Figure - uploaded by Vahab Vahdat
Content may be subject to copyright.
Figure A.10: Coronary arteries structure. LCA and RCA are the main arteries which supply several branches [68].
Source publication
Myocardial infarction (MI), also known as a heart attack, is one of the common cardiac disorders caused by prolonged myocardial ischemia. For MI patients, specifying the exact location of a heart muscle suffering from blood shortage or stoppage is of crucial importance. Automatic localization systems can support physicians for better decisions in e...
Citations
... The approach relied on a CNN-based deep learning algorithm, achieving 93.53% accuracy. A shallow neural network was employed by Jafarian et al. [80] for classification after performing DWT and PCA on ECG signals. The use of an end-to-end residual deep learning technique and the direct application of a CNN on pre-processed input signals led to 98% accuracy for MI detection. ...
... In Liu et al. [26], it was reported that the Treebagger classifier took 223.13 s for training and 0.67 s for testing. According to Jafarian et al. [80], the deep CNN had a training phase that lasted 1475.5 ± 110.37 s, while MI detection from the test data set was almost instantaneous (0.01-0.02 s). The proposed method was evaluated using Matlab software on a computer equipped with an Intel Core i7 6700 K 3.5 GHz processor and 32 GB of RAM to assess its efficiency in terms of training and classification time, revealing that it took an average of 216.3 s to train and 0.4 s to classify one ECG pattern. ...
Myocardial infarction (MI) poses a significant clinical challenge, necessitating expeditious and precise detection to mitigate potentially fatal outcomes. Current MI diagnosis predominantly relies on electrocardiography (ECG); however, it is fraught with limitations, including inter-observer variability and a reliance on expert interpretation. This study introduces an automated MI detection framework that capitalizes on hybrid signal processing methodologies and deterministic learning theory. The initial step involves the extraction of the Shannon energy envelope (SEE) and its derivative from a single-lead ECG. Integration of the SEE into the ECG’s phase portrait provides a means to capture the underlying nonlinear system dynamics. Subsequently, the application of fast and adaptive multivariate empirical mode decomposition (FA-MVEMD) yields discriminative features originating from the most energetically dominant intrinsic mode components (IMFs) within the SEE. Profound dissimilarities are discernible between ECG signals recorded from healthy subjects and those afflicted with MI. In the subsequent phase, deterministic learning theory, implemented through neural networks, is employed to facilitate the classification of ECG signals into two distinct groups. The method’s efficacy is meticulously evaluated using the PTB diagnostic ECG database, resulting in a noteworthy average classification accuracy of 99.21 $$\%$$ % within a tenfold cross-validation framework. In summation, the findings affirm that the proposed features not only complement conventional ECG attributes but also align closely with the underlying dynamics of the ECG system, ultimately fortifying the automatic detection of MI. The imperative requirement for early and accurate MI diagnosis is addressed through our approach, offering a robust and dependable means to fulfill this pivotal clinical need.
... Using deep learning algorithms, such as CNNs, has shown great promise in accurately diagnosing and predicting various diseases, including heart disease. With the utilization of convolutional neural networks, we can effectively capture local important information in electronic health records and utilize it to make accurate predictions and diagnoses (Jafarian et al., 2020) [4]. The ability of CNNs to capture local important information in electronic health records and utilize it for accurate disease predictions and diagnoses makes them a powerful tool in the development of advanced diagnostic systems for MI in echocardiogram frames. ...
... Investigating the interpretability of deep learning models is crucial for gaining trust from clinicians and ensuring the transparent application of these models in a clinical setting. 4)In addition, the impact of real-time processing and decision support systems based on the enhanced CNN algorithm and ECV-3D network for MI diagnosis requires further exploration. Understanding the practical implementation of these advanced techniques in real-time clinical environments and assessing their impact on clinical decision-making processes is essential for evaluating their potential in improving patient outcomes. ...
... By addressing the interpretability aspect, our study strives to bridge the gap between advanced deep learning techniques and clinical application, ultimately contributing to the development of more transparent and understandable diagnostic models for MI. 4)In addition, we seek to explore the practical implementation of our proposed advanced techniques, particularly the enhanced CNN algorithm and ECV-3D network, in real-time clinical environments. By assessing their impact on clinical decision-making processes, we aim to evaluate their potential to improve patient outcomes and enhance the efficiency of MI diagnosis in a real-world setting. ...
Myocardial infarction is a serious medical condition that requires prompt and accurate diagnosis for effective treatment. In this paper, we present a novel approach for detecting and classifying MI in echocardiogram frames using an enhanced CNN algorithm and ECV-3D network. The proposed method aims to improve the accuracy and efficiency of MI diagnosis by leveraging advanced deep learning techniques. Through extensive experimentation, we demonstrate the effectiveness of our approach in achieving high accuracy and robustness in MI detection and classification. The results indicate the potential of our method to aid in the early and precise diagnosis of MI, thereby contributing to improved patient outcomes and clinical decision-making. After conducting thorough experimentation, our proposed approach has achieved an impressive accuracy of 97.05% in the detection and classification of myocardial infarction in echocardiogram frames. This accomplishment showcases the robustness and reliability of our method, indicating its potential to significantly impact the accurate diagnosis of MI and subsequently improve patient outcomes. Furthermore, the area under the curve attained by our model is 0.82%, reaffirming the efficacy of the enhanced CNN algorithm and ECV-3D network in accurately detecting and classifying MI.It is noteworthy that all the parameters utilized in our approach have demonstrated a high level of accuracy, emphasizing the effectiveness of our deep learning techniques in enhancing the diagnostic process for MI. Moreover, the proposed method is capable of efficiently processing large volumes of echocardiogram frames, making it suitable for real-time clinical applications.
... PTB has been cited in 11 articles and originated as the second-highest utilized dataset. Some of them are enclosed to [23,26,45,46]. ...
... Additional feature extraction techniques using spectrograms have been adopted by the authors, especially when considering ECG signal analysis for the exceptional performance [133][134][135]. The other possible feature extraction methods in ECG signals are Fourier [118,129] and wavelet transformation [40,45,46,136]. In contrast to SVM, the convolutional neural network (CNN) model has been widely endorsed for classification. A few example studies of 1, 2, and 3-dimensional CNN networks are [3,[137][138][139][140]. ...
Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart’s electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i.e., 2012–22. Primarily, the method of ECG analysis by software systems was divided into classical signal processing (e.g. spectrograms or filters), machine learning (ML) and deep learning (DL), including recursive models, transformers and hybrid. Secondly, the data sources and benchmark datasets were depicted. Authors grouped resources by ECG acquisition methods into hospital-based portable machines and wearable devices. Authors also included new trends like advanced pre-processing, data augmentation, simulations and agent-based modeling.
The study found improvement in ECG examination perfection made each year through ML, DL, hybrid models, and transformers. Convolutional neural networks and hybrid models were more targeted and proved efficient. The transformer model extended the accuracy from 90% to 98%. The Physio-Net library helps acquire ECG signals, including the popular benchmark databases such as MIT-BIH, PTB, and challenging datasets. Similarly, wearable devices have been established as a appropriate option for monitoring patient health without the time and place limitations and are also helpful for AI model calibration with so far accuracy of 82%–83% on Samsung smartwatch. In the pre-processing signals, spectrogram generation through Fourier and wavelet transformations are erected leading approaches promoting on average accuracy of 90%–95%. Likewise, data enhancement using geometrical techniques is well-considered; however, extraction and concatenation-based methods need attention. As the what-if analysis in healthcare or cardiac issues can be performed using a complex simulation, the study reviews agent-based modeling and simulation approaches for cardiovascular risk event assessment.
... Using deep learning algorithms, such as CNNs, has shown great promise in accurately diagnosing and predicting various diseases, including heart disease. With the utilization of convolutional neural networks, we can effectively capture local important information in electronic health records and utilize it to make accurate predictions and diagnoses (Jafarian et al., 2020) [4]. The ability of CNNs to capture local important information in electronic health records and utilize it for accurate disease predictions and diagnoses makes them a powerful tool in the development of advanced diagnostic systems for MI in echocardiogram frames. ...
Myocardial infarction is a serious medical condition that requires prompt and accurate diagnosis for effective treatment. In this paper, we present a novel approach for detecting and classifying MI in echocardiogram frames using an enhancedCNNalgorithm and ECV-3D network. The proposed method aims to improve the accuracy and efficiency of MI diagnosis by leveraging advanced deep learning techniques. Through extensive experimentation, we demonstrate the effectiveness of our approach in achieving high accuracy and robustness in MI detection and classification. The results indicate the potential of our method to aid in the early and precise diagnosis of MI, thereby contributing to improved patient outcomes and clinical decision-making. After conducting thorough experimentation, our proposed approach has achieved an impressive accuracy of 97.05% in the detection and classification of myocardial infarction in echocardiogram frames. This accomplishment showcases the robustness and reliability of our method, indicating its potential to significantly impact the accurate diagnosis of MI and subsequently improve patient outcomes. Furthermore, the area under the curve attained by our model is 0.82%, reaffirming the efficacy of the enhanced CNN algorithm and ECV-3D network in accurately detecting and classifying MI.It is noteworthy that all the parameters utilized in our approach have demonstrated a high level of accuracy, emphasizing the effectiveness of our deep learning techniques in enhancing the diagnostic process for MI. Moreover, the proposed method is capable of efficiently processing large volumes of echocardiogram frames, making it suitable for real-time clinical applications.
... About 735,000 people have a heart attack in the United States alone each year, and 71.5% of those patients are first responders [4]. The prediction states that between 2015 and 2030, the incidence of coronary heart disease, the primary cause of MI, will increase by 18% [5]. The predicted cost of cardiovascular disease management by 2035 is expected to reach 1.1 trillion USD, up from 555 billion USD in 2015 [6] Early detection of MI is essential to prevent cardiac failure, arrhythmia, or unexpected death. ...
... The predicted cost of cardiovascular disease management by 2035 is expected to reach 1.1 trillion USD, up from 555 billion USD in 2015 [6] Early detection of MI is essential to prevent cardiac failure, arrhythmia, or unexpected death. A variety of evaluation modalities, including electrocardiograms (ECGs) [5], magnetic resonance imaging (MRI) [7] and echocardiography [8], can be used to identify MI. The most often used technique for supporting cardiac functions and assessing the health of the myocardial and left ventricle is magnetic resonance imaging (MRI) [7]. ...
... In multiclass classification, every class appears as a binary vector, and the target attribute is usually encoded using one-hot encoding. This research used the LET_IS column of the dataset as a categorical multiclass column and contains the following classes: Lethal outcome (cause) 0: unknown (alive) 1: cardiogenic shock 2: pulmonary edema VOLUME 4, 2016 5 This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and content may change prior to final publication. ...
One of the main causes of death from cardiovascular diseases is Myocardial Infarction (MI), which is brought on by coronary artery problems. Myocardial infarction is a pathological condition resulting from an anatomical issue with the Left Ventricle (LV). MI is a potentially fatal cardiac disease for which prompt medical attention can lower the fatality risk. This paper proposes a Deep Learning (DL) based approach to robustly detect binary and multiclass myocardial infarction (MI) in two environments, i.e., with and without data balancing. We employed a Myocardial infarction dataset that contains 1700 MI patients’ medical records. The data preprocessing step is performed, during which data balancing and normalization are carried out. In many real-world medical datasets, class imbalance is a serious problem since it often causes the proposed algorithms to predict the majority class. We apply a class imbalance handling technique to solve the imbalance issue and create a balanced and trustworthy prediction approach. To ensure the generalizability and performance comparison, we employ various deep learning algorithms such as Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Deep Neural Network (DNN), Long Short-Term Memory (LSTM) without data balancing first, and then after that, with data balancing to enhance model performance. Experiments reveal that the DNN model outperformed others by applying the class imbalance handling technique compared to the method without balancing data. The DNN model attained a maximum test accuracy of 99.39% and a test loss of 0.0252 for the binary class and achieved a maximum test accuracy of 99.74% and a test loss of 0.0115 for multiclass categorization.
... An important machine learning technique is the K-NN algorithm, which separates the feature spaces into distinct clusters according to the attributes related to the various classes. When categorising a test feature vector, this classifier takes into account the k metric distances among the features of the test sample and those of the closest class (Islam et al. 2020). The quantity of contemporaries and the type of distance metric matter a lot in K-NN architecture. ...
Myocardial infarction (MI), referred to as a heart attack, is a life-threatening condition that happens due to blood clots, typically, blood flow to a portion of the heart muscle is blocked. The cardiac muscle may become permanently damaged if there is insufficient oxygen and blood flow to the affected area. It's crucial to treat MI as soon as possible because even a small delay might have serious effects. The primary diagnostic tool to track and identify the signs of MI is the electrocardiogram (ECG). The complexity of MI signals combined with noise makes it difficult for clinicians to make a precise and prompt diagnosis. It might be laborious and time-consuming to manually analyse an enormous quantity of ECG data. Therefore, techniques for autonomously diagnosing from the ECG data are required. There have been numerous research on the topic of MI espial, but the majority of the algorithms are cognitively intensive when working with empirical data. The current study suggests a unique method for the efficient and reliable identification of MI. We employed circulant singular spectrum analysis (CSSA) for baseline wander removal, a 4-stage Savitzky-Golay (SG) filter to expunge powerline interference from the ECG signal and segmented in the preprocessing stage. Thus segmented ECG has been decomposed using CSSA, entropy based features are extracted. The best features are selected by using binary Harris hawk optimization (BHHO) and to machine learning (ML) classifiers like Naive Bayes, Decision tree, K-nearest neighbor (KNN), Support vector machine (SVM), and Ensemble subspace KNN. Our suggested method has been examined from both class as well as subject oriented perspectives. While the subject-oriented technique uses data from one patient for testing while using data from the other subjects for training, the class-wise strategy divides data as test data as well as training data regardless of subjects. We succeeded in achieving accuracy (Ac%) of 99.8, sensitivity (Se%) of 99, and 100 specificity (Sp%) under the class-oriented approach. Similarly, for the subject wise strategy we achieved a mean Ac%, Se%, and Sp% of 85.2, 83.1, and 84.5, respectively.
... The study [46] used 12-lead ECGs to establish two techniques for MI detection and localization. For feature extraction and classification, the first method used discrete wavelet transform (DWT) in conjunction with principal component analysis (PCA) and a shallow neural network (NN). ...
Despite significant improvement in prognosis, myocardial infarction (MI) remains a major cause of morbidity and mortality around the globe. MI is a life-threatening cardiovascular condition that requires prompt diagnosis and appropriate treatment. The primary objective of this research is to identify instances of anterior and inferior myocardial infarction by utilizing data obtained from Ultra-wideband radar technology in a hospital for patients of anterior and inferior MI. The collected data is preprocessed to extract spectral features. A novel feature engineering approach is designed to fuse temporal features and class prediction probability features derived from the spectral feature dataset. Several well-known machine learning models are implemented and fine-tuned to obtain optimal performance in the detection of anterior and inferior MI. The results demonstrate that integration of the fused feature set with machine learning models results in a notable improvement in both the accuracy and precision of MI detection. Notably, random forest (RF) and k-nearest neighbor showed superb performance with an accuracy of 98.8%. For demonstrating the capacity of models to generalize, K-fold cross-validation is carried out, wherein RF exhibits a mean accuracy of 99.1%. Furthermore, the examination of computational complexity indicates a low computational complexity, thereby indicating computational efficiency.
... The method achieved higher accuracy, sensitivity, and specificity than existing algorithms for MI detection using the PTB dataset. The study [32] developed two methods for MI identification and localization using 12-lead ECG, discrete wavelet transforms (DWT), and end-to-end deep machine learning algorithms. The proposed models were tested on the PTB dataset, achieving high accuracy rates. ...
Cardiovascular disease is the main cause of death worldwide. TheWorld Health Organization (WHO) reports that 17.9 million individuals die yearly due to complications from heart disease and other heart-related ailments. ECG monitoring and early detection are critical to decreasing myocardial infarction (MI) mortality. Thus, a non-invasive method to accurately classify different types of MI would be extremely beneficial. Our proposed study aims to detect and classify Anterior and Inferior MI infarction with advanced deep and machine learning techniques. A newly created UWB radar signal-based image dataset is used to conduct our study experiments. A novel Convolutional spatial Feature Engineering (CSFE) technique is proposed to extract the spatial features from the image dataset. The spatial features consist of both spatial and temporal information which allows machine learning models to leverage both the spatial and temporal relationships present in the data. Study results show that using the proposed CSFE technique, the advanced machine learning techniques achieved high-performance accuracy scores. The K-Neighbors Classifier (KNC) outperformed with a high-performance accuracy score of 98% for detecting Anterior and Inferior patients. The applied methods are fully hyperparametric tuned, and performance is validated using the k-fold cross-validation method.
... Previously, a variety of deep learning methods have been used for the classification of cardiovascular disease using electrocardiogram (ECG) signals [15]- [27]. Furthermore, several previous studies have employed recurrent neural networks (RNN) for classification of CVDs [28], [29]. The results demonstrated that RNNs outperform static conventional neural networks like a multilayer perceptron (MLP) as RNNs have a dynamic processing ability [12], [30]- [34]. ...
p>Heart failure (HF) is one of the most prevalent life-threatening cardiovascular diseases in which 6.5 million people are suffering in the USA and more than 23 million worldwide. Mechanical circulatory support of HF patients can be achieved by implanting a left ventricular assist device (LVAD) into HF patients as a bridge to transplant, recovery or destination therapy and can be controlled by measurement of normal and abnormal pulmonary arterial wedge pressure (PAWP). While there are no commercial long-term implantable pressure sensors to measure PAWP, real-time non-invasive estimation of abnormal and normal PAWP becomes vital. In this work, first an improved Harris Hawks optimizer algorithm called HHO+ is presented and tested on 24 unimodal and multimodal benchmark functions. Second, a novel fully Elman neural network (FENN) is proposed to improve the classification performance. Finally, four novel 18-layer deep learning methods of convolutional neural networks (CNNs) with multi-layer perceptron (CNN-MLP), CNN with Elman neural networks (CNN-ENN), CNN with fully Elman neural networks (CNN-FENN), and CNN with fully Elman neural networks optimized by HHO+ algorithm (CNN-FENN-HHO+) for classification of abnormal and normal PAWP using estimated HVAD pump flow were developed and compared. The estimated pump flow was derived by a non-invasive method embedded into the commercial HVAD controller. The proposed methods are evaluated on an imbalanced clinical dataset using 5-fold cross-validation. The proposed CNN-FENN-HHO+ method outperforms the proposed CNN-MLP, CNN-ENN and CNN-FENN methods and improved the classification performance metrics across 5-fold cross-validation with an average sensitivity of 79%, accuracy of 78% and specificity of 76%. The proposed methods can reduce the likelihood of hazardous events like pulmonary congestion and ventricular suction for HF patients and notify identified abnormal cases to the hospital, clinician and cardiologist for emergency action, which can diminish the mortality rate of patients with HF.</p
... Previously, a variety of deep learning methods have been used for the classification of cardiovascular disease using electrocardiogram (ECG) signals [15]- [27]. Furthermore, several previous studies have employed recurrent neural networks (RNN) for classification of CVDs [28], [29]. The results demonstrated that RNNs outperform static conventional neural networks like a multilayer perceptron (MLP) as RNNs have a dynamic processing ability [12], [30]- [34]. ...
p>Heart failure (HF) is one of the most prevalent life-threatening cardiovascular diseases in which 6.5 million people are suffering in the USA and more than 23 million worldwide. Mechanical circulatory support of HF patients can be achieved by implanting a left ventricular assist device (LVAD) into HF patients as a bridge to transplant, recovery or destination therapy and can be controlled by measurement of normal and abnormal pulmonary arterial wedge pressure (PAWP). While there are no commercial long-term implantable pressure sensors to measure PAWP, real-time non-invasive estimation of abnormal and normal PAWP becomes vital. In this work, first an improved Harris Hawks optimizer algorithm called HHO+ is presented and tested on 24 unimodal and multimodal benchmark functions. Second, a novel fully Elman neural network (FENN) is proposed to improve the classification performance. Finally, four novel 18-layer deep learning methods of convolutional neural networks (CNNs) with multi-layer perceptron (CNN-MLP), CNN with Elman neural networks (CNN-ENN), CNN with fully Elman neural networks (CNN-FENN), and CNN with fully Elman neural networks optimized by HHO+ algorithm (CNN-FENN-HHO+) for classification of abnormal and normal PAWP using estimated HVAD pump flow were developed and compared. The estimated pump flow was derived by a non-invasive method embedded into the commercial HVAD controller. The proposed methods are evaluated on an imbalanced clinical dataset using 5-fold cross-validation. The proposed CNN-FENN-HHO+ method outperforms the proposed CNN-MLP, CNN-ENN and CNN-FENN methods and improved the classification performance metrics across 5-fold cross-validation with an average sensitivity of 79%, accuracy of 78% and specificity of 76%. The proposed methods can reduce the likelihood of hazardous events like pulmonary congestion and ventricular suction for HF patients and notify identified abnormal cases to the hospital, clinician and cardiologist for emergency action, which can diminish the mortality rate of patients with HF.</p
