negligible time lag of 0.000 s between the synthetic and real ECG signals. Overall, the adoption of quartic spline interpolation in ECG modeling enhances the precision, smoothness, and fidelity of signal representation, thereby improving the effectiveness of diagnostic and analytical tasks in cardiology. Three prominent machine learning algorithms, namely Decision Tree, Logistic Regression, and Gradient Boosting, effectively classify the modeled ECG signals with classification accuracies of 0.98620, 0.98965, and 0.99137, respectively. Notably, all models exhibit robust performance, characterized by high AUC values and classification accuracy. While Gradient Boosting and Logistic Regression demonstrate marginally superior performance compared to the Decision Tree model across most metrics, all models showcase commendable efficacy in ECG signal classification. The study underscores the significance of accurate ECG modeling in health sciences and biomedical technology, offering enhanced accuracy and flexibility for improved cardiovascular health understanding and diagnostic tools.
Collapse
Affiliation(s)
- Alka Mishra
- Department of Electrical and Electronics Engineering, Bhilai Institute of Technology Durg, Durg 491001, India.
| | - Surekha Bhusnur
- Department of Electrical and Electronics Engineering, Bhilai Institute of Technology Durg, Durg 491001, India.
| | - Santosh Kumar Mishra
- Department of Mechanical Engineering, Bhilai Institute of Technology Durg, Durg 491001, India.
| | - Pushpendra Singh
- Department of Electronics & Telecommunication Engineering, Bhilai Institute of Technology Durg, Durg 491001, India.
| |
Collapse
|
6
|
Yang Y, Lan T, Wang Y, Li F, Liu L, Huang X, Gao F, Jiang S, Zhang Z, Chen X. Data imbalance in cardiac health diagnostics using CECG-GAN. Sci Rep 2024; 14:14767. [PMID: 38926539 PMCID: PMC11208545 DOI: 10.1038/s41598-024-65619-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2023] [Accepted: 06/21/2024] [Indexed: 06/28/2024] Open
Abstract
Heart disease is the world's leading cause of death. Diagnostic models based on electrocardiograms (ECGs) are often limited by the scarcity of high-quality data and issues of data imbalance. To address these challenges, we propose a conditional generative adversarial network (CECG-GAN). This strategy enables the generation of samples that closely approximate the distribution of ECG data. Additionally, CECG-GAN addresses waveform jitter, slow processing speeds, and dataset imbalance issues through the integration of a transformer architecture. We evaluated this approach using two datasets: MIT-BIH and CSPC2020. The experimental results demonstrate that CECG-GAN achieves outstanding performance metrics. Notably, the percentage root mean square difference (PRD) reached 55.048, indicating a high degree of similarity between generated and actual ECG waveforms. Additionally, the Fréchet distance (FD) was approximately 1.139, the root mean square error (RMSE) registered at 0.232, and the mean absolute error (MAE) was recorded at 0.166.
Collapse
Affiliation(s)
- Yang Yang
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130022, China
- Changchun University of Architecture and Civil Engineering, Changchun, 130607, China
| | - Tianyu Lan
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130022, China
- Jilin Province Advanced Control Technology and Intelligent Automation Equipment Research Engineering Lab, Changchun, 130022, China
| | - Yang Wang
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130022, China
- Jilin Province Advanced Control Technology and Intelligent Automation Equipment Research Engineering Lab, Changchun, 130022, China
| | - Fengtian Li
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130022, China
- Jilin Province Advanced Control Technology and Intelligent Automation Equipment Research Engineering Lab, Changchun, 130022, China
| | - Liyan Liu
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130022, China
- Jilin Province Advanced Control Technology and Intelligent Automation Equipment Research Engineering Lab, Changchun, 130022, China
| | - Xupeng Huang
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130022, China
- Jilin Province Advanced Control Technology and Intelligent Automation Equipment Research Engineering Lab, Changchun, 130022, China
| | - Fei Gao
- Changchun University of Architecture and Civil Engineering, Changchun, 130607, China
| | - Shuhua Jiang
- School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, 130022, China
| | - Zhijun Zhang
- Tongfang Nuctech Co., Beijing, 100084, China
- Department of Cardiology, FAW General Hospital, Changchun, 130011, Jilin, China
| | - Xing Chen
- Department of Cardiology, FAW General Hospital, Changchun, 130011, Jilin, China.
| |
Collapse
|
7
|
Balraj K, Ramteke M, Mittal S, Bhargava R, Rathore AS. MADR-Net: multi-level attention dilated residual neural network for segmentation of medical images. Sci Rep 2024; 14:12699. [PMID: 38830932 PMCID: PMC11148105 DOI: 10.1038/s41598-024-63538-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2023] [Accepted: 05/29/2024] [Indexed: 06/05/2024] Open
Abstract
Medical image segmentation has made a significant contribution towards delivering affordable healthcare by facilitating the automatic identification of anatomical structures and other regions of interest. Although convolution neural networks have become prominent in the field of medical image segmentation, they suffer from certain limitations. In this study, we present a reliable framework for producing performant outcomes for the segmentation of pathological structures of 2D medical images. Our framework consists of a novel deep learning architecture, called deep multi-level attention dilated residual neural network (MADR-Net), designed to improve the performance of medical image segmentation. MADR-Net uses a U-Net encoder/decoder backbone in combination with multi-level residual blocks and atrous pyramid scene parsing pooling. To improve the segmentation results, channel-spatial attention blocks were added in the skip connection to capture both the global and local features and superseded the bottleneck layer with an ASPP block. Furthermore, we introduce a hybrid loss function that has an excellent convergence property and enhances the performance of the medical image segmentation task. We extensively validated the proposed MADR-Net on four typical yet challenging medical image segmentation tasks: (1) Left ventricle, left atrium, and myocardial wall segmentation from Echocardiogram images in the CAMUS dataset, (2) Skin cancer segmentation from dermoscopy images in ISIC 2017 dataset, (3) Electron microscopy in FIB-SEM dataset, and (4) Fluid attenuated inversion recovery abnormality from MR images in LGG segmentation dataset. The proposed algorithm yielded significant results when compared to state-of-the-art architectures such as U-Net, Residual U-Net, and Attention U-Net. The proposed MADR-Net consistently outperformed the classical U-Net by 5.43%, 3.43%, and 3.92% relative improvement in terms of dice coefficient, respectively, for electron microscopy, dermoscopy, and MRI. The experimental results demonstrate superior performance on single and multi-class datasets and that the proposed MADR-Net can be utilized as a baseline for the assessment of cross-dataset and segmentation tasks.
Collapse
Affiliation(s)
- Keerthiveena Balraj
- Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, 110016, India
| | - Manojkumar Ramteke
- Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, 110016, India
- Department of Chemical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India
| | - Shachi Mittal
- Department of Laboratory Medicine and Pathology, School of Medicine, University of Washington, Seattle, WA, USA
| | - Rohit Bhargava
- Departments of Bioengineering, Electrical and Computer Engineering, Mechanical Science and Engineering, Chemical and Biomolecular Engineering and Chemistry, Beckman Institute for Advanced Science and Technology, Cancer Center at Illinois, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA
| | - Anurag S Rathore
- Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, 110016, India.
- Department of Chemical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India.
| |
Collapse
|
8
|
Shivashankara KK, Deepanshi, Mehri Shervedani A, Clifford GD, Reyna MA, Sameni R. ECG-Image-Kit: a synthetic image generation toolbox to facilitate deep learning-based electrocardiogram digitization. Physiol Meas 2024; 45:055019. [PMID: 39150768 PMCID: PMC11135178 DOI: 10.1088/1361-6579/ad4954] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2024] [Revised: 04/29/2024] [Accepted: 05/09/2024] [Indexed: 08/18/2024]
Abstract
Objective.Cardiovascular diseases are a major cause of mortality globally, and electrocardiograms (ECGs) are crucial for diagnosing them. Traditionally, ECGs are stored in printed formats. However, these printouts, even when scanned, are incompatible with advanced ECG diagnosis software that require time-series data. Digitizing ECG images is vital for training machine learning models in ECG diagnosis, leveraging the extensive global archives collected over decades. Deep learning models for image processing are promising in this regard, although the lack of clinical ECG archives with reference time-series data is challenging. Data augmentation techniques using realistic generative data models provide a solution.Approach.We introduceECG-Image-Kit, an open-source toolbox for generating synthetic multi-lead ECG images with realistic artifacts from time-series data, aimed at automating the conversion of scanned ECG images to ECG data points. The tool synthesizes ECG images from real time-series data, applying distortions like text artifacts, wrinkles, and creases on a standard ECG paper background.Main results.As a case study, we used ECG-Image-Kit to create a dataset of 21 801 ECG images from the PhysioNet QT database. We developed and trained a combination of a traditional computer vision and deep neural network model on this dataset to convert synthetic images into time-series data for evaluation. We assessed digitization quality by calculating the signal-to-noise ratio and compared clinical parameters like QRS width, RR, and QT intervals recovered from this pipeline, with the ground truth extracted from ECG time-series. The results show that this deep learning pipeline accurately digitizes paper ECGs, maintaining clinical parameters, and highlights a generative approach to digitization.Significance.The toolbox has broad applications, including model development for ECG image digitization and classification. The toolbox currently supports data augmentation for the 2024 PhysioNet Challenge, focusing on digitizing and classifying paper ECG images.
Collapse
Affiliation(s)
- Kshama Kodthalu Shivashankara
- School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, United States of America
| | - Deepanshi
- Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, United States of America
| | - Afagh Mehri Shervedani
- Electrical and Computer Engineering Department, University of Illinois Chicago, Chicago, IL 60607, United States of America
| | - Gari D Clifford
- Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, United States of America
- Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, United States of America
| | - Matthew A Reyna
- Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, United States of America
| | - Reza Sameni
- Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, United States of America
- Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, United States of America
| |
Collapse
|
9
|
Luo J, Zhang M, Li H, Tao D, Gao R. A Smartphone-Based M-Health Monitoring System for Arrhythmia Diagnosis. BIOSENSORS 2024; 14:201. [PMID: 38667194 PMCID: PMC11047874 DOI: 10.3390/bios14040201] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/02/2024] [Revised: 02/28/2024] [Accepted: 04/16/2024] [Indexed: 04/28/2024]
Abstract
Deep learning technology has been widely adopted in the research of automatic arrhythmia detection. However, there are several limitations in existing diagnostic models, e.g., difficulties in extracting temporal information from long-term ECG signals, a plethora of parameters, and sluggish operation speed. Additionally, the diagnosis performance of arrhythmia is prone to mistakes from signal noise. This paper proposes a smartphone-based m-health system for arrhythmia diagnosis. First, we design a cycle-GAN-based ECG denoising model which takes real-world noise signals as input and aims to produce clean ECG signals. In order to train its two generators and two discriminators simultaneously, we explore an unsupervised pre-training strategy to initialize the generator and accelerate the convergence speed during training. Second, we propose an arrhythmia diagnosis model based on the time convolution network (TCN). This model can identify 34 common arrhythmia events using eight-lead ECG signals, and we deploy such a model on the Android platform to develop an at-home ECG monitoring system. Experimental results have demonstrated that our approach outperforms the existing noise reduction methods and arrhythmia diagnosis models in terms of denoising effect, recognition accuracy, model size, and operation speed, making it more suitable for deployment on mobile devices for m-health monitoring services.
Collapse
Affiliation(s)
| | | | | | | | - Ruipeng Gao
- School of Software Enginerring, Beijing Jiaotong University, Beijing 100044, China; (J.L.); (M.Z.); (H.L.); (D.T.)
| |
Collapse
|
10
|
Guo Y, Tang Q, Li S, Chen Z. Reconstruction of Missing Electrocardiography Signals from Photoplethysmography Data Using Deep Neural Network. Bioengineering (Basel) 2024; 11:365. [PMID: 38671786 PMCID: PMC11048151 DOI: 10.3390/bioengineering11040365] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2024] [Revised: 04/04/2024] [Accepted: 04/08/2024] [Indexed: 04/28/2024] Open
Abstract
ECG helps in diagnosing heart disease by recording heart activity. During long-term measurements, data loss occurs due to sensor detachment. Therefore, research into the reconstruction of missing ECG data is essential. However, ECG requires user participation and cannot be used for continuous heart monitoring. Continuous monitoring of PPG signals is conversely low-cost and easy to carry out. In this study, a deep neural network model is proposed for the reconstruction of missing ECG signals using PPG data. This model is an end-to-end deep learning neural network utilizing WNet architecture as a basis, on which a bidirectional long short-term memory network is added in establishing a second model. The performance of both models is verified using 146 records from the MIMIC III matched subset. Compared with the reference, the ECG reconstructed using the proposed model has a Pearson's correlation coefficient of 0.851, root mean square error (RMSE) of 0.075, percentage root mean square difference (PRD) of 5.452, and a Fréchet distance (FD) of 0.302. The experimental results demonstrate that it is feasible to reconstruct missing ECG signals from PPG.
Collapse
Affiliation(s)
- Yanke Guo
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China; (Y.G.); (S.L.)
| | - Qunfeng Tang
- School of Life and Environmental Sciences, Guilin University of Electronic Technology, Guilin 541004, China;
| | - Shiyong Li
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China; (Y.G.); (S.L.)
| | - Zhencheng Chen
- School of Life and Environmental Sciences, Guilin University of Electronic Technology, Guilin 541004, China;
| |
Collapse
|
11
|
Sohn J, Shin H, Lee J, Kim HC. Validation of Electrocardiogram Based Photoplethysmogram Generated Using U-Net Based Generative Adversarial Networks. JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2024; 8:140-157. [PMID: 38273980 PMCID: PMC10805750 DOI: 10.1007/s41666-023-00156-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2022] [Revised: 10/24/2023] [Accepted: 11/13/2023] [Indexed: 01/27/2024]
Abstract
Photoplethysmogram (PPG) performs an important role in alarming atrial fibrillation (AF). While the importance of PPG is emphasized, there is insufficient amount of openly available atrial fibrillation PPG data. We propose a U-net-based generative adversarial network (GAN) which synthesize PPG from paired electrocardiogram (ECG). To measure the performance of the proposed GAN, we compared the generated PPG to reference PPG in terms of morphology similarity and also examined its influence on AF detection classifier performance. First, morphology was compared using two different metrics against the reference signal: percent root mean square difference (PRD) and Pearson correlation coefficient. The mean PRD and Pearson correlation coefficient were 27% and 0.94, respectively. Heart rate variability (HRV) of the reference AF ECG and the generated PPG were compared as well. The p-value of the paired t-test was 0.248, indicating that no significant difference was observed between the two HRV values. Second, to validate the generated AF PPG dataset, four different datasets were prepared combining the generated PPG and real AF PPG. Each dataset was used to optimize a classification model while maintaining the same architecture. A test dataset was prepared to test the performance of each optimized model. Subsequently, these datasets were used to test the hypothesis whether the generated data benefits the training of an AF classifier. Comparing the performance metrics of each optimized model, the training dataset consisting of generated and real AF PPG showed a test accuracy result of 0.962, which was close to that of the dataset consisting only of real AF PPG data at 0.961. Furthermore, both models yielded the same F1 score of 0.969. Lastly, using only the generated AF PPG dataset resulted in test accuracy of 0.945, indicating that the trained model was capable of generating valuable AF PPG. Therefore, it can be concluded that the generated AF PPG can be used to augment insufficient data. To summarize, this study proposes a GAN-based method to generate atrial fibrillation PPG that can be used for training atrial fibrillation PPG classification models.
Collapse
Affiliation(s)
- Jangjay Sohn
- Institute of Medical & Biological Engineering, Medical Research Center, Seoul National University College of Medicine, Seoul, Korea
- Department of Electronic Engineering, Hanyang University, Seoul, Korea
| | - Heean Shin
- Samsung SDS R&D Center, Seoul, Republic of Korea
| | - Joonnyong Lee
- Mellowing Factory Co., Ltd., 131 Sapeyong-daero 57-gil, Seocho-gu, Seoul, 06535 Republic of Korea
| | - Hee Chan Kim
- Interdisciplinary Program in Bioengineering, Seoul National University, Seoul, Korea
- Department of Biomedical Engineering, Seoul National University College of Medicine, 103, Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
| |
Collapse
|
12
|
Zhou F, Li J. ECG data enhancement method using generate adversarial networks based on Bi-LSTM and CBAM. Physiol Meas 2024; 45:025003. [PMID: 38266299 DOI: 10.1088/1361-6579/ad2218] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2023] [Accepted: 01/24/2024] [Indexed: 01/26/2024]
Abstract
Objective.The classification performance of electrocardiogram (ECG) classification algorithms is easily affected by data imbalance, which often leads to poor model prediction performance for a few classes and a consequent decrease in the overall performance of the model.Approach.To address this problem, this paper proposed an ECG data augmentation method based on a generative adversarial network (GAN) that combines bidirectional long short-term memory (Bi-LSTM) networks and convolutional block attention mechanism (CBAM) to improve the overall performance of ECG classification models. In this paper, we used two ECG databases, namely the MIT-BIH arrhythmia (MIT-BIH-AR) database and the Chinese cardiovascular disease database (CCDD). The quality of the ECG signals produced by the generated models was assessed using the percent relative difference, root mean square error, Frechet distance, dynamic time warping (DTW), and Pearson correlation metrics. In addition, we also validated the impact of our proposed data augmentation method on ECG classification performance on MIT-BIH-AR database and CCDD.Main results.On the MIT-BIH-AR database, the overall accuracy of the data-enhanced balanced dataset was improved to 99.46% for 15 types of heartbeat classification task. On the CCDD, which focuses on the detection of ventricular precession (PVC), the overall accuracy of PVC detection improved to 99.15% after performing data enhancement.Significance.The experimental results indicate that the data augmentation method proposed in this paper can further improve the ECG classification performance.
Collapse
Affiliation(s)
- Feiyan Zhou
- Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, 541004, People's Republic of China
- Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, People's Republic of China
| | - Jiajia Li
- Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, 541004, People's Republic of China
- Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, People's Republic of China
| |
Collapse
|
13
|
Kolk MZH, Ruipérez-Campillo S, Alvarez-Florez L, Deb B, Bekkers EJ, Allaart CP, Van Der Lingen ALCJ, Clopton P, Išgum I, Wilde AAM, Knops RE, Narayan SM, Tjong FVY. Dynamic prediction of malignant ventricular arrhythmias using neural networks in patients with an implantable cardioverter-defibrillator. EBioMedicine 2024; 99:104937. [PMID: 38118401 PMCID: PMC10772563 DOI: 10.1016/j.ebiom.2023.104937] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 10/20/2023] [Accepted: 12/12/2023] [Indexed: 12/22/2023] Open
Abstract
BACKGROUND Risk stratification for ventricular arrhythmias currently relies on static measurements that fail to adequately capture dynamic interactions between arrhythmic substrate and triggers over time. We trained and internally validated a dynamic machine learning (ML) model and neural network that extracted features from longitudinally collected electrocardiograms (ECG), and used these to predict the risk of malignant ventricular arrhythmias. METHODS A multicentre study in patients implanted with an implantable cardioverter-defibrillator (ICD) between 2007 and 2021 in two academic hospitals was performed. Variational autoencoders (VAEs), which combine neural networks with variational inference principles, and can learn patterns and structure in data without explicit labelling, were trained to encode the mean ECG waveforms from the limb leads into 16 variables. Supervised dynamic ML models using these latent ECG representations and clinical baseline information were trained to predict malignant ventricular arrhythmias treated by the ICD. Model performance was evaluated on a hold-out set, using time-dependent receiver operating characteristic (ROC) and calibration curves. FINDINGS 2942 patients (61.7 ± 13.9 years, 25.5% female) were included, with a total of 32,129 ECG recordings during a mean follow-up of 43.9 ± 35.9 months. The mean time-varying area under the ROC curve for the dynamic model was 0.738 ± 0.07, compared to 0.639 ± 0.03 for a static (i.e. baseline-only model). Feature analyses indicated dynamic changes in latent ECG representations, particularly those affecting the T-wave morphology, were of highest importance for model predictions. INTERPRETATION Dynamic ML models and neural networks effectively leverage routinely collected longitudinal ECG recordings for personalised and updated predictions of malignant ventricular arrhythmias, outperforming static models. FUNDING This publication is part of the project DEEP RISK ICD (with project number 452019308) of the research programme Rubicon which is (partly) financed by the Dutch Research Council (NWO). This research is partly funded by the Amsterdam Cardiovascular Sciences (personal grant F.V.Y.T).
Collapse
Affiliation(s)
- Maarten Z H Kolk
- Department of Clinical and Experimental Cardiology, Amsterdam UMC Location University of Amsterdam, Heart Center, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, the Netherlands
| | - Samuel Ruipérez-Campillo
- Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA; Department of Information Technology and Electrical Engineering, Swiss Federal Institute of Technology Zurich (ETHz), Gloriastrasse 35, Zurich, Switzerland; ITACA Institute, Universtitat Politècnica de València, Camino de Vera S/n, Valencia, Spain
| | - Laura Alvarez-Florez
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Center Location University of Amsterdam, Meibergdreef 9, Amsterdam, the Netherlands
| | - Brototo Deb
- Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA
| | - Erik J Bekkers
- Faculty of Science, University of Amsterdam, Science Park 904, Amsterdam, the Netherlands
| | - Cornelis P Allaart
- Department of Cardiology, Amsterdam UMC, Location VU Medical Center, De Boelelaan 1118, Amsterdam, the Netherlands
| | | | - Paul Clopton
- Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA
| | - Ivana Išgum
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Center Location University of Amsterdam, Meibergdreef 9, Amsterdam, the Netherlands; Faculty of Science, University of Amsterdam, Science Park 904, Amsterdam, the Netherlands; Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, the Netherlands
| | - Arthur A M Wilde
- Department of Clinical and Experimental Cardiology, Amsterdam UMC Location University of Amsterdam, Heart Center, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, the Netherlands
| | - Reinoud E Knops
- Department of Clinical and Experimental Cardiology, Amsterdam UMC Location University of Amsterdam, Heart Center, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, the Netherlands
| | - Sanjiv M Narayan
- Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA
| | - Fleur V Y Tjong
- Department of Clinical and Experimental Cardiology, Amsterdam UMC Location University of Amsterdam, Heart Center, Meibergdreef 9, Amsterdam, the Netherlands; Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA; Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, the Netherlands.
| |
Collapse
|
14
|
Mehri M, Calmon G, Odille F, Oster J, Lalande A. A Generative Adversarial Network to Synthesize 3D Magnetohydrodynamic Distortions for Electrocardiogram Analyses Applied to Cardiac Magnetic Resonance Imaging. SENSORS (BASEL, SWITZERLAND) 2023; 23:8691. [PMID: 37960391 PMCID: PMC10649946 DOI: 10.3390/s23218691] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Revised: 10/13/2023] [Accepted: 10/20/2023] [Indexed: 11/15/2023]
Abstract
Recently, deep learning (DL) models have been increasingly adopted for automatic analyses of medical data, including electrocardiograms (ECGs). Large, available ECG datasets, generally of high quality, often lack specific distortions, which could be helpful for enhancing DL-based algorithms. Synthetic ECG datasets could overcome this limitation. A generative adversarial network (GAN) was used to synthesize realistic 3D magnetohydrodynamic (MHD) distortion templates, as observed during magnetic resonance imaging (MRI), and then added to available ECG recordings to produce an augmented dataset. Similarity metrics, as well as the accuracy of a DL-based R-peak detector trained with and without data augmentation, were used to evaluate the effectiveness of the synthesized data. Three-dimensional MHD distortions produced by the proposed GAN were similar to the measured ones used as input. The precision of a DL-based R-peak detector, tested on actual unseen data, was significantly enhanced by data augmentation; its recall was higher when trained with augmented data. Using synthesized MHD-distorted ECGs significantly improves the accuracy of a DL-based R-peak detector, with a good generalization capacity. This provides a simple and effective alternative to collecting new patient data. DL-based algorithms for ECG analyses can suffer from bias or gaps in training datasets. Using a GAN to synthesize new data, as well as metrics to evaluate its performance, can overcome the scarcity issue of data availability.
Collapse
Affiliation(s)
- Maroua Mehri
- Epsidy, 54000 Nancy, France; (M.M.); (G.C.)
- Ecole Nationale d’Ingénieurs de Sousse, LATIS-Laboratory of Advanced Technology and Intelligent Systems, Université de Sousse, 4023 Sousse, Tunisia
| | | | - Freddy Odille
- Epsidy, 54000 Nancy, France; (M.M.); (G.C.)
- IADI-Imagerie Adaptative Diagnostique et Interventionnelle, Inserm U1254, Université de Lorraine, 54000 Nancy, France;
- CIC-IT 1433, Inserm, CHRU de Nancy, Université de Lorraine, 54000 Nancy, France
| | - Julien Oster
- IADI-Imagerie Adaptative Diagnostique et Interventionnelle, Inserm U1254, Université de Lorraine, 54000 Nancy, France;
- CIC-IT 1433, Inserm, CHRU de Nancy, Université de Lorraine, 54000 Nancy, France
| | - Alain Lalande
- ICMUB Laboratory, CNRS 6302, University of Burgundy, 21000 Dijon, France;
- Department of Medical Imaging, University Hospital of Dijon, 21079 Dijon, France
| |
Collapse
|
15
|
Iftikhar N, Hussain AI, Fatima T, Alsuwayt B, Althaiban AK. Bioactivity-Guided Isolation and Antihypertensive Activity of Citrullus colocynthis Polyphenols in Rats with Genetic Model of Hypertension. MEDICINA (KAUNAS, LITHUANIA) 2023; 59:1880. [PMID: 37893598 PMCID: PMC10608828 DOI: 10.3390/medicina59101880] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Revised: 10/10/2023] [Accepted: 10/16/2023] [Indexed: 10/29/2023]
Abstract
Background and Objectives: Citrullus colocynthis belongs to the Cucurbitaceae family and is a wild medicinal plant used in folk literature to treat various diseases. The purpose of the current study was to explore the antihypertensive and antioxidant potentials of Citrullus colocynthis (CC) polyphenol-rich fractions using a spontaneous hypertensive rat (SHR) model. Materials and Methods: The concentrated aqueous ethanol extract of CC fruit was successively fractioned using solvents of increasing polarity, i.e., hexane, chloroform, ethyl acetate and n-butanol. The obtained extracts were analyzed for total phenolic content (TPC), total flavonoid content (TFC) and total flavonol content (TOF). Moreover, the CC extracts were further evaluated for radical scavenging capacity using 2,2-diphenyl-1-picrylhydrazyl (DPPH) and 2,2-azino-bis-3-ethylbenzothiazoline-6-sulfonic acid (ABTS) assays and antioxidant activity using inhibition of linoleic acid peroxidation and determination of reducing potential protocols. The phytochemical components were characterized by HPLC-MWD-ESI-MS in positive ionization mode. Results: The results showed that ethyl acetate fraction (EAF) exhibited a higher content of phenolic compounds in term of TPC (289 mg/g), TFC (7.6 mg/g) and TOF (35.7 mg/g). EAF showed higher antioxidant and DPPH and ABTS scavenging activities with SC50 values of 6.2 and 79.5 µg/mL, respectively. LCMS analysis revealed that twenty polyphenol compounds were identified in the EAF, including phenolic acids and flavonoids, mainly myricetin and quercetin derivatives. The in vivo antihypertensive activity of EAF of CC on SHR revealed that it significantly decreased the mean arterial pressure (MAP), systolic blood pressure (SBP), diastolic blood pressures (DBP) and pulse pressure (PP) as compared to normal and hypertensive control groups. Moreover, EAF of CC significantly reduced the oxidative stress in the animals in a dose-dependent manner by normalizing the levels of superoxide dismutase (SOD), malondialdehyde (MDA), reduced glutathione (GSH), nitric oxide (NOx) and total antioxidant capacity (TAC). Furthermore, the treatment groups, especially the 500 mg of EAF per kg body weight (EA-500) group, significantly (p ≤ 0.05) improved the electrocardiogram (ECG) pattern and pulse wave velocity (PWV). Conclusion: It was concluded that the EAF of CC is a rich source of polyphenols and showed the best antioxidant activity and antihypertensive potential in SHR.
Collapse
Affiliation(s)
- Neelam Iftikhar
- Natural Product and Synthetic Chemistry Laboratory, Department of Chemistry, Government College University Faisalabad, Faisalabad 38000, Pakistan;
| | - Abdullah Ijaz Hussain
- Natural Product and Synthetic Chemistry Laboratory, Department of Chemistry, Government College University Faisalabad, Faisalabad 38000, Pakistan;
- Central Hi-Tech Laboratory, Government College University Faisalabad, Faisalabad 38000, Pakistan
| | - Tabinda Fatima
- Department of Pharmaceutical Chemistry, College of Pharmacy, University of Hafr Al Batin, Hafar Al Batin 39524, Saudi Arabia;
| | - Bader Alsuwayt
- Department of Pharmacy Practice, College of Pharmacy, University of Hafr Al Batin, Hafar Al Batin 39524, Saudi Arabia; (B.A.); (A.K.A.)
| | - Abdullah K. Althaiban
- Department of Pharmacy Practice, College of Pharmacy, University of Hafr Al Batin, Hafar Al Batin 39524, Saudi Arabia; (B.A.); (A.K.A.)
| |
Collapse
|
16
|
Zama MH, Schwenker F. ECG Synthesis via Diffusion-Based State Space Augmented Transformer. SENSORS (BASEL, SWITZERLAND) 2023; 23:8328. [PMID: 37837158 PMCID: PMC10575261 DOI: 10.3390/s23198328] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/09/2023] [Revised: 09/25/2023] [Accepted: 10/03/2023] [Indexed: 10/15/2023]
Abstract
Cardiovascular diseases (CVDs) are a major global health concern, causing significant morbidity and mortality. AI's integration with healthcare offers promising solutions, with data-driven techniques, including ECG analysis, emerging as powerful tools. However, privacy concerns pose a major barrier to distributing healthcare data for addressing data-driven CVD classification. To address confidentiality issues related to sensitive health data distribution, we propose leveraging artificially synthesized data generation. Our contribution introduces a novel diffusion-based model coupled with a State Space Augmented Transformer. This synthesizes conditional 12-lead electrocardiograms based on the 12 multilabeled heart rhythm classes of the PTB-XL dataset, with each lead depicting the heart's electrical activity from different viewpoints. Recent advances establish diffusion models as groundbreaking generative tools, while the State Space Augmented Transformer captures long-term dependencies in time series data. The quality of generated samples was assessed using metrics like Dynamic Time Warping (DTW) and Maximum Mean Discrepancy (MMD). To evaluate authenticity, we assessed the similarity of performance of a pre-trained classifier on both generated and real ECG samples.
Collapse
Affiliation(s)
- Md Haider Zama
- Department of Computer Engineering, Jamia Millia Islamia, New Delhi 110025, India;
| | - Friedhelm Schwenker
- Institute of Neural Information Processing, Ulm University, 89081 Ulm, Germany
| |
Collapse
|
17
|
Peppes N, Tsakanikas P, Daskalakis E, Alexakis T, Adamopoulou E, Demestichas K. FoGGAN: Generating Realistic Parkinson's Disease Freezing of Gait Data Using GANs. SENSORS (BASEL, SWITZERLAND) 2023; 23:8158. [PMID: 37836988 PMCID: PMC10574838 DOI: 10.3390/s23198158] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 09/23/2023] [Accepted: 09/27/2023] [Indexed: 10/15/2023]
Abstract
Data scarcity in the healthcare domain is a major drawback for most state-of-the-art technologies engaging artificial intelligence. The unavailability of quality data due to both the difficulty to gather and label them as well as due to their sensitive nature create a breeding ground for data augmentation solutions. Parkinson's Disease (PD) which can have a wide range of symptoms including motor impairments consists of a very challenging case for quality data acquisition. Generative Adversarial Networks (GANs) can help alleviate such data availability issues. In this light, this study focuses on a data augmentation solution engaging Generative Adversarial Networks (GANs) using a freezing of gait (FoG) symptom dataset as input. The data generated by the so-called FoGGAN architecture presented in this study are almost identical to the original as concluded by a variety of similarity metrics. This highlights the significance of such solutions as they can provide credible synthetically generated data which can be utilized as training dataset inputs to AI applications. Additionally, a DNN classifier's performance is evaluated using three different evaluation datasets and the accuracy results were quite encouraging, highlighting that the FOGGAN solution could lead to the alleviation of the data shortage matter.
Collapse
Affiliation(s)
- Nikolaos Peppes
- Institute of Communication and Computer Systems, National Technical University of Athens, 15773 Athens, Greece; (P.T.); (E.D.); (T.A.); (E.A.)
| | - Panagiotis Tsakanikas
- Institute of Communication and Computer Systems, National Technical University of Athens, 15773 Athens, Greece; (P.T.); (E.D.); (T.A.); (E.A.)
| | - Emmanouil Daskalakis
- Institute of Communication and Computer Systems, National Technical University of Athens, 15773 Athens, Greece; (P.T.); (E.D.); (T.A.); (E.A.)
| | - Theodoros Alexakis
- Institute of Communication and Computer Systems, National Technical University of Athens, 15773 Athens, Greece; (P.T.); (E.D.); (T.A.); (E.A.)
| | - Evgenia Adamopoulou
- Institute of Communication and Computer Systems, National Technical University of Athens, 15773 Athens, Greece; (P.T.); (E.D.); (T.A.); (E.A.)
| | - Konstantinos Demestichas
- Department of Agricultural Economics and Rural Development, Agricultural University of Athens, 11855 Athens, Greece;
| |
Collapse
|
18
|
Vaziri S, Liu H, Xie E, Ratiney H, Sdika M, Lupo JM, Xu D, Li Y. Evaluation of deep learning models for quality control of MR spectra. Front Neurosci 2023; 17:1219343. [PMID: 37706154 PMCID: PMC10495580 DOI: 10.3389/fnins.2023.1219343] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Accepted: 08/10/2023] [Indexed: 09/15/2023] Open
Abstract
Purpose While 3D MR spectroscopic imaging (MRSI) provides valuable spatial metabolic information, one of the hurdles for clinical translation is its interpretation, with voxel-wise quality control (QC) as an essential and the most time-consuming step. This work evaluates the accuracy of machine learning (ML) models for automated QC filtering of individual spectra from 3D healthy control and patient datasets. Methods A total of 53 3D MRSI datasets from prior studies (30 neurological diseases, 13 brain tumors, and 10 healthy controls) were included in the study. Three ML models were evaluated: a random forest classifier (RF), a convolutional neural network (CNN), and an inception CNN (ICNN) along with two hybrid models: CNN + RF, ICNN + RF. QC labels used for training were determined manually through consensus of two MRSI experts. Normalized and cropped real-valued spectra was used as input. A cross-validation approach was used to separate datasets into training/validation/testing sets of aggregated voxels. Results All models achieved a minimum AUC of 0.964 and accuracy of 0.910. In datasets from neurological disease and controls, the CNN model produced the highest AUC (0.982), while the RF model achieved the highest AUC in patients with brain tumors (0.976). Within tumor lesions, which typically exhibit abnormal metabolism, the CNN AUC was 0.973 while that of the RF was 0.969. Data quality inference times were on the order of seconds for an entire 3D dataset, offering drastic time reduction compared to manual labeling. Conclusion ML methods accurately and rapidly performed automated QC. Results in tumors highlights the applicability to a variety of metabolic conditions.
Collapse
Affiliation(s)
- Sana Vaziri
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States
| | - Huawei Liu
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States
| | - Emily Xie
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States
| | - Hélène Ratiney
- Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, Lyon, France
| | - Michaël Sdika
- Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, Lyon, France
| | - Janine M. Lupo
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States
- UC San Francisco/UC Berkeley Graduate Program in Bioengineering, San Francisco, CA, United States
| | - Duan Xu
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States
- UC San Francisco/UC Berkeley Graduate Program in Bioengineering, San Francisco, CA, United States
| | - Yan Li
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States
| |
Collapse
|
19
|
Metshein M, Abdullayev A, Gautier A, Larras B, Frappe A, Cardiff B, Annus P, Land R, Märtens O. Sensor-Location-Specific Joint Acquisition of Peripheral Artery Bioimpedance and Photoplethysmogram for Wearable Applications. SENSORS (BASEL, SWITZERLAND) 2023; 23:7111. [PMID: 37631647 PMCID: PMC10457752 DOI: 10.3390/s23167111] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/15/2023] [Revised: 08/05/2023] [Accepted: 08/08/2023] [Indexed: 08/27/2023]
Abstract
BACKGROUND Cardiovascular diseases (CVDs), being the culprit for one-third of deaths globally, constitute a challenge for biomedical instrumentation development, especially for early disease detection. Pulsating arterial blood flow, providing access to cardiac-related parameters, involves the whole body. Unobtrusive and continuous acquisition of electrical bioimpedance (EBI) and photoplethysmography (PPG) constitute important techniques for monitoring the peripheral arteries, requiring novel approaches and clever means. METHODS In this work, five peripheral arteries were selected for EBI and PPG signal acquisition. The acquisition sites were evaluated based on the signal morphological parameters. A small-data-based deep learning model, which increases the data by dividing them into cardiac periods, was proposed to evaluate the continuity of the signals. RESULTS The highest sensitivity of EBI was gained for the carotid artery (0.86%), three times higher than that for the next best, the posterior tibial artery (0.27%). The excitation signal parameters affect the measured EBI, confirming the suitability of classical 100 kHz frequency (average probability of 52.35%). The continuity evaluation of the EBI signals confirmed the advantage of the carotid artery (59.4%), while the posterior tibial artery (49.26%) surpasses the radial artery (48.17%). The PPG signal, conversely, commends the location of the posterior tibial artery (97.87%). CONCLUSIONS The peripheral arteries are highly suitable for non-invasive EBI and PPG signal acquisition. The posterior tibial artery constitutes a candidate for the joint acquisition of EBI and PPG signals in sensor-fusion-based wearable devices-an important finding of this research.
Collapse
Affiliation(s)
- Margus Metshein
- Thomas Johann Seebeck Department of Electronics, Tallinn University of Technology, Ehitajate Tee 5, 19086 Tallinn, Estonia
| | - Anar Abdullayev
- Thomas Johann Seebeck Department of Electronics, Tallinn University of Technology, Ehitajate Tee 5, 19086 Tallinn, Estonia
| | - Antoine Gautier
- University Lille, CNRS, Centrale Lille, Junia, University Polytechnique Hauts-de-France, UMR 8520-IEMN, F-59000 Lille, France
| | - Benoit Larras
- University Lille, CNRS, Centrale Lille, Junia, University Polytechnique Hauts-de-France, UMR 8520-IEMN, F-59000 Lille, France
| | - Antoine Frappe
- University Lille, CNRS, Centrale Lille, Junia, University Polytechnique Hauts-de-France, UMR 8520-IEMN, F-59000 Lille, France
| | - Barry Cardiff
- School of Electrical and Electronic Engineering, University College Dublin, D04V1W8 Dublin, Ireland
| | - Paul Annus
- Thomas Johann Seebeck Department of Electronics, Tallinn University of Technology, Ehitajate Tee 5, 19086 Tallinn, Estonia
| | - Raul Land
- Thomas Johann Seebeck Department of Electronics, Tallinn University of Technology, Ehitajate Tee 5, 19086 Tallinn, Estonia
| | - Olev Märtens
- Thomas Johann Seebeck Department of Electronics, Tallinn University of Technology, Ehitajate Tee 5, 19086 Tallinn, Estonia
| |
Collapse
|
20
|
Baj G, Gandin I, Scagnetto A, Bortolussi L, Cappelletto C, Di Lenarda A, Barbati G. Comparison of discrimination and calibration performance of ECG-based machine learning models for prediction of new-onset atrial fibrillation. BMC Med Res Methodol 2023; 23:169. [PMID: 37481514 PMCID: PMC10363301 DOI: 10.1186/s12874-023-01989-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2023] [Accepted: 07/13/2023] [Indexed: 07/24/2023] Open
Abstract
BACKGROUND Machine learning (ML) methods to build prediction models starting from electrocardiogram (ECG) signals are an emerging research field. The aim of the present study is to investigate the performances of two ML approaches based on ECGs for the prediction of new-onset atrial fibrillation (AF), in terms of discrimination, calibration and sample size dependence. METHODS We trained two models to predict new-onset AF: a convolutional neural network (CNN), that takes as input the raw ECG signals, and an eXtreme Gradient Boosting model (XGB), that uses the signal's extracted features. A penalized logistic regression model (LR) was used as a benchmark. Discrimination was evaluated with the area under the ROC curve, while calibration with the integrated calibration index. We investigated the dependence of models' performances on the sample size and on class imbalance corrections introduced with random under-sampling. RESULTS CNN's discrimination was the most affected by the sample size, outperforming XGB and LR only around n = 10.000 observations. Calibration showed only a small dependence on the sample size for all the models considered. Balancing the training set with random undersampling did not improve discrimination in any of the models. Instead, the main effect of imbalance corrections was to worsen the models' calibration (for CNN, integrated calibration index from 0.014 [0.01, 0.018] to 0.17 [0.16, 0.19]). The sample size emerged as a fundamental point for developing the CNN model, especially in terms of discrimination (AUC = 0.75 [0.73, 0.77] when n = 10.000, AUC = 0.80 [0.79, 0.81] when n = 150.000). The effect of the sample size on the other two models was weaker. Imbalance corrections led to poorly calibrated models, for all the approaches considered, reducing the clinical utility of the models. CONCLUSIONS Our results suggest that the choice of approach in the analysis of ECG should be based on the amount of data available, preferring more standard models for small datasets. Moreover, imbalance correction methods should be avoided when developing clinical prediction models, where calibration is crucial.
Collapse
Affiliation(s)
- Giovanni Baj
- Department of Mathematics and Geosciences, University of Trieste, Trieste, Italy.
| | - Ilaria Gandin
- Department of Medical Sciences, Biostatistics Unit, University of Trieste, Trieste, Italy
| | - Arjuna Scagnetto
- Cardiovascular Center, Territorial Specialistic Department, University Hospital and Health Services of Trieste, Trieste, Italy
| | - Luca Bortolussi
- Department of Mathematics and Geosciences, University of Trieste, Trieste, Italy
| | - Chiara Cappelletto
- Cardiovascular Center, Territorial Specialistic Department, University Hospital and Health Services of Trieste, Trieste, Italy
| | - Andrea Di Lenarda
- Cardiovascular Center, Territorial Specialistic Department, University Hospital and Health Services of Trieste, Trieste, Italy
| | - Giulia Barbati
- Department of Medical Sciences, Biostatistics Unit, University of Trieste, Trieste, Italy
| |
Collapse
|
21
|
Asadi M, Poursalim F, Loni M, Daneshtalab M, Sjödin M, Gharehbaghi A. Accurate detection of paroxysmal atrial fibrillation with certified-GAN and neural architecture search. Sci Rep 2023; 13:11378. [PMID: 37452165 PMCID: PMC10349064 DOI: 10.1038/s41598-023-38541-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Accepted: 07/10/2023] [Indexed: 07/18/2023] Open
Abstract
This paper presents a novel machine learning framework for detecting PxAF, a pathological characteristic of electrocardiogram (ECG) that can lead to fatal conditions such as heart attack. To enhance the learning process, the framework involves a generative adversarial network (GAN) along with a neural architecture search (NAS) in the data preparation and classifier optimization phases. The GAN is innovatively invoked to overcome the class imbalance of the training data by producing the synthetic ECG for PxAF class in a certified manner. The effect of the certified GAN is statistically validated. Instead of using a general-purpose classifier, the NAS automatically designs a highly accurate convolutional neural network architecture customized for the PxAF classification task. Experimental results show that the accuracy of the proposed framework exhibits a high value of 99.0% which not only enhances state-of-the-art by up to 5.1%, but also improves the classification performance of the two widely-accepted baseline methods, ResNet-18, and Auto-Sklearn, by [Formula: see text] and [Formula: see text].
Collapse
Affiliation(s)
- Mehdi Asadi
- Department of Electrical Engineering, Tarbiat Modares University, Tehran, Iran
| | | | - Mohammad Loni
- School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden
| | - Masoud Daneshtalab
- School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden
| | - Mikael Sjödin
- School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden
| | - Arash Gharehbaghi
- Department of Biomedical Engineering, Linköping University, Linköping, Sweden.
| |
Collapse
|
22
|
Wang X, Sahiner B, Scully CG, Cha KH. AFE-GAN: Synthesizing Electrocardiograms with Atrial Fibrillation Characteristics Using Generative Adversarial Networks . ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-5. [PMID: 38083445 DOI: 10.1109/embc40787.2023.10340565] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
Labeled ECG data in diseased state are, however, relatively scarce due to various concerns including patient privacy and low prevalence. We propose the first study in its kind that synthesizes atrial fibrillation (AF)-like ECG signals from normal ECG signals using the AFE-GAN, a generative adversarial network. Our AFE-GAN adjusts both beat morphology and rhythm variability when generating the atrial fibrillation-like ECG signals. Two publicly available arrhythmia detectors classified 72.4% and 77.2% of our generated signals as AF in a four-class (normal, AF, other abnormal, noisy) classification. This work shows the feasibility to synthesize abnormal ECG signals from normal ECG signals.Clinical significance - The AF ECG signal generated with our AFE-GAN has the potential to be used as training materials for health practitioners or be used as class-balance supplements for training automatic AF detectors.
Collapse
|
23
|
Rahman MM, Rivolta MW, Badilini F, Sassi R. A Systematic Survey of Data Augmentation of ECG Signals for AI Applications. SENSORS (BASEL, SWITZERLAND) 2023; 23:s23115237. [PMID: 37299964 DOI: 10.3390/s23115237] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Revised: 05/23/2023] [Accepted: 05/27/2023] [Indexed: 06/12/2023]
Abstract
AI techniques have recently been put under the spotlight for analyzing electrocardiograms (ECGs). However, the performance of AI-based models relies on the accumulation of large-scale labeled datasets, which is challenging. To increase the performance of AI-based models, data augmentation (DA) strategies have been developed recently. The study presented a comprehensive systematic literature review of DA for ECG signals. We conducted a systematic search and categorized the selected documents by AI application, number of leads involved, DA method, classifier, performance improvements after DA, and datasets employed. With such information, this study provided a better understanding of the potential of ECG augmentation in enhancing the performance of AI-based ECG applications. This study adhered to the rigorous PRISMA guidelines for systematic reviews. To ensure comprehensive coverage, publications between 2013 and 2023 were searched across multiple databases, including IEEE Explore, PubMed, and Web of Science. The records were meticulously reviewed to determine their relevance to the study's objective, and those that met the inclusion criteria were selected for further analysis. Consequently, 119 papers were deemed relevant for further review. Overall, this study shed light on the potential of DA to advance the field of ECG diagnosis and monitoring.
Collapse
Affiliation(s)
- Md Moklesur Rahman
- Dipartimento di Informatica, Università degli Studi di Milano, 20133 Milan, Italy
| | | | - Fabio Badilini
- School of Nursing, University of California, San Francisco, CA 94143, USA
- AMPS-LLC, New York, NY 10025, USA
| | - Roberto Sassi
- Dipartimento di Informatica, Università degli Studi di Milano, 20133 Milan, Italy
| |
Collapse
|
24
|
Hazratifard M, Agrawal V, Gebali F, Elmiligi H, Mamun M. Ensemble Siamese Network (ESN) Using ECG Signals for Human Authentication in Smart Healthcare System. SENSORS (BASEL, SWITZERLAND) 2023; 23:4727. [PMID: 37430641 DOI: 10.3390/s23104727] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/20/2023] [Revised: 05/10/2023] [Accepted: 05/11/2023] [Indexed: 07/12/2023]
Abstract
Advancements in digital communications that permit remote patient visits and condition monitoring can be attributed to a revolution in digital healthcare systems. Continuous authentication based on contextual information offers a number of advantages over traditional authentication, including the ability to estimate the likelihood that the users are who they claim to be on an ongoing basis over the course of an entire session, making it a much more effective security measure for proactively regulating authorized access to sensitive data. Current authentication models that rely on machine learning have their shortcomings, such as the difficulty in enrolling new users to the system or model training sensitivity to imbalanced datasets. To address these issues, we propose using ECG signals, which are easily accessible in digital healthcare systems, for authentication through an Ensemble Siamese Network (ESN) that can handle small changes in ECG signals. Adding preprocessing for feature extraction to this model can result in superior results. We trained this model on ECG-ID and PTB benchmark datasets, achieving 93.6% and 96.8% accuracy and 1.76% and 1.69% equal error rates, respectively. The combination of data availability, simplicity, and robustness makes it an ideal choice for smart healthcare and telehealth.
Collapse
Affiliation(s)
- Mehdi Hazratifard
- Department of Electrical and Computer Engineering, University of Victoria, Victoria, BC V8W 2Y2, Canada
| | - Vibhav Agrawal
- Department of Electrical and Computer Engineering, University of Victoria, Victoria, BC V8W 2Y2, Canada
| | - Fayez Gebali
- Department of Electrical and Computer Engineering, University of Victoria, Victoria, BC V8W 2Y2, Canada
| | - Haytham Elmiligi
- Department of Electrical and Computer Engineering, University of Victoria, Victoria, BC V8W 2Y2, Canada
| | - Mohammad Mamun
- National Research Council of Canada, Government of Canada, Ottawa, ON K1A 0R6, Canada
| |
Collapse
|
25
|
Deep Convolutional Generative Adversarial Network with LSTM for ECG Denoising. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2023; 2023:6737102. [PMID: 36818542 PMCID: PMC9937753 DOI: 10.1155/2023/6737102] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/17/2022] [Revised: 11/23/2022] [Accepted: 01/19/2023] [Indexed: 02/12/2023]
Abstract
The electrocardiogram (ECG), as an essential basis for the diagnosis of cardiovascular diseases, is usually disturbed by various noise. To obtain accurate human physiological information from ECG, the denoising and reconstruction of ECG are critical. In this paper, we proposed an ECG denoising method referred to as LSTM-DCGAN which is based on an improved generative adversarial network (GAN). The overall network structure is composed of multiple layers of convolutional networks. Furthermore, the convolutional features can be connected to their time series order dependence by adding LSTM layers after each convolutional layer. To verify the effectiveness and the denoising performance of the improved network structure, we test the proposed algorithm on the famous MIT-BIH Arrhythmia Database with different levels of noise from the MIT-BIH Noise Stress Test Database. Experimental results show that our method can remove the single noise and the mixed noise while retaining the complete ECG information. For the mixed noise removal, the average SNRimp, RMSE, and PRD are 19.254 dB, 0.028, and 10.350, respectively. Compared with the state-of-the-art methods, DCGAN, and the LSTM-GAN methods, our method obtains the higher SNRimp and the lower RMSE and PRD scores. These results suggest that the proposed LSTM-DCGAN approach has a significant advantage for ECG processing and application in complex scenes.
Collapse
|
26
|
Mäkynen M, Ng GA, Li X, Schlindwein FS. Wearable Devices Combined with Artificial Intelligence-A Future Technology for Atrial Fibrillation Detection? SENSORS (BASEL, SWITZERLAND) 2022; 22:8588. [PMID: 36433186 PMCID: PMC9697321 DOI: 10.3390/s22228588] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Revised: 11/02/2022] [Accepted: 11/03/2022] [Indexed: 06/16/2023]
Abstract
Atrial fibrillation (AF) is the most common cardiac arrhythmia in the world. The arrhythmia and methods developed to cure it have been studied for several decades. However, professionals worldwide are still working to improve treatment quality. One novel technology that can be useful is a wearable device. The two most used recordings from these devices are photoplethysmogram (PPG) and electrocardiogram (ECG) signals. As the price lowers, these devices will become significant technology to increase sensitivity, for monitoring and for treatment quality support. This is important as AF can be challenging to detect in advance, especially during home monitoring. Modern artificial intelligence (AI) has the potential to respond to this challenge. AI has already achieved state of the art results in many applications, including bioengineering. In this perspective, we discuss wearable devices combined with AI for AF detection, an approach that enables a new era of possibilities for the future.
Collapse
Affiliation(s)
- Marko Mäkynen
- School of Engineering, University of Leicester, Leicester LE1 7RH, UK; (M.M.); (X.L.)
| | - G. Andre Ng
- School of Engineering, University of Leicester, Leicester LE1 7RH, UK; (M.M.); (X.L.)
- National Institute for Health Research Leicester Cardiovascular Biomedical Research Centre, Glenfield Hospital, Leicester LE5 4PW, UK;
| | - Xin Li
- School of Engineering, University of Leicester, Leicester LE1 7RH, UK; (M.M.); (X.L.)
| | | |
Collapse
|
27
|
Deep Learning-Based Data Augmentation and Model Fusion for Automatic Arrhythmia Identification and Classification Algorithms. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:1577778. [PMID: 35990162 PMCID: PMC9388256 DOI: 10.1155/2022/1577778] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/09/2022] [Revised: 07/09/2022] [Accepted: 07/19/2022] [Indexed: 11/18/2022]
Abstract
Automated ECG-based arrhythmia detection is critical for early cardiac disease prevention and diagnosis. Recently, deep learning algorithms have been widely applied for arrhythmia detection with great success. However, the lack of labeled ECG data and low classification accuracy can have a significant impact on the overall effectiveness of a classification algorithm. In order to better apply deep learning methods to arrhythmia classification, in this study, feature extraction and classification strategy based on generative adversarial network data augmentation and model fusion are proposed to address these problems. First, the arrhythmia sparse data is augmented by generative adversarial networks. Then, aiming at the identification of different types of arrhythmias in long-term ECG, a spatial information fusion model based on ResNet and a temporal information fusion model based on BiLSTM are proposed. The model effectively fuses the location information of the nearest neighbors through the local feature extraction part of the generated ECG feature map and obtains the correlation of the global features by autonomous learning in multiple spaces through the BiLSTM network in the part of the global feature extraction. In addition, an attention mechanism is introduced to enhance the features of arrhythmia-type signal segments, and this mechanism can effectively focus on the extraction of key information to form a feature vector for final classification. Finally, it is validated by the enhanced MIT-BIH arrhythmia database. The experimental results demonstrate that the proposed classification technique enhances arrhythmia diagnostic accuracy by 99.4%, and the algorithm has high recognition performance and clinical value.
Collapse
|
28
|
Wang M, Yin X, Zhu Y, Hu J. Representation Learning and Pattern Recognition in Cognitive Biometrics: A Survey. SENSORS (BASEL, SWITZERLAND) 2022; 22:5111. [PMID: 35890799 PMCID: PMC9320620 DOI: 10.3390/s22145111] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/17/2022] [Revised: 07/01/2022] [Accepted: 07/05/2022] [Indexed: 01/27/2023]
Abstract
Cognitive biometrics is an emerging branch of biometric technology. Recent research has demonstrated great potential for using cognitive biometrics in versatile applications, including biometric recognition and cognitive and emotional state recognition. There is a major need to summarize the latest developments in this field. Existing surveys have mainly focused on a small subset of cognitive biometric modalities, such as EEG and ECG. This article provides a comprehensive review of cognitive biometrics, covering all the major biosignal modalities and applications. A taxonomy is designed to structure the corresponding knowledge and guide the survey from signal acquisition and pre-processing to representation learning and pattern recognition. We provide a unified view of the methodological advances in these four aspects across various biosignals and applications, facilitating interdisciplinary research and knowledge transfer across fields. Furthermore, this article discusses open research directions in cognitive biometrics and proposes future prospects for developing reliable and secure cognitive biometric systems.
Collapse
Affiliation(s)
- Min Wang
- School of Engineering and Information Technology, University of New South Wales, Canberra, ACT 2612, Australia; (M.W.); (X.Y.)
| | - Xuefei Yin
- School of Engineering and Information Technology, University of New South Wales, Canberra, ACT 2612, Australia; (M.W.); (X.Y.)
| | - Yanming Zhu
- School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia;
| | - Jiankun Hu
- School of Engineering and Information Technology, University of New South Wales, Canberra, ACT 2612, Australia; (M.W.); (X.Y.)
| |
Collapse
|
29
|
Liu B. Research on Emotion Analysis and Psychoanalysis Application With Convolutional Neural Network and Bidirectional Long Short-Term Memory. Front Psychol 2022; 13:852242. [PMID: 35846596 PMCID: PMC9280270 DOI: 10.3389/fpsyg.2022.852242] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2022] [Accepted: 03/21/2022] [Indexed: 11/13/2022] Open
Abstract
This study mainly focuses on the emotion analysis method in the application of psychoanalysis based on sentiment recognition. The method is applied to the sentiment recognition module in the server, and the sentiment recognition function is effectively realized through the improved convolutional neural network and bidirectional long short-term memory (C-BiL) model. First, the implementation difficulties of the C-BiL model and specific sentiment classification design are described. Then, the specific design process of the C-BiL model is introduced, and the innovation of the C-BiL model is indicated. Finally, the experimental results of the models are compared and analyzed. Among the deep learning models, the accuracy of the C-BiL model designed in this study is relatively high irrespective of the binary classification, the three classification, or the five classification, with an average improvement of 2.47% in Diary data set, 2.16% in Weibo data set, and 2.08% in Fudan data set. Therefore, the C-BiL model designed in this study can not only successfully classify texts but also effectively improve the accuracy of text sentiment recognition.
Collapse
|
30
|
Noguer J, Contreras I, Mujahid O, Beneyto A, Vehi J. Generation of Individualized Synthetic Data for Augmentation of the Type 1 Diabetes Data Sets Using Deep Learning Models. SENSORS 2022; 22:s22134944. [PMID: 35808449 PMCID: PMC9269743 DOI: 10.3390/s22134944] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Revised: 06/24/2022] [Accepted: 06/27/2022] [Indexed: 12/14/2022]
Abstract
In this paper, we present a methodology based on generative adversarial network architecture to generate synthetic data sets with the intention of augmenting continuous glucose monitor data from individual patients. We use these synthetic data with the aim of improving the overall performance of prediction models based on machine learning techniques. Experiments were performed on two cohorts of patients suffering from type 1 diabetes mellitus with significant differences in their clinical outcomes. In the first contribution, we have demonstrated that the chosen methodology is able to replicate the intrinsic characteristics of individual patients following the statistical distributions of the original data. Next, a second contribution demonstrates the potential of synthetic data to improve the performance of machine learning approaches by testing and comparing different prediction models for the problem of predicting nocturnal hypoglycemic events in type 1 diabetic patients. The results obtained for both generative and predictive models are quite encouraging and set a precedent in the use of generative techniques to train new machine learning models.
Collapse
Affiliation(s)
- Josep Noguer
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (J.N.); (I.C.); (O.M.); (A.B.)
| | - Ivan Contreras
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (J.N.); (I.C.); (O.M.); (A.B.)
| | - Omer Mujahid
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (J.N.); (I.C.); (O.M.); (A.B.)
| | - Aleix Beneyto
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (J.N.); (I.C.); (O.M.); (A.B.)
| | - Josep Vehi
- Institut d’Informàtica i Aplicacions, Universitat de Girona, 17003 Girona, Spain; (J.N.); (I.C.); (O.M.); (A.B.)
- Centro de Investigación Biomédica en Red de Diabetes y Enfermedades Metabólicas Asociadas (CIBERDEM), 28029 Madrid, Spain
- Correspondence:
| |
Collapse
|
31
|
Beetz M, Banerjee A, Grau V. Multi-Domain Variational Autoencoders for Combined Modeling of MRI-Based Biventricular Anatomy and ECG-Based Cardiac Electrophysiology. Front Physiol 2022; 13:886723. [PMID: 35755443 PMCID: PMC9213788 DOI: 10.3389/fphys.2022.886723] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Accepted: 05/02/2022] [Indexed: 11/16/2022] Open
Abstract
Human cardiac function is characterized by a complex interplay of mechanical deformation and electrophysiological conduction. Similar to the underlying cardiac anatomy, these interconnected physiological patterns vary considerably across the human population with important implications for the effectiveness of clinical decision-making and the accuracy of computerized heart models. While many previous works have investigated this variability separately for either cardiac anatomy or physiology, this work aims to combine both aspects in a single data-driven approach and capture their intricate interdependencies in a multi-domain setting. To this end, we propose a novel multi-domain Variational Autoencoder (VAE) network to capture combined Electrocardiogram (ECG) and Magnetic Resonance Imaging (MRI)-based 3D anatomy information in a single model. Each VAE branch is specifically designed to address the particular challenges of the respective input domain, enabling efficient encoding, reconstruction, and synthesis of multi-domain cardiac signals. Our method achieves high reconstruction accuracy on a United Kingdom Biobank dataset, with Chamfer Distances between reconstructed and input anatomies below the underlying image resolution and ECG reconstructions outperforming multiple single-domain benchmarks by a considerable margin. The proposed VAE is capable of generating realistic virtual populations of arbitrary size with good alignment in clinical metrics between the synthesized and gold standard anatomies and Maximum Mean Discrepancy (MMD) scores of generated ECGs below those of comparable single-domain approaches. Furthermore, we observe the latent space of our VAE to be highly interpretable with separate components encoding different aspects of anatomical and ECG variability. Finally, we demonstrate that the combined anatomy and ECG representation improves the performance in a cardiac disease classification task by 3.9% in terms of Area Under the Receiver Operating Characteristic (AUROC) curve over the best corresponding single-domain modeling approach.
Collapse
Affiliation(s)
- Marcel Beetz
- Department of Engineering Science, Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, United Kingdom
| | - Abhirup Banerjee
- Department of Engineering Science, Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, United Kingdom
- Radcliffe Department of Medicine, Division of Cardiovascular Medicine, University of Oxford, Oxford, United Kingdom
| | - Vicente Grau
- Department of Engineering Science, Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, United Kingdom
| |
Collapse
|
32
|
Ke S, Liu W. Consistency of Multiagent Distributed Generative Adversarial Networks. IEEE TRANSACTIONS ON CYBERNETICS 2022; 52:4886-4896. [PMID: 33079688 DOI: 10.1109/tcyb.2020.3022695] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
The mathematical properties of generative adversarial networks (GANs) are presented via opinion dynamics, in which the discriminator is regarded as an agent while the generator is regarded as the principal (or another type of agent) in a GAN. In some cases, the overall convergence must be achieved through establishing a local information interaction between one agent and its neighbors via the multiagent system consistency theory and algorithms. So the goals of the multiagent consistency algorithm and the Nash equilibrium of GANs are virtually identical. Then, the existence of the Degroot model solution proves that the generator and discriminator in GANs can reach a consensus on the distribution function. Therefore, a new sufficient and necessary condition for the existence of a Nash equilibrium in GANs is obtained. Furthermore, a novel multiagent distributed GAN (MADGAN) is proposed to address the multiagent cognitive consistency problem in large-scale distributed network, based on the social group wisdom and the influence of the network structure on the agent. The nodes of a multiagent network are regarded as discriminators and generators, the discriminator with a relatively large degree of influence as a leader, and the generator as a follower, the lines with the degree denote the influence between the agents. The conditions of consensus are presented for a multigenerator and multidiscriminator (multiagent) distributed GAN by analyzing the existence of stationary distribution to the Markov chain of multiple agent states. Finally, theoretical results are verified with simulation based on the MNIST dataset.
Collapse
|
33
|
Segmentation of Drug-Treated Cell Image and Mitochondrial-Oxidative Stress Using Deep Convolutional Neural Network. OXIDATIVE MEDICINE AND CELLULAR LONGEVITY 2022; 2022:5641727. [PMID: 35663204 PMCID: PMC9162846 DOI: 10.1155/2022/5641727] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/03/2022] [Accepted: 04/27/2022] [Indexed: 12/27/2022]
Abstract
Most multicellular organisms require apoptosis, or programmed cell death, to function properly and survive. On the other hand, morphological and biochemical characteristics of apoptosis have remained remarkably consistent throughout evolution. Apoptosis is thought to have at least three functionally distinct phases: induction, effector, and execution. Recent studies have revealed that reactive oxygen species (ROS) and the oxidative stress could play an essential role in apoptosis. Advanced microscopic imaging techniques allow biologists to acquire an extensive amount of cell images within a matter of minutes which rule out the manual analysis of image data acquisition. The segmentation of cell images is often considered the cornerstone and central problem for image analysis. Currently, the issue of segmentation of mitochondrial cell images via deep learning receives increasing attention. The manual labeling of cell images is time-consuming and challenging to train a pro. As a courtesy method, mitochondrial cell imaging (MCI) is proposed to identify the normal, drug-treated, and diseased cells. Furthermore, cell movement (fission and fusion) is measured to evaluate disease risk. The newly proposed drug-treated, normal, and diseased image segmentation (DNDIS) algorithm can quickly segment mitochondrial cell images without supervision and further segment the highly drug-treated cells in the picture, i.e., normal, diseased, and drug-treated cells. The proposed method is based on the ResNet-50 deep learning algorithm. The dataset consists of 414 images mainly categorised into different sets (drug, diseased, and normal) used microscopically. The proposed automated segmentation method has outperformed and secured high precision (90%, 92%, and 94%); moreover, it also achieves proper training. This study will benefit medicines and diseased cell measurements in medical tests and clinical practices.
Collapse
|
34
|
Tang Q, Chen Z, Guo Y, Liang Y, Ward R, Menon C, Elgendi M. Robust Reconstruction of Electrocardiogram Using Photoplethysmography: A Subject-Based Model. Front Physiol 2022; 13:859763. [PMID: 35547575 PMCID: PMC9082149 DOI: 10.3389/fphys.2022.859763] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2022] [Accepted: 03/21/2022] [Indexed: 11/13/2022] Open
Abstract
Electrocardiography and photoplethysmography are non-invasive techniques that measure signals from the cardiovascular system. While the cycles of the two measurements are highly correlated, the correlation between the waveforms has rarely been studied. Measuring the photoplethysmogram (PPG) is much easier and more convenient than the electrocardiogram (ECG). Recent research has shown that PPG can be used to reconstruct the ECG, indicating that practitioners can gain a deep understanding of the patients’ cardiovascular health using two physiological signals (PPG and ECG) while measuring only PPG. This study proposes a subject-based deep learning model that reconstructs an ECG using a PPG and is based on the bidirectional long short-term memory model. Because the ECG waveform may vary from subject to subject, this model is subject-specific. The model was tested using 100 records from the MIMIC III database. Of these records, 50 had a circulatory disease. The results show that a long ECG signal could be effectively reconstructed from PPG, which is, to our knowledge, the first attempt in this field. A length of 228 s of ECG was constructed by the model, which was trained and validated using 60 s of PPG and ECG signals. To segment the data, a different approach that segments the data into short time segments of equal length (and that do not rely on beats and beat detection) was investigated. Segmenting the PPG and ECG time series data into equal segments of 1-min width gave the optimal results. This resulted in a high Pearson’s correlation coefficient between the reconstructed 228 s of ECG and referenced ECG of 0.818, while the root mean square error was only 0.083 mV, and the dynamic time warping distance was 2.12 mV per second on average.
Collapse
Affiliation(s)
- Qunfeng Tang
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, China.,Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada
| | - Zhencheng Chen
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, China
| | - Yanke Guo
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, China
| | - Yongbo Liang
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, China
| | - Rabab Ward
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada
| | - Carlo Menon
- Biomedical and Mobile Health Technology Laboratory, Department of Health Sciences and Technology, Zurich, Switzerland
| | - Mohamed Elgendi
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada.,Biomedical and Mobile Health Technology Laboratory, Department of Health Sciences and Technology, Zurich, Switzerland
| |
Collapse
|
35
|
Ball STM, Celik N, Sayari E, Abdul Kadir L, O’Brien F, Barrett-Jolley R. DeepGANnel: Synthesis of fully annotated single molecule patch-clamp data using generative adversarial networks. PLoS One 2022; 17:e0267452. [PMID: 35536793 PMCID: PMC9089889 DOI: 10.1371/journal.pone.0267452] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2021] [Accepted: 04/09/2022] [Indexed: 11/19/2022] Open
Abstract
Development of automated analysis tools for “single ion channel” recording is hampered by the lack of available training data. For machine learning based tools, very large training sets are necessary with sample-by-sample point labelled data (e.g., 1 sample point every 100microsecond). In an experimental context, such data are labelled with human supervision, and whilst this is feasible for simple experimental analysis, it is infeasible to generate the enormous datasets that would be necessary for a big data approach using hand crafting. In this work we aimed to develop methods to generate simulated ion channel data that is free from assumptions and prior knowledge of noise and underlying hidden Markov models. We successfully leverage generative adversarial networks (GANs) to build an end-to-end pipeline for generating an unlimited amount of labelled training data from a small, annotated ion channel “seed” record, and this needs no prior knowledge of theoretical dynamical ion channel properties. Our method utilises 2D CNNs to maintain the synchronised temporal relationship between the raw and idealised record. We demonstrate the applicability of the method with 5 different data sources and show authenticity with t-SNE and UMAP projection comparisons between real and synthetic data. The model would be easily extendable to other time series data requiring parallel labelling, such as labelled ECG signals or raw nanopore sequencing data.
Collapse
Affiliation(s)
- Sam T. M. Ball
- Faculty of Health and Life Science, University of Liverpool, Liverpool, United Kingdom
| | - Numan Celik
- Faculty of Health and Life Science, University of Liverpool, Liverpool, United Kingdom
| | - Elaheh Sayari
- Faculty of Health and Life Science, University of Liverpool, Liverpool, United Kingdom
| | - Lina Abdul Kadir
- Faculty of Health and Life Science, University of Liverpool, Liverpool, United Kingdom
| | - Fiona O’Brien
- Faculty of Health and Life Science, University of Liverpool, Liverpool, United Kingdom
| | - Richard Barrett-Jolley
- Faculty of Health and Life Science, University of Liverpool, Liverpool, United Kingdom
- * E-mail:
| |
Collapse
|
36
|
Chen YW, Li YJ, Deng P, Yang ZY, Zhong KH, Zhang LG, Chen Y, Zhi HY, Hu XY, Gu JT, Ning JL, Lu KZ, Zhang J, Xia ZY, Qin XL, Yi B. Learning to predict in-hospital mortality risk in the intensive care unit with attention-based temporal convolution network. BMC Anesthesiol 2022; 22:119. [PMID: 35461225 PMCID: PMC9034533 DOI: 10.1186/s12871-022-01625-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2021] [Accepted: 03/21/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Dynamic prediction of patient mortality risk in the ICU with time series data is limited due to high dimensionality, uncertainty in sampling intervals, and other issues. A new deep learning method, temporal convolution network (TCN), makes it possible to deal with complex clinical time series data in ICU. We aimed to develop and validate it to predict mortality risk using time series data from MIMIC III dataset. METHODS A total of 21,139 records of ICU stays were analysed and 17 physiological variables from the MIMIC III dataset were used to predict mortality risk. Then we compared the model performance of the attention-based TCN with that of traditional artificial intelligence (AI) methods. RESULTS The area under receiver operating characteristic (AUCROC) and area under precision-recall curve (AUC-PR) of attention-based TCN for predicting the mortality risk 48 h after ICU admission were 0.837 (0.824 -0.850) and 0.454, respectively. The sensitivity and specificity of attention-based TCN were 67.1% and 82.6%, respectively, compared to the traditional AI method, which had a low sensitivity (< 50%). CONCLUSIONS The attention-based TCN model achieved better performance in the prediction of mortality risk with time series data than traditional AI methods and conventional score-based models. The attention-based TCN mortality risk model has the potential for helping decision-making for critical patients. TRIAL REGISTRATION Data used for the prediction of mortality risk were extracted from the freely accessible MIMIC III dataset. The project was approved by the Institutional Review Boards of Beth Israel Deaconess Medical Center (Boston, MA) and the Massachusetts Institute of Technology (Cambridge, MA). Requirement for individual patient consent was waived because the project did not impact clinical care and all protected health information was deidentified. The data were accessed via a data use agreement between PhysioNet, a National Institutes of Health-supported data repository (https://www.physionet.org/), and one of us (Yu-wen Chen, Certification Number: 28341490). All methods were carried out in accordance with the institutional guidelines and regulations.
Collapse
Affiliation(s)
- Yu-Wen Chen
- Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, 610041, China.,Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Science, Chongqing, 400714, China.,University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Yu-Jie Li
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Peng Deng
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Zhi-Yong Yang
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Kun-Hua Zhong
- Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, 610041, China.,Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Science, Chongqing, 400714, China.,University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Li-Ge Zhang
- Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, 610041, China.,University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Yang Chen
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Hong-Yu Zhi
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Xiao-Yan Hu
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Jian-Teng Gu
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Jiao-Lin Ning
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Kai-Zhi Lu
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China
| | - Ju Zhang
- Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Science, Chongqing, 400714, China
| | - Zheng-Yuan Xia
- Department of Anaesthesiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, China
| | - Xiao-Lin Qin
- Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, 610041, China. .,University of Chinese Academy of Sciences, Beijing, 100049, China.
| | - Bin Yi
- Department of Anaesthesiology, Southwest Hospital, The Third Military Medical University (Army Medical University), Chongqing, 400038, China.
| |
Collapse
|
37
|
Generative Adversarial Networks for Creating Synthetic Nucleic Acid Sequences of Cat Genome. Int J Mol Sci 2022; 23:ijms23073701. [PMID: 35409058 PMCID: PMC8998662 DOI: 10.3390/ijms23073701] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Revised: 03/23/2022] [Accepted: 03/25/2022] [Indexed: 01/04/2023] Open
Abstract
Nucleic acids are the basic units of deoxyribonucleic acid (DNA) sequencing. Every organism demonstrates different DNA sequences with specific nucleotides. It reveals the genetic information carried by a particular DNA segment. Nucleic acid sequencing expresses the evolutionary changes among organisms and revolutionizes disease diagnosis in animals. This paper proposes a generative adversarial networks (GAN) model to create synthetic nucleic acid sequences of the cat genome tuned to exhibit specific desired properties. We obtained the raw sequence data from Illumina next generation sequencing. Various data preprocessing steps were performed using Cutadapt and DADA2 tools. The processed data were fed to the GAN model that was designed following the architecture of Wasserstein GAN with gradient penalty (WGAN-GP). We introduced a predictor and an evaluator in our proposed GAN model to tune the synthetic sequences to acquire certain realistic properties. The predictor was built for extracting samples with a promoter sequence, and the evaluator was built for filtering samples that scored high for motif-matching. The filtered samples were then passed to the discriminator. We evaluated our model based on multiple metrics and demonstrated outputs for latent interpolation, latent complementation, and motif-matching. Evaluation results showed our proposed GAN model achieved 93.7% correlation with the original data and produced significant outcomes as compared to existing models for sequence generation.
Collapse
|
38
|
Short Single-Lead ECG Signal Delineation-Based Deep Learning: Implementation in Automatic Atrial Fibrillation Identification. SENSORS 2022; 22:s22062329. [PMID: 35336500 PMCID: PMC8953093 DOI: 10.3390/s22062329] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Revised: 03/09/2022] [Accepted: 03/14/2022] [Indexed: 01/27/2023]
Abstract
Physicians manually interpret an electrocardiogram (ECG) signal morphology in routine clinical practice. This activity is a monotonous and abstract task that relies on the experience of understanding ECG waveform meaning, including P-wave, QRS-complex, and T-wave. Such a manual process depends on signal quality and the number of leads. ECG signal classification based on deep learning (DL) has produced an automatic interpretation; however, the proposed method is used for specific abnormality conditions. When the ECG signal morphology change to other abnormalities, it cannot proceed automatically. To generalize the automatic interpretation, we aim to delineate ECG waveform. However, the output of delineation process only ECG waveform duration classes for P-wave, QRS-complex, and T-wave. It should be combined with a medical knowledge rule to produce the abnormality interpretation. The proposed model is applied for atrial fibrillation (AF) identification. This study meets the AF criteria with RR irregularities and the absence of P-waves in essential oscillations for even more accurate identification. The QT database by Physionet is utilized for developing the delineation model, and it validates with The Lobachevsky University Database. The results show that our delineation model works properly, with 98.91% sensitivity, 99.01% precision, 99.79% specificity, 99.79% accuracy, and a 98.96% F1 score. We use about 4058 normal sinus rhythm records and 1804 AF records from the experiment to identify AF conditions that are taken from three datasets. The comprehensive testing has produced higher negative predictive value and positive predictive value. This means that the proposed model can identify AF conditions from ECG signal delineation. Our approach can considerably contribute to AF diagnosis with these results.
Collapse
|
39
|
An Intelligent Music Production Technology Based on Generation Confrontation Mechanism. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:5083146. [PMID: 35186065 PMCID: PMC8853763 DOI: 10.1155/2022/5083146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/12/2021] [Accepted: 12/22/2021] [Indexed: 12/04/2022]
Abstract
In recent years, with the development of deep neural network becoming more and more mature, especially after the proposal of generative confrontation mechanism, academia has made many achievements in the research of image, video and text generation. Therefore, scholars began to use similar attempts in the research of music generation. Therefore, based on the existing theoretical technology and research work, this paper studies music production, and then proposes an intelligent music production technology based on generation confrontation mechanism to enrich the research in the field of computer music generation. This paper takes the music generation method based on generation countermeasure mechanism as the research topic, and mainly studies the following: after studying the existing music generation model based on generation countermeasure network, a time structure model for maintaining music coherence is proposed. In music generation, avoid manual input and ensure the interdependence between tracks. At the same time, this paper studies and implements the generation method of discrete music events based on multi track, including multi track correlation model and discrete processing. The lakh MIDI data set is studied. On this basis, the lakh MIDI is pre-processed to obtain the LMD piano roll data set, which is used in the music generation experiment of MCT-GAN. When studying the multi track music generation based on generation countermeasure network, this paper studies and analyzes three models, and puts forward the multi track music generation method based on CT-GAN, which mainly improves the existing music generation model based on GAN. Finally, the generation results of MCT-GAN are compared with those of Muse-GAN, so as to reflect the improvement effect of MCT-GAN. Select 20 auditees to listen to the generated music and real music and distinguish them. Finally, analyze them according to the evaluation results. After evaluation, it is concluded that the research effect of multi track music generation based on CT-GAN is improved.
Collapse
|
40
|
Quilodrán-Casas C, Silva VLS, Arcucci R, Heaney CE, Guo Y, Pain CC. Digital twins based on bidirectional LSTM and GAN for modelling the COVID-19 pandemic. Neurocomputing 2022; 470:11-28. [PMID: 34703079 PMCID: PMC8531233 DOI: 10.1016/j.neucom.2021.10.043] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2021] [Revised: 08/04/2021] [Accepted: 10/19/2021] [Indexed: 01/09/2023]
Abstract
The outbreak of the coronavirus disease 2019 (COVID-19) has now spread throughout the globe infecting over 150 million people and causing the death of over 3.2 million people. Thus, there is an urgent need to study the dynamics of epidemiological models to gain a better understanding of how such diseases spread. While epidemiological models can be computationally expensive, recent advances in machine learning techniques have given rise to neural networks with the ability to learn and predict complex dynamics at reduced computational costs. Here we introduce two digital twins of a SEIRS model applied to an idealised town. The SEIRS model has been modified to take account of spatial variation and, where possible, the model parameters are based on official virus spreading data from the UK. We compare predictions from one digital twin based on a data-corrected Bidirectional Long Short-Term Memory network with predictions from another digital twin based on a predictive Generative Adversarial Network. The predictions given by these two frameworks are accurate when compared to the original SEIRS model data. Additionally, these frameworks are data-agnostic and could be applied to towns, idealised or real, in the UK or in other countries. Also, more compartments could be included in the SEIRS model, in order to study more realistic epidemiological behaviour.
Collapse
Affiliation(s)
- César Quilodrán-Casas
- Data Science Institute, Department of Computing, Imperial College London, UK
- Department of Earth Science & Engineering, Imperial College London, UK
| | | | - Rossella Arcucci
- Data Science Institute, Department of Computing, Imperial College London, UK
- Department of Earth Science & Engineering, Imperial College London, UK
| | - Claire E Heaney
- Department of Earth Science & Engineering, Imperial College London, UK
| | - YiKe Guo
- Data Science Institute, Department of Computing, Imperial College London, UK
| | - Christopher C Pain
- Data Science Institute, Department of Computing, Imperial College London, UK
- Department of Earth Science & Engineering, Imperial College London, UK
| |
Collapse
|
41
|
Chen J, Li H, Song L, Zhang G, Hu B, Wang S, Liu S, Li S, Chen T, Liu J. Synthetic aircraft RS image modelling based on improved conditional GAN joint embedding network. Sci Rep 2022; 12:320. [PMID: 35013409 PMCID: PMC8748831 DOI: 10.1038/s41598-021-03880-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2021] [Accepted: 12/10/2021] [Indexed: 11/09/2022] Open
Abstract
Developing an efficient and quality remote sensing (RS) technology using volume and efficient modelling in different aircraft RS images is challenging. Generative models serve as a natural and convenient simulation method. Because aircraft types belong to the fine class under the rough class, the issue of feature entanglement may occur while modelling multiple aircraft classes. Our solution to this issue was a novel first-generation realistic aircraft type simulation system (ATSS-1) based on the RS images. It realised fine modelling of the seven aircraft types based on a real scene by establishing an adaptive weighted conditional attention generative adversarial network and joint geospatial embedding (GE) network. An adaptive weighted conditional batch normalisation attention block solved the subclass entanglement by reassigning the intra-class-wise characteristic responses. Subsequently, an asymmetric residual self-attention module was developed by establishing a remote region asymmetric relationship for mining the finer potential spatial representation. The mapping relationship between the input RS scene and the potential space of the generated samples was explored through the GE network construction that used the selected prior distribution z, as an intermediate representation. A public RS dataset (OPT-Aircraft_V1.0) and two public datasets (MNIST and Fashion-MNIST) were used for simulation model testing. The results demonstrated the effectiveness of ATSS-1, promoting further development of realistic automatic RS simulation.
Collapse
Affiliation(s)
- Junyu Chen
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China.,University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Haiwei Li
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China.
| | - Liyao Song
- School of Information and Communications Engineering, Xi'an Jiaotong University, Xi'an, 710049, China
| | - Geng Zhang
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China.
| | - Bingliang Hu
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China.
| | - Shuang Wang
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China
| | - Song Liu
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China
| | - Siyuan Li
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China
| | - Tieqiao Chen
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China
| | - Jia Liu
- Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an, 710119, China
| |
Collapse
|
42
|
Ben Ali W, Pesaranghader A, Avram R, Overtchouk P, Perrin N, Laffite S, Cartier R, Ibrahim R, Modine T, Hussin JG. Implementing Machine Learning in Interventional Cardiology: The Benefits Are Worth the Trouble. Front Cardiovasc Med 2021; 8:711401. [PMID: 34957230 PMCID: PMC8692711 DOI: 10.3389/fcvm.2021.711401] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2021] [Accepted: 11/08/2021] [Indexed: 12/23/2022] Open
Abstract
Driven by recent innovations and technological progress, the increasing quality and amount of biomedical data coupled with the advances in computing power allowed for much progress in artificial intelligence (AI) approaches for health and biomedical research. In interventional cardiology, the hope is for AI to provide automated analysis and deeper interpretation of data from electrocardiography, computed tomography, magnetic resonance imaging, and electronic health records, among others. Furthermore, high-performance predictive models supporting decision-making hold the potential to improve safety, diagnostic and prognostic prediction in patients undergoing interventional cardiology procedures. These applications include robotic-assisted percutaneous coronary intervention procedures and automatic assessment of coronary stenosis during diagnostic coronary angiograms. Machine learning (ML) has been used in these innovations that have improved the field of interventional cardiology, and more recently, deep Learning (DL) has emerged as one of the most successful branches of ML in many applications. It remains to be seen if DL approaches will have a major impact on current and future practice. DL-based predictive systems also have several limitations, including lack of interpretability and lack of generalizability due to cohort heterogeneity and low sample sizes. There are also challenges for the clinical implementation of these systems, such as ethical limits and data privacy. This review is intended to bring the attention of health practitioners and interventional cardiologists to the broad and helpful applications of ML and DL algorithms to date in the field. Their implementation challenges in daily practice and future applications in the field of interventional cardiology are also discussed.
Collapse
Affiliation(s)
- Walid Ben Ali
- Service Médico-Chirurgical, Valvulopathies-Chirurgie Cardiaque-Cardiologie Interventionelle Structurelle, Hôpital Cardiologique de Haut Lévèque, Bordeaux, France.,Structural Heart Program and Interventional Cardiology, Université de Montréal, Montreal Heart Institute, Montréal, QC, Canada
| | - Ahmad Pesaranghader
- Faculty of Medicine, Research Center, Montreal Heart Institute, Université de Montréal, Montréal, QC, Canada.,Computer Science and Operations Research Department, Mila (Quebec Artificial Intelligence Institute), Montreal, QC, Canada
| | - Robert Avram
- Faculty of Medicine, Research Center, Montreal Heart Institute, Université de Montréal, Montréal, QC, Canada
| | - Pavel Overtchouk
- Interventional Cardiology and Cardiovascular Surgery Centre Hospitalier Regional Universitaire de Lille (CHRU de Lille), Lille, France
| | - Nils Perrin
- Structural Heart Program and Interventional Cardiology, Université de Montréal, Montreal Heart Institute, Montréal, QC, Canada
| | - Stéphane Laffite
- Service Médico-Chirurgical, Valvulopathies-Chirurgie Cardiaque-Cardiologie Interventionelle Structurelle, Hôpital Cardiologique de Haut Lévèque, Bordeaux, France
| | - Raymond Cartier
- Structural Heart Program and Interventional Cardiology, Université de Montréal, Montreal Heart Institute, Montréal, QC, Canada
| | - Reda Ibrahim
- Structural Heart Program and Interventional Cardiology, Université de Montréal, Montreal Heart Institute, Montréal, QC, Canada
| | - Thomas Modine
- Service Médico-Chirurgical, Valvulopathies-Chirurgie Cardiaque-Cardiologie Interventionelle Structurelle, Hôpital Cardiologique de Haut Lévèque, Bordeaux, France
| | - Julie G Hussin
- Faculty of Medicine, Research Center, Montreal Heart Institute, Université de Montréal, Montréal, QC, Canada
| |
Collapse
|
43
|
Engr YS, Lalande A, Afilalo J, Jodoin PM. Generative Adversarial Networks in Cardiology. Can J Cardiol 2021; 38:196-203. [PMID: 34780990 DOI: 10.1016/j.cjca.2021.11.003] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2021] [Revised: 11/04/2021] [Accepted: 11/08/2021] [Indexed: 01/18/2023] Open
Abstract
Generative Adversarial Networks (GANs) are state-of-the-art neural network models used to synthesize images and other data. GANs brought a considerable improvement to the quality of synthetic data, quickly becoming the standard for data generation tasks. In this work, we summarize the applications of GANs in the field of cardiology, including generation of realistic cardiac images, electrocardiography signals, and synthetic electronic health records. The utility of GAN-generated data is discussed with respect to research, clinical care, and academia. Moreover, we present illustrative examples of our GAN-generated cardiac magnetic resonance and echocardiography images, showing the evolution in image quality across six different models, which has become almost indistinguishable from real images. Finally, we discuss future applications, such as modality translation or patient trajectory modeling. Moreover, we discuss the pending challenges that GANs need to overcome, namely their training dynamics, the medical fidelity or the data regulations and ethics questions, to become integrated in cardiology workflows.
Collapse
Affiliation(s)
| | - Alain Lalande
- Laboratoire ImVIA, Université de Bourgogne, 64 rue Sully, 21000 Dijon, France; Medical Imaging Department, University Hospital of Dijon, 1 Bld Jeanne d'Arc, 21079, Dijon, France
| | - Jonathan Afilalo
- Jewish General Hospital, McGill University, 3755 Côte Ste-Catherine Road, Montreal, Qc, Canada, H3T 1E2
| | - Pierre-Marc Jodoin
- Université de Sherbrooke, 2500 Boul. de l'Universite, Sherbrooke, Qc, Canada, J1K 2R1
| |
Collapse
|
44
|
Zhou X, Zhu X, Nakamura K, Noro M. Electrocardiogram Quality Assessment with a Generalized Deep Learning Model Assisted by Conditional Generative Adversarial Networks. Life (Basel) 2021; 11:1013. [PMID: 34685385 PMCID: PMC8539388 DOI: 10.3390/life11101013] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2021] [Revised: 09/14/2021] [Accepted: 09/21/2021] [Indexed: 11/16/2022] Open
Abstract
The electrocardiogram (ECG) is widely used for cardiovascular disease diagnosis and daily health monitoring. Before ECG analysis, ECG quality screening is an essential but time-consuming and experience-dependent work for technicians. An automatic ECG quality assessment method can reduce unnecessary time loss to help cardiologists perform diagnosis. This study aims to develop an automatic quality assessment system to search qualified ECGs for interpretation. The proposed system consists of data augmentation and quality assessment parts. For data augmentation, we train a conditional generative adversarial networks model to get an ECG segment generator, and thus to increase the number of training data. Then, we pre-train a deep quality assessment model based on a training dataset composed of real and generated ECG. Finally, we fine-tune the proposed model using real ECG and validate it on two different datasets composed of real ECG. The proposed system has a generalized performance on the two validation datasets. The model's accuracy is 97.1% and 96.4%, respectively for the two datasets. The proposed method outperforms a shallow neural network model, and also a deep neural network models without being pre-trained by generated ECG. The proposed system demonstrates improved performance in the ECG quality assessment, and it has the potential to be an initial ECG quality screening tool in clinical practice.
Collapse
Affiliation(s)
- Xue Zhou
- Biomedical Information Engineering Lab, The University of Aizu, Aizu-Wakamatsu, Fukushima 965-8580, Japan;
| | - Xin Zhu
- Biomedical Information Engineering Lab, The University of Aizu, Aizu-Wakamatsu, Fukushima 965-8580, Japan;
| | - Keijiro Nakamura
- Division of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo 153-8515, Japan
| | - Mahito Noro
- Division of Cardiovascular Medicine, Odawara Cardiovascular Hospital, Tokyo 250-0873, Japan;
| |
Collapse
|
45
|
Zhang YH, Babaeizadeh S. Synthesis of standard 12‑lead electrocardiograms using two-dimensional generative adversarial networks. J Electrocardiol 2021; 69:6-14. [PMID: 34474312 DOI: 10.1016/j.jelectrocard.2021.08.019] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2021] [Revised: 06/23/2021] [Accepted: 08/15/2021] [Indexed: 11/24/2022]
Abstract
This paper proposes a two-dimensional (2D) bidirectional long short-term memory generative adversarial network (GAN) to produce synthetic standard 12-lead ECGs corresponding to four types of signals-left ventricular hypertrophy (LVH), left branch bundle block (LBBB), acute myocardial infarction (ACUTMI), and Normal. It uses a fully automatic end-to-end process to generate and verify the synthetic ECGs that does not require any visual inspection. The proposed model is able to produce synthetic standard 12-lead ECG signals with success rates of 98% for LVH, 93% for LBBB, 79% for ACUTMI, and 59% for Normal. Statistical evaluation of the data confirms that the synthetic ECGs are not biased towards or overfitted to the training ECGs, and span a wide range of morphological features. This study demonstrates that it is feasible to use a 2D GAN to produce standard 12-lead ECGs suitable to augment artificially a diverse database of real ECGs, thus providing a possible solution to the demand for extensive ECG datasets.
Collapse
Affiliation(s)
- Yu-He Zhang
- Advanced Algorithm Research Center, Philips Healthcare, Cambridge, MA, USA.
| | - Saeed Babaeizadeh
- Advanced Algorithm Research Center, Philips Healthcare, Cambridge, MA, USA
| |
Collapse
|
46
|
Iwana BK, Uchida S. An empirical survey of data augmentation for time series classification with neural networks. PLoS One 2021; 16:e0254841. [PMID: 34264999 PMCID: PMC8282049 DOI: 10.1371/journal.pone.0254841] [Citation(s) in RCA: 65] [Impact Index Per Article: 21.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2021] [Accepted: 07/04/2021] [Indexed: 11/29/2022] Open
Abstract
In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.
Collapse
Affiliation(s)
- Brian Kenji Iwana
- Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan
| | - Seiichi Uchida
- Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan
| |
Collapse
|
47
|
Stabenau HF, Bridge CP, Waks JW. ECGAug: A novel method of generating augmented annotated electrocardiogram QRST complexes and rhythm strips. Comput Biol Med 2021; 134:104408. [PMID: 34010792 DOI: 10.1016/j.compbiomed.2021.104408] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2020] [Revised: 04/12/2021] [Accepted: 04/13/2021] [Indexed: 10/21/2022]
Abstract
Applications of neural networks (NNs) in medicine have increased dramatically in recent years. In order to train a NN that performs ECG segmentation, it can be very time consuming, or even completely prohibitive, to manually annotate fiducial points on enough QRST complexes to reach a high level of performance. Existing methods for time series data augmentation risk creating non-physiological ECG signals that may hamper NN training, and are unable to provide accurate fiducial point locations in the augmented data. We therefore developed ECGAug, a new method which generates an augmented training set of QRST signals (single beats or rhythm strips) with accurate fiducial point annotations. Our algorithm recombines a library of existing, annotated QRS complexes and T waves in physiologic ways, and then performs additional physiological transformations to generate a set of new annotated QRST complexes or rhythm strips to be used for NN training or validation of ECG annotation algorithms. In experiments where we trained NNs to annotate QRST complexes with a limited training dataset, QRST complexes added to the training dataset by ECGAug significantly improved NN performance. We present the ECGAug process, demonstrate its efficacy, and provide links for downloading the open source ECGAug software.
Collapse
Affiliation(s)
- Hans Friedrich Stabenau
- Harvard-Thorndike Electrophysiology Institute, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA
| | - Christopher P Bridge
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Jonathan W Waks
- Harvard-Thorndike Electrophysiology Institute, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
48
|
Priyadarshini I, Cotton C. A novel LSTM-CNN-grid search-based deep neural network for sentiment analysis. THE JOURNAL OF SUPERCOMPUTING 2021; 77:13911-13932. [PMID: 33967391 PMCID: PMC8097246 DOI: 10.1007/s11227-021-03838-w] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 04/21/2021] [Indexed: 06/01/2023]
Abstract
As the number of users getting acquainted with the Internet is escalating rapidly, there is more user-generated content on the web. Comprehending hidden opinions, sentiments, and emotions in emails, tweets, reviews, and comments is a challenge and equally crucial for social media monitoring, brand monitoring, customer services, and market research. Sentiment analysis determines the emotional tone behind a series of words may essentially be used to understand the attitude, opinions, and emotions of users. We propose a novel long short-term memory (LSTM)-convolutional neural networks (CNN)-grid search-based deep neural network model for sentiment analysis. The study considers baseline algorithms like convolutional neural networks, K-nearest neighbor, LSTM, neural networks, LSTM-CNN, and CNN-LSTM which have been evaluated using accuracy, precision, sensitivity, specificity, and F-1 score, on multiple datasets. Our results show that the proposed model based on hyperparameter optimization outperforms other baseline models with an overall accuracy greater than 96%.
Collapse
Affiliation(s)
- Ishaani Priyadarshini
- Department of Electrical and Computer Engineering, University of Delaware, Newark, USA
| | - Chase Cotton
- Department of Electrical and Computer Engineering, University of Delaware, Newark, USA
| |
Collapse
|
49
|
Kuznetsov VV, Moskalenko VA, Gribanov DV, Zolotykh NY. Interpretable Feature Generation in ECG Using a Variational Autoencoder. Front Genet 2021; 12:638191. [PMID: 33868375 PMCID: PMC8049433 DOI: 10.3389/fgene.2021.638191] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2020] [Accepted: 03/01/2021] [Indexed: 12/22/2022] Open
Abstract
We propose a method for generating an electrocardiogram (ECG) signal for one cardiac cycle using a variational autoencoder. Our goal was to encode the original ECG signal using as few features as possible. Using this method we extracted a vector of new 25 features, which in many cases can be interpreted. The generated ECG has quite natural appearance. The low value of the Maximum Mean Discrepancy metric, 3.83 × 10−3, indicates good quality of ECG generation too. The extracted new features will help to improve the quality of automatic diagnostics of cardiovascular diseases. Generating new synthetic ECGs will allow us to solve the issue of the lack of labeled ECG for using them in supervised learning.
Collapse
Affiliation(s)
- V V Kuznetsov
- Institute of Information Technologies, Mathematics, and Mechanics, Lobachevsky State University of Nizhni Novgorod, Nizhni Novgorod, Russia
| | - V A Moskalenko
- Institute of Information Technologies, Mathematics, and Mechanics, Lobachevsky State University of Nizhni Novgorod, Nizhni Novgorod, Russia.,Mathematics of Future Technologies Center, Lobachevsky State University of Nizhni Novgorod, Nizhni Novgorod, Russia
| | - D V Gribanov
- Laboratory of Algorithms and Technologies for Networks Analysis, National Research University Higher School of Economics, Nizhni Novgorod, Russia
| | - Nikolai Yu Zolotykh
- Institute of Information Technologies, Mathematics, and Mechanics, Lobachevsky State University of Nizhni Novgorod, Nizhni Novgorod, Russia.,Mathematics of Future Technologies Center, Lobachevsky State University of Nizhni Novgorod, Nizhni Novgorod, Russia
| |
Collapse
|
50
|
Geng D, Alkhachroum A, Melo Bicchi M, Jagid J, Cajigas I, Chen ZS. Deep learning for robust detection of interictal epileptiform discharges. J Neural Eng 2021; 18. [PMID: 33770777 DOI: 10.1088/1741-2552/abf28e] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2020] [Accepted: 03/26/2021] [Indexed: 01/13/2023]
Abstract
OBJECTIVE Automatic detection of interictal epileptiform discharges (IEDs, short as ``spikes'') from an epileptic brain can help predict seizure recurrence and support the diagnosis of epilepsy. Developing fast, reliable and robust detection methods for IEDs based on scalp or intracortical EEG may facilitate online seizure monitoring and closed-loop neurostimulation. APPROACH We developed a new deep learning approach, which employs a long short-term memory (LSTM) network architecture (``IEDnet'') and an auxiliary classifier generative adversarial network (AC-GAN), to train on both expert-annotated and augmented spike events from intracranial electroencephalography (iEEG) recordings of epilepsy patients. We validated our IEDnet with two real-world iEEG datasets, and compared IEDnet with the support vector machine (SVM) and random forest (RF) classifiers on their detection performances. MAIN RESULTS IEDnet achieved excellent cross-validated detection performances in terms of both sensitivity and specificity, and outperformed SVM and RF. Synthetic spike samples augmented by AC-GAN further improved the detection performance. In addition, the performance of IEDnet was robust with respect to the sampling frequency and noise. Furthermore, we also demonstrated the cross-institutional generalization ability of IEDnet while testing between two datasets. SIGNIFICANCE IEDnet achieves excellent detection performances in identifying interictal spikes. AC-GAN can produce augmented iEEG samples to improve supervised deep learning.
Collapse
Affiliation(s)
- David Geng
- New York University School of Medicine, One Park Avenue, New York, New York, 10016-6402, UNITED STATES
| | - Ayham Alkhachroum
- University of Miami Miller School of Medicine, 1600 NW 10th Avenue, Miami, Florida, 33136-1015, UNITED STATES
| | - Manuel Melo Bicchi
- University of Miami Miller School of Medicine, 1600 NW 10th Avenue, Miami, Florida, 33136-1015, UNITED STATES
| | - Jonathan Jagid
- University of Miami Miller School of Medicine, 1600 NW 10th Avenue, Miami, Florida, 33136-1015, UNITED STATES
| | - Iahn Cajigas
- Department of Neurological Surgery, University of Miami Miller School of Medicine, 1095 NW 14th Ter # D4-6, Miami, Miami, Florida, 33136-1060, UNITED STATES
| | - Zhe Sage Chen
- Psychiatry, New York University School of Medicine, One Park Avenue, Rm 226, New York, New York, 10016, UNITED STATES
| |
Collapse
|