RF-CNN-F: random forest with convolutional neural network features for coronary artery disease diagnosis based on cardiac magnetic resonance.

Coronary artery disease (CAD) is a prevalent disease with high morbidity and mortality rates. Invasive coronary angiography is the reference standard for diagnosing CAD but is costly and associated with risks. Noninvasive imaging like cardiac magnetic resonance (CMR) facilitates CAD assessment and can serve as a gatekeeper to downstream invasive testing. Machine learning methods are increasingly applied for automated interpretation of imaging and other clinical results for medical diagnosis. In this study, we proposed a novel CAD detection method based on CMR images by utilizing the feature extraction ability of deep neural networks and combining the features with the aid of a random forest for the very first time. It is necessary to convert image data to numeric features so that they can be used in the nodes of the decision trees. To this end, the predictions of multiple stand-alone convolutional neural networks (CNNs) were considered as input features for the decision trees. The capability of CNNs in representing image data renders our method a generic classification approach applicable to any image dataset. We named our method RF-CNN-F, which stands for Random Forest with CNN Features. We conducted experiments on a large CMR dataset that we have collected and made publicly accessible. Our method achieved excellent accuracy (99.18%) using Adam optimizer compared to a stand-alone CNN trained using fivefold cross validation (93.92%) tested on the same dataset.

RLMD-PA: A Reinforcement Learning-Based Myocarditis Diagnosis Combined with a Population-Based Algorithm for Pretraining Weights.

Myocarditis is heart muscle inflammation that is becoming more prevalent these days, especially with the prevalence of COVID-19. Noninvasive imaging cardiac magnetic resonance (CMR) can be used to diagnose myocarditis, but the interpretation is time-consuming and requires expert physicians. Computer-aided diagnostic systems can facilitate the automatic screening of CMR images for triage. This paper presents an automatic model for myocarditis classification based on a deep reinforcement learning approach called as reinforcement learning-based myocarditis diagnosis combined with population-based algorithm (RLMD-PA) that we evaluated using the Z-Alizadeh Sani myocarditis dataset of CMR images prospectively acquired at Omid Hospital, Tehran. This model addresses the imbalanced classification problem inherent to the CMR dataset and formulates the classification problem as a sequential decision-making process. The policy of architecture is based on convolutional neural network (CNN). To implement this model, we first apply the artificial bee colony (ABC) algorithm to obtain initial values for RLMD-PA weights. Next, the agent receives a sample at each step and classifies it. For each classification act, the agent gets a reward from the environment in which the reward of the minority class is greater than the reward of the majority class. Eventually, the agent finds an optimal policy under the guidance of a particular reward function and a helpful learning environment. Experimental results based on standard performance metrics show that RLMD-PA has achieved high accuracy for myocarditis classification, indicating that the proposed model is suitable for myocarditis diagnosis.

CNN-KCL: Automatic myocarditis diagnosis using convolutional neural network combined with k-means clustering.

Myocarditis is the form of an inflammation of the middle layer of the heart wall which is caused by a viral infection and can affect the heart muscle and its electrical system. It has remained one of the most challenging diagnoses in cardiology. Myocardial is the prime cause of unexpected death in approximately 20% of adults less than 40 years of age. Cardiac MRI (CMR) has been considered a noninvasive and golden standard diagnostic tool for suspected myocarditis and plays an indispensable role in diagnosing various cardiac diseases. However, the performance of CMR depends heavily on the clinical presentation and features such as chest pain, arrhythmia, and heart failure. Besides, other imaging factors like artifacts, technical errors, pulse sequence, acquisition parameters, contrast agent dose, and more importantly qualitatively visual interpretation can affect the result of the diagnosis. This paper introduces a new deep learning-based model called Convolutional Neural Network-Clustering (CNN-KCL) to diagnose Myocarditis. In this study, we used 47 subjects with a total number of 98,898 images to diagnose myocarditis disease. Our results demonstrate that the proposed method achieves an accuracy of 97.41% based on 10 fold-cross validation technique with 4 clusters for diagnosis of Myocarditis. To the best of our knowledge, this research is the first to use deep learning algorithms for the diagnosis of myocarditis.

FCM-DNN: diagnosing coronary artery disease by deep accuracy fuzzy C-means clustering model.

Cardiovascular disease is one of the most challenging diseases in middle-aged and older people, which causes high mortality. Coronary artery disease (CAD) is known as a common cardiovascular disease. A standard clinical tool for diagnosing CAD is angiography. The main challenges are dangerous side effects and high angiography costs. Today, the development of artificial intelligence-based methods is a valuable achievement for diagnosing disease. Hence, in this paper, artificial intelligence methods such as neural network (NN), deep neural network (DNN), and fuzzy C-means clustering combined with deep neural network (FCM-DNN) are developed for diagnosing CAD on a cardiac magnetic resonance imaging (CMRI) dataset. The original dataset is used in two different approaches. First, the labeled dataset is applied to the NN and DNN to create the NN and DNN models. Second, the labels are removed, and the unlabeled dataset is clustered via the FCM method, and then, the clustered dataset is fed to the DNN to create the FCM-DNN model. By utilizing the second clustering and modeling, the training process is improved, and consequently, the accuracy is increased. As a result, the proposed FCM-DNN model achieves the best performance with a 99.91% accuracy specifying 10 clusters, i.e., 5 clusters for healthy subjects and 5 clusters for sick subjects, through the 10-fold cross-validation technique compared to the NN and DNN models reaching the accuracies of 92.18% and 99.63%, respectively. To the best of our knowledge, no study has been conducted for CAD diagnosis on the CMRI dataset using artificial intelligence methods. The results confirm that the proposed FCM-DNN model can be helpful for scientific and research centers.

Objective evaluation of deep uncertainty predictions for COVID-19 detection.

Deep neural networks (DNNs) have been widely applied for detecting COVID-19 in medical images. Existing studies mainly apply transfer learning and other data representation strategies to generate accurate point estimates. The generalization power of these networks is always questionable due to being developed using small datasets and failing to report their predictive confidence. Quantifying uncertainties associated with DNN predictions is a prerequisite for their trusted deployment in medical settings. Here we apply and evaluate three uncertainty quantification techniques for COVID-19 detection using chest X-Ray (CXR) images. The novel concept of uncertainty confusion matrix is proposed and new performance metrics for the objective evaluation of uncertainty estimates are introduced. Through comprehensive experiments, it is shown that networks pertained on CXR images outperform networks pretrained on natural image datasets such as ImageNet. Qualitatively and quantitatively evaluations also reveal that the predictive uncertainty estimates are statistically higher for erroneous predictions than correct predictions. Accordingly, uncertainty quantification methods are capable of flagging risky predictions with high uncertainty estimates. We also observe that ensemble methods more reliably capture uncertainties during the inference. DNN-based solutions for COVID-19 detection have been mainly proposed without any principled mechanism for risk mitigation. Previous studies have mainly focused on on generating single-valued predictions using pretrained DNNs. In this paper, we comprehensively apply and comparatively evaluate three uncertainty quantification techniques for COVID-19 detection using chest X-Ray images. The novel concept of uncertainty confusion matrix is proposed and new performance metrics for the objective evaluation of uncertainty estimates are introduced for the first time. Using these new uncertainty performance metrics, we quantitatively demonstrate when we could trust DNN predictions for COVID-19 detection from chest X-rays. It is important to note the proposed novel uncertainty evaluation metrics are generic and could be applied for evaluation of probabilistic forecasts in all classification problems.

Combining a convolutional neural network with autoencoders to predict the survival chance of COVID-19 patients.

COVID-19 has caused many deaths worldwide. The automation of the diagnosis of this virus is highly desired. Convolutional neural networks (CNNs) have shown outstanding classification performance on image datasets. To date, it appears that COVID computer-aided diagnosis systems based on CNNs and clinical information have not yet been analysed or explored. We propose a novel method, named the CNN-AE, to predict the survival chance of COVID-19 patients using a CNN trained with clinical information. Notably, the required resources to prepare CT images are expensive and limited compared to those required to collect clinical data, such as blood pressure, liver disease, etc. We evaluated our method using a publicly available clinical dataset that we collected. The dataset properties were carefully analysed to extract important features and compute the correlations of features. A data augmentation procedure based on autoencoders (AEs) was proposed to balance the dataset. The experimental results revealed that the average accuracy of the CNN-AE (96.05%) was higher than that of the CNN (92.49%). To demonstrate the generality of our augmentation method, we trained some existing mortality risk prediction methods on our dataset (with and without data augmentation) and compared their performances. We also evaluated our method using another dataset for further generality verification. To show that clinical data can be used for COVID-19 survival chance prediction, the CNN-AE was compared with multiple pre-trained deep models that were tuned based on CT images.

Fusion of convolution neural network, support vector machine and Sobel filter for accurate detection of COVID-19 patients using X-ray images.

The coronavirus (COVID-19) is currently the most common contagious disease which is prevalent all over the world. The main challenge of this disease is the primary diagnosis to prevent secondary infections and its spread from one person to another. Therefore, it is essential to use an automatic diagnosis system along with clinical procedures for the rapid diagnosis of COVID-19 to prevent its spread. Artificial intelligence techniques using computed tomography (CT) images of the lungs and chest radiography have the potential to obtain high diagnostic performance for Covid-19 diagnosis. In this study, a fusion of convolutional neural network (CNN), support vector machine (SVM), and Sobel filter is proposed to detect COVID-19 using X-ray images. A new X-ray image dataset was collected and subjected to high pass filter using a Sobel filter to obtain the edges of the images. Then these images are fed to CNN deep learning model followed by SVM classifier with ten-fold cross validation strategy. This method is designed so that it can learn with not many data. Our results show that the proposed CNN-SVM with Sobel filter (CNN-SVM + Sobel) achieved the highest classification accuracy, sensitivity and specificity of 99.02%, 100% and 95.23%, respectively in automated detection of COVID-19. It showed that using Sobel filter can improve the performance of CNN. Unlike most of the other researches, this method does not use a pre-trained network. We have also validated our developed model using six public databases and obtained the highest performance. Hence, our developed model is ready for clinical application.

Arrhythmogenic right ventricular cardiomyopathy in patients with biallelic JUP-associated skin fragility.

Arrhythmogenic right ventricular cardiomyopathy (ARVC), with skin manifestations, has been associated with mutations in JUP encoding plakoglobin. Genotype-phenotype correlations regarding the penetrance of cardiac involvement, and age of onset have not been well established. We examined a cohort of 362 families with skin fragility to screen for genetic mutations with next-generation sequencing-based methods. In two unrelated families, a previously unreported biallelic mutation, JUP: c.201delC; p.Ser68Alafs*92, was disclosed. The consequences of this mutation were determined by expression profiling both at tissue and ultrastructural levels, and the patients were evaluated by cardiac and cutaneous work-up. Whole-transcriptome sequencing by RNA-Seq revealed JUP as the most down-regulated gene among 21 skin fragility-associated genes. Immunofluorescence showed the lack of plakoglobin in the epidermis. Two probands, 2.5 and 22-year-old, with the same homozygous mutation, allowed us to study the cross-sectional progression of cardiac involvements in relation to age. The older patient had anterior T wave inversions, prolonged terminal activation duration (TAD), and RV enlargement by echocardiogram, and together with JUP mutation met definite ARVC diagnosis. The younger patient had no evidence of cardiac disease, but met possible ARVC diagnosis with one major criterion (the JUP mutation). In conclusion, we identified the same biallelic homozygous JUP mutation in two unrelated families with skin fragility, but cardiac findings highlighted age-dependent penetrance of ARVC. Thus, young, phenotypically normal patients with biallelic JUP mutations should be monitored for development of ARVC.

Value of pathologic Q wave in surface electrocardiography in the prediction of myocardial nonviability: A cardiac magnetic resonance imaging-based study.

In surface electrocardiography (ECG), Q wave is often considered as a sign of irreversibly scarred myocardium. Cardiac magnetic resonance (CMR) imaging is an accurate mean for the detection of myocardial viability. Herein, we study the predictive value of Q wave in nonviable (scarred) myocardium by CMR study. Retrospective analysis of the ECG and CMR data of 35 coronary artery disease patients was performed. The delayed enhancement CMR protocol was used for the detection of viability. The presence of a pathologic Q wave in surface ECG was negatively related to myocardial viability with a kappa measurement of agreement of -0.544 and P < 0.0001. Pathologic Q wave in surface ECG can be used as a simple tool for myocardial viability prediction.

Temporal Super Resolution Enhancement of Echocardiographic Images Based on Sparse Representation.

A challenging issue for echocardiographic image interpretation is the accurate analysis of small transient motions of myocardium and valves during real-time visualization. A higher frame rate video may reduce this difficulty, and temporal super resolution (TSR) is useful for illustrating the fast-moving structures. In this paper, we introduce a novel framework that optimizes TSR enhancement of echocardiographic images by utilizing temporal information and sparse representation. The goal of this method is to increase the frame rate of echocardiographic videos, and therefore enable more accurate analyses of moving structures. For the proposed method, we first derived temporal information by extracting intensity variation time curves (IVTCs) assessed for each pixel. We then designed both low-resolution and high-resolution overcomplete dictionaries based on prior knowledge of the temporal signals and a set of prespecified known functions. The IVTCs can then be described as linear combinations of a few prototype atoms in the low-resolution dictionary. We used the Bayesian compressive sensing (BCS) sparse recovery algorithm to find the sparse coefficients of the signals. We extracted the sparse coefficients and the corresponding active atoms in the low-resolution dictionary to construct new sparse coefficients corresponding to the high-resolution dictionary. Using the estimated atoms and the high-resolution dictionary, a new IVTC with more samples was constructed. Finally, by placing the new IVTC signals in the original IVTC positions, we were able to reconstruct the original echocardiography video with more frames. The proposed method does not require training of low-resolution and high-resolution dictionaries, nor does it require motion estimation; it does not blur fast-moving objects, and does not have blocking artifacts.

Congenital partial absence of the pericardium presenting with a rare concurrent abnormality of vascular ring diagnosed by cardiac magnetic resonance imaging.

Congenital absence of the pericardium is a rare abnormality that can be diagnosed by cardiac imaging procedures. A 49-year-old male needed medical attention due to the appearance of palpitation with a systolic murmur, and a notable aortic arch deviation was seen in the chest X-ray. In the echocardiogram, a poor echo window was detected. A cardiac magnetic resonance imaging (MRI) showed a rare concomitant anomaly of partial absence of the pericardium including a rare defect of the right-sided aortic arch. Using cardiac MRI, the pericardium can be easily visualized, and thus, its absence more easily detected, aiding appropriate clinical decision-making.

Effect of exercise on blood flow through the aortic valve: a combined clinical and numerical study.

The aim of this study was to measure the cardiac output and stroke volume for a healthy subject by coupling an echocardiogram Doppler (echo-Doppler) method with a fluid-structure interaction (FSI) simulation at rest and during exercise. Blood flow through aortic valve was measured by Doppler flow echocardiography. Aortic valve geometry was calculated by echocardiographic imaging. An FSI simulation was performed, using an arbitrary Lagrangian-Eulerian mesh. Boundary conditions were defined by pressure loads on ventricular and aortic sides. Pressure loads applied brachial pressures with (stage 1) and without (stage 2) differences between brachial, central and left ventricular pressures. FSI results for cardiac output were 15.4% lower than Doppler results for stage 1 (r = 0.999). This difference increased to 22.3% for stage 2. FSI results for stroke volume were undervalued by 15.3% when compared to Doppler results at stage 1 and 26.2% at stage 2 (r = 0.94). The predicted mean backflow of blood was 4.6%. Our results show that numerical methods can be combined with clinical measurements to provide good estimates of patient-specific cardiac output and stroke volume at different heart rates.

Doppler-derived strain and strain rate imaging assessment of right ventricular systolic function in adults late after tetralogy of Fallot repair: an observational study.

OBJECTIVE: Tetralogy of Fallot (TOF) is the most common form of cyanotic congenital heart disease. Today, we are faced with an increasing number of patients with residual pulmonary regurgitation (PR) late after TOF repair. The right ventricular (RV) volumes and function are among the most important factors influencing clinical decision-making. Cardiac magnetic resonance (CMR) is the gold standard method for the quantitative assessment of the RV function; it is, however, expensive for routine clinical follow-up and sometimes is contraindicated. We sought to evaluate the RV systolic function via CMR and compare it with Doppler-derived strain(S) and strain rate (SR) imaging in patients with repaired TOF. METHODS: In an observational cross-sectional study, 70 patients (22 women, mean age=22±4.9 years) late after TOF repair with severe PR were evaluated. Peak systolic strain and SR in the basal, mid, and apical segments of RV free wall (RVFW) were measured and compared with the RV function measured in the short-axis cine MR. Associations between RVEF and S/SR, investigated by ordinal logistic regression models. RESULTS: Significant association was observed between RV function and mean S of all the three segments of the RVFW segments [OR (CI95%): 1.17 (1.05-1.31)]. Association between RV function and mean SR of all the three segments of the RVFW segments was borderline significant [OR (CI95%): 1.7 (0.97-2.93)]. CONCLUSION: There was a significant correlation between the Doppler-derived mean strain of RVFW and the RV function measured by CMR in adults late after TOF repair. These quantitative methods improved the assessment of the RV function and served as an additional method to follow up patients with contraindications to CMR.

A data mining approach for diagnosis of coronary artery disease.

Cardiovascular diseases are very common and are one of the main reasons of death. Being among the major types of these diseases, correct and in-time diagnosis of coronary artery disease (CAD) is very important. Angiography is the most accurate CAD diagnosis method; however, it has many side effects and is costly. Existing studies have used several features in collecting data from patients, while applying different data mining algorithms to achieve methods with high accuracy and less side effects and costs. In this paper, a dataset called Z-Alizadeh Sani with 303 patients and 54 features, is introduced which utilizes several effective features. Also, a feature creation method is proposed to enrich the dataset. Then Information Gain and confidence were used to determine the effectiveness of features on CAD. Typical Chest Pain, Region RWMA2, and age were the most effective ones besides the created features by means of Information Gain. Moreover Q Wave and ST Elevation had the highest confidence. Using data mining methods and the feature creation algorithm, 94.08% accuracy is achieved, which is higher than the known approaches in the literature.

Modified optical flow technique for cardiac motions analysis in echocardiography images.

The quantitative analysis of cardiac motions in echocardiography images is a noteworthy issue in processing of these images. Cardiac motions can be estimated by optical flow (OF) computation in different regions of image which is based on the assumption that the intensity of a moving pattern remains constant in consecutive frames. However, in echocardiographic sequences, this assumption may be violated because of unique specifications of ultrasound. There are some methodsapplying the brightness variation effect in OF. Almost all of them have presented a mathematical brightness variation model globally in the images. Nevertheless, there is not a brightness variation model for echocardiographic images in these methods. Therefore, we are looking for a method to apply brightness variations locally in different regions of the image. In this study, we proposed a method to modify ausual OF technique by considering intensity variation. To evaluate this method, we implement two other OF-based methods, one usual OF method and a modified OF method applying brightness variation as a multiplier and an offset (generalized dynamic imaging model [GDIM]) and compare them with ours. These algorithms and ours were implemented on real 2D echocardiograms. Our method resulted in more accurate estimations than two others. At last, we compared our method with expert'spoint of view and observed that three distance metrics between them was appropriately smaller than other methods. The Haussdorff distance between the estimated curve defined by the proposed method and the expert defined curve is 4.81 pixels less than this distance for Lucas-Kanade and 2.28 pixels less than GDIM.

Diagnosis of coronary arteries stenosis using data mining.

Cardiovascular diseases are one of the most common diseases that cause a large number of deaths each year. Coronary Artery Disease (CAD) is the most common type of these diseases worldwide and is the main reason of heart attacks. Thus early diagnosis of CAD is very essential and is an important field of medical studies. Many methods are used to diagnose CAD so far. These methods reduce cost and deaths. But a few studies examined stenosis of each vessel separately. Determination of stenosed coronary artery when significant ECG abnormality exists is not a difficult task. Moreover, ECG abnormality is not common among CAD patients. The aim of this study is to find a way for specifying the lesioned vessel when there is not enough ECG changes and only based on risk factors, physical examination and Para clinic data. Therefore, a new data set was used which has no missing value and includes new and effective features like Function Class, Dyspnoea, Q Wave, ST Elevation, ST Depression and Tinversion. These data was collected from 303 random visitor of Tehran's Shaheed Rajaei Cardiovascular, Medical and Research Centre, in 2011 fall and 2012 winter. They processed with C4.5, Naïve Bayes, and k-nearest neighbour (KNN) algorithms and their accuracy were measured by tenfold cross validation. In the best method the accuracy of diagnosis of stenosis of each vessel reached to 74.20 ± 5.51% for Left Anterior Descending (LAD), 63.76 ± 9.73% for Left Circumflex and 68.33 ± 6.90% for Right Coronary Artery. The effective features of stenosis of each vessel were found too.

A New Method for Pseudo-increasing Frame Rates of Echocardiography Images Using Manifold Learning.

Increasing frame rate is a challenging issue for better interpretation of medical images and diagnosis based on tracking the small transient motions of myocardium and valves in real time visualization. In this paper, manifold learning algorithm is applied to extract the nonlinear embedded information about echocardiography images from the consecutive images in two dimensional manifold spaces. In this method, we presume that the dimensionality of echocardiography images obtained from a patient is artificially high and the images can be described as functions of only a few underlying parameters such as periodic motion due to heartbeat. By this approach, each image is projected as a point on the reconstructed manifold; hence, the relationship between images in the new domain can be obtained according to periodicity of the heart cycle. To have a better tracking of the echocardiography, images during the fast motions of heart we have rearranged the similar frames of consecutive heart cycles in a sequence. This provides a full view slow motion of heart movement through increasing the frame rate to three times the traditional ultrasound systems.

Automatic detection of end-diastole and end-systole from echocardiography images using manifold learning.

The automatic detection of end-diastole and end-systole frames of echocardiography images is the first step for calculation of the ejection fraction, stroke volume and some other features related to heart motion abnormalities. In this paper, the manifold learning algorithm is applied on 2D echocardiography images to find out the relationship between the frames of one cycle of heart motion. By this approach the nonlinear embedded information in sequential images is represented in a two-dimensional manifold by the LLE algorithm and each image is depicted by a point on reconstructed manifold. There are three dense regions on the manifold which correspond to the three phases of cardiac cycle ('isovolumetric contraction', 'isovolumetric relaxation', 'reduced filling'), wherein there is no prominent change in ventricular volume. By the fact that the end-systolic and end-diastolic frames are in isovolumic phases of the cardiac cycle, the dense regions can be used to find these frames. By calculating the distance between consecutive points in the manifold, the isovolumic frames are mapped on the three minimums of the distance diagrams which were used to select the corresponding images. The minimum correlation between these images leads to detection of end-systole and end-diastole frames. The results on six healthy volunteers have been validated by an experienced echo cardiologist and depict the usefulness of the presented method.