Recurrence Plot-Based Approach for Cardiac Arrhythmia Classification Using Inception-ResNet-v2

High-Precision Intelligent Diagnosis of Pancreatic Cancer: Flowing Diffuseness from Single to Whole

Raman spectroscopy, as a label-free optical technique, provides a unique solution for tissue diagnosis. However, due to the limitation of point-by-point acquisition mode and multivariate statistical analysis methods, conventional methods pose a major bottleneck toward achieving highly time-efficient, accurate, and holistic diagnosis. Here, the authors establish line-scan Raman spectrochemical holistic analysis (LRSHA), an intelligent diagnostic method for rapid Raman data collection and holistic tissue diagnosis. The line-scan technique is first used for rapid spectral acquisition (∼15 s) in a tissue block area (0.75 × 0.5 mm2), which is 2 orders of magnitude faster than conventional methods. Then, the one-dimensional (1D) Raman spectra are converted into two-dimensional (2D) Raman encoding figures by the spectral recurrence plot transformation. The 2D deep learning models achieve 96.0% accuracy, 7% higher than that of 1D deep learning models. Moreover, the neighborhood enhancement method is applied to correct the initial deep learning results, like ripple flowing diffuseness from single to whole, which ultimately greatly improves the diagnostic accuracy to 99.7%. We also demonstrated that our method can identify tissue neoplasia at resection margins that appear nearly normal to the naked eye. Together, the LRSHA method shows valuable potential for rapid, efficient, and accurate tissue diagnosis.

Investigating the Use of Generative Adversarial Networks-Based Deep Learning for Reducing Motion Artifacts in Cardiac Magnetic Resonance

Objective

To evaluate the effectiveness of deep learning technology based on generative adversarial networks (GANs) in reducing motion artifacts in cardiac magnetic resonance (CMR) cine sequences.

Methods

The training and testing datasets consisted of 2000 and 200 pairs of clear and blurry images, respectively, acquired through simulated motion artifacts in CMR cine sequences. These datasets were used to establish and train a deep learning GAN model. To assess the efficacy of the deep learning network in mitigating motion artifacts, 100 images with simulated motion artifacts and 37 images with real-world motion artifacts encountered in clinical practice were selected. Image quality pre- and post-optimization was assessed using metrics including Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Leningrad Focus Measure, and a 5-point Likert scale.

Results

After GAN optimization, notable improvements were observed in the PSNR, SSIM, and focus measure metrics for the 100 images with simulated artifacts. These metrics increased from initial values of 23.85±2.85, 0.71±0.08, and 4.56±0.67, respectively, to 27.91±1.74, 0.83±0.05, and 7.74±0.39 post-optimization. Additionally, the subjective assessment scores significantly improved from 2.44±1.08 to 4.44±0.66 (P<0.001). For the 37 images with real-world artifacts, the Tenengrad Focus Measure showed a significant enhancement, rising from 6.06±0.91 to 10.13±0.48 after artifact removal. Subjective ratings also increased from 3.03±0.73 to 3.73±0.87 (P<0.001).

Conclusion

GAN-based deep learning technology effectively reduces motion artifacts present in CMR cine images, demonstrating significant potential for clinical application in optimizing CMR motion artifact management.

M-NET: Transforming Single Nucleotide Variations Into Patient Feature Images for the Prediction of Prostate Cancer Metastasis and Identification of Significant Pathways

High-performance prediction of prostate cancer metastasis based on single nucleotide variations remains a challenge. Therefore, we developed a novel biologically informed deep learning framework, named M-NET, for the prediction of prostate cancer metastasis. Within the framework, we transformed single nucleotide variations into patient feature images that are optimal for fitting convolutional neural networks. Moreover, we identified significant pathways associated with the metastatic status. The experimental results showed that M-NET significantly outperformed other comparison methods based on single nucleotide variations, achieving improvements in accuracy, precision, recall, F1-score, area under the receiver operating characteristics curve, and area under the precision-recall curve by 6.3%, 8.4%, 5.1%, 0.070, 0.041, and 0.026, respectively. Furthermore, M-NET identified some important pathways associated with the metastatic status, such as signaling by the hedgehog pathway. In summary, compared with other comparative methods, M-NET exhibited a better performance in the prediction of prostate cancer metastasis.

Enhanced CAD Detection Using Novel Multi-Modal Learning: Integration of ECG, PCG, and Coupling Signals

Early and highly precise detection is essential for delaying the progression of coronary artery disease (CAD). Previous methods primarily based on single-modal data inherently lack sufficient information that compromises detection precision. This paper proposes a novel multi-modal learning method aimed to enhance CAD detection by integrating ECG, PCG, and coupling signals. A novel coupling signal is initially generated by operating the deconvolution of ECG and PCG. Then, various entropy features are extracted from ECG, PCG, and its coupling signals, as well as recurrence deep features also encoded by integrating recurrence plots and a parallel-input 2-D CNN. After feature reduction and selection, final classification is performed by combining optimal multi-modal features and support vector machine. This method was validated on simultaneously recorded standard lead-II ECG and PCG signals from 199 subjects. The experimental results demonstrate that the proposed multi-modal method by integrating all signals achieved a notable enhancement in detection performance with best accuracy of 95.96%, notably outperforming results of single-modal and joint analysis with accuracies of 80.41%, 86.51%, 91.44%, and 90.42% using ECG, PCG, coupling signal, and joint ECG and PCG, respectively. This indicates that our multi-modal method provides more sufficient information for CAD detection, with the coupling information playing an important role in classification.

Coronary Artery Disease Detection Based on a Novel Multi-Modal Deep-Coding Method Using ECG and PCG Signals

Coronary artery disease (CAD) is an irreversible and fatal disease. It necessitates timely and precise diagnosis to slow CAD progression. Electrocardiogram (ECG) and phonocardiogram (PCG), conveying abundant disease-related information, are prevalent clinical techniques for early CAD diagnosis. Nevertheless, most previous methods have relied on single-modal data, restricting their diagnosis precision due to suffering from information shortages. To address this issue and capture adequate information, the development of a multi-modal method becomes imperative. In this study, a novel multi-modal learning method is proposed to integrate both ECG and PCG for CAD detection. Along with deconvolution operation, a novel ECG-PCG coupling signal is evaluated initially to enrich the diagnosis information. After constructing a modified recurrence plot, we build a parallel CNN network to encode multi-modal information, involving ECG, PCG and ECG-PCG coupling deep-coding features. To remove irrelevant information while preserving discriminative features, we add an autoencoder network to compress feature dimension. Final CAD classification is conducted by combining support vector machine and optimal multi-modal features. The experiment is validated on 199 simultaneously recorded ECG and PCG signals from non-CAD and CAD subjects, and achieves high performance with accuracy, sensitivity, specificity and f1-score of 98.49%, 98.57%,98.57% and 98.89%, respectively. The result demonstrates the superiority of the proposed multi-modal method in overcoming information shortages of single-modal signals and outperforming existing models in CAD detection. This study highlights the potential of multi-modal deep-coding information, and offers a wider insight to enhance CAD diagnosis.

Atrial Fibrillation Prediction Based on Recurrence Plot and ResNet

Atrial fibrillation (AF) is the most prevalent form of arrhythmia, with a rising incidence and prevalence worldwide, posing significant implications for public health. In this paper, we introduce an approach that combines the Recurrence Plot (RP) technique and the ResNet architecture to predict AF. Our method involves three main steps: using wavelet filtering to remove noise interference; generating RPs through phase space reconstruction; and employing a multi-level chained residual network for AF prediction. To validate our approach, we established a comprehensive database consisting of electrocardiogram (ECG) recordings from 1008 AF patients and 48,292 Non-AF patients, with a total of 2067 and 93,129 ECGs, respectively. The experimental results demonstrated high levels of prediction precision (90.5%), recall (89.1%), F1 score (89.8%), accuracy (93.4%), and AUC (96%) on our dataset. Moreover, when tested on a publicly available AF dataset (AFPDB), our method achieved even higher prediction precision (94.8%), recall (99.4%), F1 score (97.0%), accuracy (97.0%), and AUC (99.7%). These findings suggest that our proposed method can effectively extract subtle information from ECG signals, leading to highly accurate AF predictions.

A graph-based cardiac arrhythmia classification methodology using one-lead ECG recordings

In this study, we present a novel graph-based methodology for an accurate classification of cardiac arrhythmia diseases using a single-lead electrocardiogram (ECG). The proposed approach employs the visibility graph technique to generate graphs from time signals. Subsequently, informative features are extracted from each graph and then fed into classifiers to match the input ECG signal with the appropriate target arrhythmia class. The six target classes in this study are normal (N), left bundle branch block (LBBB), right bundle branch block (RBBB), premature ventricular contraction (PVC), atrial premature contraction (A), and fusion (F) beats. Three classification models were explored, including graph convolutional neural network (GCN), multi-layer perceptron (MLP), and random forest (RF). ECG recordings from the MIT-BIH arrhythmia database were utilized to train and evaluate these classifiers. The results indicate that the multi-layer perceptron model attains the highest performance, showcasing an average accuracy of 99.02%. Following closely, the random forest achieves a strong performance as well, with an accuracy of 98.94% while providing critical intuitions.

AF automatic classification based on different time-delay values of the recurrence plot

Recurrence plot (RP) has been widely used to transform 1D ECG waveforms into 2D images and explore the recurrence patterns of the electrical signals generated by the cardiac system. However, selecting the critical parameter time-delay τ for creating an RP has not been well-reported. In this work, we investigated the influence of different τ values on the RP-based AF prediction. And the results illustrated that the best classification performance could be achieved at τ=1 with full characters of the dynamic system.Clinical Relevance-This work established the AF classification system based on recurrence features and found the optimal parameters of the recurrence plot improving the ECG-based classification performance.

Ensembled Feature based Multi-Label ECG Arrhythmia Classification

Arrhythmia is one of the major contributors to sudden cardiac death. Compared to single-label arrhythmia classification, multi-label classification provides the advantage of simultaneous detection of different cardiac ailments. Existing multi-label approaches employ deep learning models, which have several limitations, e.g., data dependency, overfitting, complexity, and lack of interpretability. In this work, we propose a multi-label classification framework with ensembled hand-crafted features added with label powerset, which better preserves the correlation between classes. Experimentation with CPSC 2018 database shows that the proposed model provides accuracy and F1-score of 88.52% and 88.45% for single-label data and 88.11% and 86.32% for multi-label data, respectively. The proposed method improves individual class performance for some important diseases compared to the existing multi-label state-of-the-art methods.Clinical relevance- Early detection of life-threatening multi-label ECG patterns consisting of atrial fibrillation, atrioventricular block, and right bundle branch block with high accuracy can reduce the sudden cardiac death rate.

Atrial fibrillation classification based on the 2D representation of minimal subset ECG and a non-deep neural network

Atrial fibrillation (AF) is the most common cardiac arrhythmia, and its early detection is critical for preventing complications and optimizing treatment. In this study, a novel AF prediction method is proposed, which is based on investigating a subset of the 12-lead ECG data using a recurrent plot and ParNet-adv model. The minimal subset of ECG leads (II &V1) is determined via a forward stepwise selection procedure, and the selected 1D ECG data is transformed into 2D recurrence plot (RP) images as an input to train a shallow ParNet-adv Network for AF prediction. In this study, the proposed method achieved F1 score of 0.9763, Precision of 0.9654, Recall of 0.9875, Specificity of 0.9646, and Accuracy of 0.9760, which significantly outperformed solutions based on single leads and complete 12 leads. When studying several ECG datasets, including the CPSC and Georgia ECG databases of the PhysioNet/Computing in Cardiology Challenge 2020, the new method achieved F1 score of 0.9693 and 0.8660, respectively. The results suggested a good generalization of the proposed method. Compared with several state-of-art frameworks, the proposed model with a shallow network of only 12 depths and asymmetric convolutions achieved the highest average F1 score. Extensive experimental studies proved that the proposed method has a high potential for AF prediction in clinical and particularly wearable applications.

Cardiac Arrhythmia classification based on 3D recurrence plot analysis and deep learning

Artificial intelligence (AI) aided cardiac arrhythmia (CA) classification has been an emerging research topic. Existing AI-based classification methods commonly analyze electrocardiogram (ECG) signals in lower dimensions, using one-dimensional (1D) temporal signals or two-dimensional (2D) images, which, however, may have limited capability in characterizing lead-wise spatiotemporal correlations, which are critical to the classification accuracy. In addition, existing methods mostly assume that the ECG data are linear temporal signals. This assumption may not accurately represent the nonlinear, nonstationary nature of the cardiac electrophysiological process. In this work, we have developed a three-dimensional (3D) recurrence plot (RP)-based deep learning algorithm to explore the nonlinear recurrent features of ECG and Vectorcardiography (VCG) signals, aiming to improve the arrhythmia classification performance. The 3D ECG/VCG images are generated from standard 12 lead ECG and 3 lead VCG signals for neural network training, validation, and testing. The superiority and effectiveness of the proposed method are validated by various experiments. Based on the PTB-XL dataset, the proposed method achieved an average F1 score of 0.9254 for the 3D ECG-based case and 0.9350 for the 3D VCG-based case. In contrast, recently published 1D and 2D ECG-based CA classification methods yielded lower average F1 scores of 0.843 and 0.9015, respectively. Thus, the improved performance and visual interpretability make the proposed 3D RP-based method appealing for practical CA classification.

From 12 to 1 ECG lead: multiple cardiac condition detection mixing a hybrid machine learning approach with a one-vs-rest classification strategy

OBJECTIVE

Detecting different cardiac diseases using a single or reduced number of leads is still challenging. This work aims to provide and validate an automated method able to classify ECG recordings. Performance using complete 12-lead systems, reduced lead sets, and single-lead ECGs is evaluated and compared.

APPROACH

Seven different databases with 12-lead ECGs were provided during the PhysioNet/Computing in Cardiology Challenge 2021, where 88,253 annotated samples associated with none, one, or several cardiac conditions among 26 different classes were released for training, whereas 42,896 hidden samples were used for testing. After signal preprocessing, 81 features per ECG-lead were extracted, mainly based on heart rate variability, QRST patterns and spectral domain. Next, a One-vs-Rest classification approach made of independent binary classifiers for each cardiac condition was trained. This strategy allowed each ECG to be classified as belonging to none, one or several classes. For each class, a classification model among two binary Supervised Classifiers and one Hybrid Unsupervised-Supervised classification system was selected. Finally, we performed a 3-fold cross-validation to assess the system's performance.

MAIN RESULTS

Our classifiers received scores of 0.39, 0.38, 0.39, 0.38, and 0.37 for the 12, 6, 4, 3 and 2-lead versions of the hidden test set with the Challenge evaluation metric (CM). Also, we obtained a mean G-score of 0.80, 0.78, 0.79, 0.79, 0.77 and 0.74 for the 12, 6, 4, 3, 2 and 1-lead subsets with the public training set during our 3-fold cross-validation.

SIGNIFICANCE

We proposed and tested a machine learning approach focused on flexibility for identifying multiple cardiac conditions using one or more ECG leads. Our minimal-lead approach may be beneficial for novel portable or wearable ECG devices used as screening tools, as it can also detect multiple and concurrent cardiac conditions.

An Intelligent ECG-Based Tool for Diagnosing COVID-19 via Ensemble Deep Learning Techniques

Diagnosing COVID-19 accurately and rapidly is vital to control its quick spread, lessen lockdown restrictions, and decrease the workload on healthcare structures. The present tools to detect COVID-19 experience numerous shortcomings. Therefore, novel diagnostic tools are to be examined to enhance diagnostic accuracy and avoid the limitations of these tools. Earlier studies indicated multiple structures of cardiovascular alterations in COVID-19 cases which motivated the realization of using ECG data as a tool for diagnosing the novel coronavirus. This study introduced a novel automated diagnostic tool based on ECG data to diagnose COVID-19. The introduced tool utilizes ten deep learning (DL) models of various architectures. It obtains significant features from the last fully connected layer of each DL model and then combines them. Afterward, the tool presents a hybrid feature selection based on the chi-square test and sequential search to select significant features. Finally, it employs several machine learning classifiers to perform two classification levels. A binary level to differentiate between normal and COVID-19 cases, and a multiclass to discriminate COVID-19 cases from normal and other cardiac complications. The proposed tool reached an accuracy of 98.2% and 91.6% for binary and multiclass levels, respectively. This performance indicates that the ECG could be used as an alternative means of diagnosis of COVID-19.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

High-Precision Intelligent Cancer Diagnosis Method: 2D Raman Figures Combined with Deep Learning

Raman spectroscopy, as a label-free detection technology, has been widely used in tumor diagnosis. However, most tumor diagnosis procedures utilize multivariate statistical analysis methods for classification, which poses a major bottleneck toward achieving high accuracy. Here, we propose a concept called the two-dimensional (2D) Raman figure combined with convolutional neural network (CNN) to improve the accuracy. Two-dimensional Raman figures can be obtained from four transformation methods: spectral recurrence plot (SRP), spectral Gramian angular field (SGAF), spectral short-time Fourier transform (SSTFT), and spectral Markov transition field (SMTF). Two-dimensional CNN models all yield more than 95% accuracy, which is higher than the PCA-LDA method and the Raman-spectrum-CNN method, indicating that 2D Raman figure inputs combined with CNN may be one reason for gaining excellent performances. Among 2D-CNN models, the main difference is the conversion, where SRP is based on the structure of wavenumber series with the best performances (98.9% accuracy, 99.5% sensitivity, 98.3% specificity), followed by SGAF on the wavenumber series, SSTFT on wavenumber and intensity information, and SMTF on wavenumber position information. The inclusion of external information in the conversion may be another reason for improvement in the accuracy. The excellent capability shows huge potential for tumor diagnosis via 2D Raman figures and may be applied in other spectroscopy analytical fields.

ECG Recurrence Plot-Based Arrhythmia Classification Using Two-Dimensional Deep Residual CNN Features

In this paper, an effective electrocardiogram (ECG) recurrence plot (RP)-based arrhythmia classification algorithm that can be implemented in portable devices is presented. Public databases from PhysioNet were used to conduct this study including the MIT-BIH Atrial Fibrillation Database, the MIT-BIH Arrhythmia Database, the MIT-BIH Malignant Ventricular Ectopy Database, and the Creighton University Ventricular Tachyarrhythmia Database. ECG time series were segmented and converted using an RP, and two-dimensional images were used as inputs to the CNN classifiers. In this study, two-stage classification is proposed to improve the accuracy. The ResNet-18 architecture was applied to detect ventricular fibrillation (VF) and noise during the first stage, whereas normal, atrial fibrillation, premature atrial contraction, and premature ventricular contractions were detected using ResNet-50 in the second stage. The method was evaluated using 5-fold cross-validation which improved the results when compared to previous studies, achieving first and second stage average accuracies of 97.21% and 98.36%, sensitivities of 96.49% and 97.92%, positive predictive values of 95.54% and 98.20%, and F1-scores of 95.96% and 98.05%, respectively. Furthermore, a 5-fold improvement in the memory requirement was achieved when compared with a previous study, making this classifier feasible for use in resource-constricted environments such as portable devices. Even though the method is successful, first stage training requires combining four different arrhythmia types into one label (other), which generates more data for the other category than for VF and noise, thus creating a data imbalance that affects the first stage performance.