Machine Learning in the Evaluation of Myocardial Ischemia Through Nuclear Cardiology

Explainable deep-learning-based ischemia detection using hybrid O-15 H2O perfusion positron emission tomography and computed tomography imaging with clinical data

BACKGROUND

We developed an explainable deep-learning (DL)-based classifier to identify flow-limiting coronary artery disease (CAD) by O-15 H2O perfusion positron emission tomography computed tomography (PET/CT) and coronary CT angiography (CTA) imaging. The classifier uses polar map images with numerical data and visualizes data findings.

METHODS

A DLmodel was implemented and evaluated on 138 individuals, consisting of a combined image-and data-based classifier considering 35 clinical, CTA, and PET variables. Data from invasive coronary angiography were used as reference. Performance was evaluated with clinical classification using accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE), precision (PRE), net benefit, and Cohen's Kappa. Statistical testing was conducted using McNemar's test.

RESULTS

The DL model had a median ACC = 0.8478, AUC = 0.8481, F1S = 0.8293, SEN = 0.8500, SPE = 0.8846, and PRE = 0.8500. Improved detection of true-positive and false-negative cases, increased net benefit in thresholds up to 34%, and comparable Cohen's kappa was seen, reaching similar performance to clinical reading. Statistical testing revealed no significant differences between DL model and clinical reading.

CONCLUSIONS

The combined DL model is a feasible and an effective method in detection of CAD, allowing to highlight important data findings individually in interpretable manner.

Machine Learning Algorithms for Predicting Stunting among Under-Five Children in Papua New Guinea

Preventing stunting is particularly important for healthy development across the life course. In Papua New Guinea (PNG), the prevalence of stunting in children under five years old has consistently not improved. Therefore, the primary objective of this study was to employ multiple machine learning algorithms to identify the most effective model and key predictors for stunting prediction in children in PNG. The study used data from the 2016-2018 Papua New Guinea Demographic Health Survey, including from 3380 children with complete height-for-age data. The least absolute shrinkage and selection operator (LASSO) and random-forest-recursive feature elimination were used for feature selection. Logistic regression, a conditional decision tree, a support vector machine with a radial basis function kernel, and an extreme gradient boosting machine (XGBoost) were employed to construct the prediction model. The performance of the final model was evaluated using accuracy, precision, recall, F1 score, and area under the curve (AUC). The results of the study showed that LASSO-XGBoost has the best performance for predicting stunting in PNG (AUC: 0.765; 95% CI: 0.714-0.819) with accuracy, precision, recall, and F1 scores of 0.728, 0.715, 0.628, and 0.669, respectively. Combined with the SHAP value method, the optimal prediction model identified living in the Highlands Region, the age of the child, being in the richest family, and having a larger or smaller birth size as the top five important characteristics for predicting stunting. Based on the model, the findings support the necessity of preventing stunting early in life. Emphasizing the nutritional status of vulnerable maternal and child populations in PNG is recommended to promote maternal and child health and overall well-being.

Automated identification of myocardial perfusion defects in dynamic cardiac computed tomography using deep learning

PURPOSE

The purpose of this study was to develop and evaluate deep convolutional neural network (CNN) models for quantifying myocardial blood flow (MBF) as well as for identifying myocardial perfusion defects in dynamic cardiac computed tomography (CT) images.

METHODS

Adenosine stress cardiac CT perfusion data acquired from 156 patients having or being suspected with coronary artery disease were considered for model development and validation. U-net-based deep CNN models were developed to segment the aorta and myocardium and to localize anatomical landmarks. Color-coded MBF maps were obtained in short-axis slices from the apex to the base level and were used to train a deep CNN classifier. Three binary classification models were built for the detection of perfusion defect in the left anterior descending artery (LAD), the right coronary artery (RCA), and the left circumflex artery (LCX) territories.

RESULTS

Mean Dice scores were 0.94 (±0.07) and 0.86 (±0.06) for the aorta and myocardial deep learning-based segmentations, respectively. With the localization U-net, mean distance errors were 3.5 (±3.5) mm and 3.8 (±2.4) mm for the basal and apical center points, respectively. The classification models identified perfusion defects with the accuracy of mean area under the receiver operating curve (AUROC) values of 0.959 (±0.023) for LAD, 0.949 (±0.016) for RCA, and 0.957 (±0.021) for LCX.

CONCLUSION

The presented method has the potential to fully automate the quantification of MBF and subsequently identify the main coronary artery territories with myocardial perfusion defects in dynamic cardiac CT perfusion.

Classification of ischemia from myocardial polar maps in 15O-H2O cardiac perfusion imaging using a convolutional neural network

We implemented a two-dimensional convolutional neural network (CNN) for classification of polar maps extracted from Carimas (Turku PET Centre, Finland) software used for myocardial perfusion analysis. 138 polar maps from ¹⁵O–H₂O stress perfusion study in JPEG format from patients classified as ischemic or non-ischemic based on finding obstructive coronary artery disease (CAD) on invasive coronary artery angiography were used. The CNN was evaluated against the clinical interpretation. The classification accuracy was evaluated with: accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE) and precision (PRE). The CNN had a median ACC of 0.8261, AUC of 0.8058, F1S of 0.7647, SEN of 0.6500, SPE of 0.9615 and PRE of 0.9286. In comparison, clinical interpretation had ACC of 0.8696, AUC of 0.8558, F1S of 0.8333, SEN of 0.7500, SPE of 0.9615 and PRE of 0.9375. The CNN classified only 2 cases differently than the clinical interpretation. The clinical interpretation and CNN had similar accuracy in classifying false positives and true negatives. Classification of ischemia is feasible in ¹⁵O–H₂O stress perfusion imaging using JPEG polar maps alone with a custom CNN and may be useful for the detection of obstructive CAD.

Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning

BACKGROUND

Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD).

OBJECTIVE

Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period.

METHODS

The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method.

RESULTS

The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R² from 0.3 to 0.6.

CONCLUSIONS

By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.

Interpretable Detection and Location of Myocardial Infarction Based on Ventricular Fusion Rule Features

Myocardial infarction (MI) is one of the most common cardiovascular diseases threatening human life. In order to accurately distinguish myocardial infarction and have a good interpretability, the classification method that combines rule features and ventricular activity features is proposed in this paper. Specifically, according to the clinical diagnosis rule and the pathological changes of myocardial infarction on the electrocardiogram, the local information extracted from the Q wave, ST segment, and T wave is computed as the rule feature. All samples of the QT segment are extracted as ventricular activity features. Then, in order to reduce the computational complexity of the ventricular activity features, the effects of Discrete Wavelet Transform (DWT), Principal Component Analysis (PCA), and Locality Preserving Projections (LPP) on the extracted ventricular activity features are compared. Combining rule features and ventricular activity features, all the 12 leads features are fused as the ultimate feature vector. Finally, eXtreme Gradient Boosting (XGBoost) is used to identify myocardial infarction, and the overall accuracy rate of 99.86% is obtained on the Physikalisch-Technische Bundesanstalt (PTB) database. This method has a good medical diagnosis basis while improving the accuracy, which is very important for clinical decision-making.

Exploration of the efficacy of radiomics applied to left ventricular tomograms obtained from D-SPECT MPI for the auxiliary diagnosis of myocardial ischemia in CAD

To explore the feasibility and efficacy of radiomics with left ventricular tomograms obtained from D-SPECT myocardial perfusion imaging (MPI) for auxiliary diagnosis of myocardial ischemia in coronary artery disease (CAD). The images of 103 patients with CAD myocardial ischemia between September 2020 and April 2021 were retrospectively selected. After information desensitization processing, format conversion, annotation using the Labelme tool on an open-source platform, lesion classification, and establishment of a database, the images were cropped for analysis. The ResNet18 model was used to automate two steps (classification and segmentation) with five randomization, training and validation steps. The sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, positive predictive value, negative predictive value, Youden's index, agreement rate, and kappa value were calculated as evaluation indexes of the classification results for each training-validation step; then, receiver operating characteristics (ROC) curves were drawn, and the areas under the curve (AUCs) were calculated. The Dice coefficient, intersection over union, and Hausdorff distance were calculated as evaluation indexes of the segmentation results for each training-validation step; then, the predicted images were exported. Under the existing conditions, the radiomics model used in this study had an AUC above 0.95 in identifying the presence or absence of myocardial ischemia; in the prediction of the extent of myocardial ischemia, its evaluation index distribution is also close to that of the gold standard. Radiomics can be feasibly applied to left ventricular tomograms obtained from D-SPECT MPI for auxiliary diagnosis. With more in-depth research and the development of technology, adding this method to the existing auxiliary diagnosis will likely further improve the diagnostic accuracy and efficiency, and patients will therefore benefit.

Automatic Diagnosis of Coronary Artery Disease in SPECT Myocardial Perfusion Imaging Employing Deep Learning

Focusing on coronary artery disease (CAD) patients, this research paper addresses the problem of automatic diagnosis of ischemia or infarction using single-photon emission computed tomography (SPECT) (Siemens Symbia S Series) myocardial perfusion imaging (MPI) scans and investigates the capabilities of deep learning and convolutional neural networks. Considering the wide applicability of deep learning in medical image classification, a robust CNN model whose architecture was previously determined in nuclear image analysis is introduced to recognize myocardial perfusion images by extracting the insightful features of an image and use them to classify it correctly. In addition, a deep learning classification approach using transfer learning is implemented to classify cardiovascular images as normal or abnormal (ischemia or infarction) from SPECT MPI scans. The present work is differentiated from other studies in nuclear cardiology as it utilizes SPECT MPI images. To address the two-class classification problem of CAD diagnosis, achieving adequate accuracy, simple, fast and efficient CNN architectures were built based on a CNN exploration process. They were then employed to identify the category of CAD diagnosis, presenting its generalization capabilities. The results revealed that the applied methods are sufficiently accurate and able to differentiate the infarction or ischemia from healthy patients (overall classification accuracy = 93.47% ± 2.81%, AUC score = 0.936). To strengthen the findings of this study, the proposed deep learning approaches were compared with other popular state-of-the-art CNN architectures for the specific dataset. The prediction results show the efficacy of new deep learning architecture applied for CAD diagnosis using SPECT MPI scans over the existing ones in nuclear medicine.

Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT

In daily clinical practice, clinicians integrate available data to ascertain the diagnostic and prognostic probability of a disease or clinical outcome for their patients. For patients with suspected or known cardiovascular disease, several anatomical and functional imaging techniques are commonly performed to aid this endeavor, including coronary computed tomography angiography (CCTA) and nuclear cardiology imaging. Continuous improvement in positron emission tomography (PET), single-photon emission computed tomography (SPECT), and CT hardware and software has resulted in improved diagnostic performance and wide implementation of these imaging techniques in daily clinical practice. However, the human ability to interpret, quantify, and integrate these data sets is limited. The identification of novel markers and application of machine learning (ML) algorithms, including deep learning (DL) to cardiovascular imaging techniques will further improve diagnosis and prognostication for patients with cardiovascular diseases. The goal of this position paper of the European Association of Nuclear Medicine (EANM) and the European Association of Cardiovascular Imaging (EACVI) is to provide an overview of the general concepts behind modern machine learning-based artificial intelligence, highlights currently prefered methods, practices, and computational models, and proposes new strategies to support the clinical application of ML in the field of cardiovascular imaging using nuclear cardiology (hybrid) and CT techniques.

Improving patient identification for advanced cardiac imaging through machine learning-integration of clinical and coronary CT angiography data

BACKGROUND

Standard computed tomography angiography (CTA) outputs a myriad of interrelated variables in the evaluation of suspected coronary artery disease (CAD). But an important proportion of obstructive lesions does not cause significant myocardial ischemia. Nowadays, machine learning (ML) allows integration of numerous variables through complex interdependencies that optimize classification and prediction at the individual level. We evaluated ML performance in integrating CTA and clinical variables to identify patients that demonstrate myocardial ischemia through PET and those who ultimately underwent early revascularization.

METHODS AND RESULTS

830 patients with CTA and selective PET were analyzed. Nine clinical and 58 CTA variables were integrated through ensemble-boosting ML to identify patients with ischemia and those who underwent early revascularization. ML performance was compared against expert CTA interpretation, calcium score and clinical variables. While ML using all CTA variables achieved an AUC = 0.85, it was outperformed by expert CTA interpretation (AUC = 0.87, p < 0.01 for comparison), comparable to ML integration of CTA variables with clinical variables. However, the best performance was achieved by ML integration of expert CTA interpretation and clinical variables for both dependent variables (AUCs = 0.91 and 0.90, p < 0.001).

CONCLUSIONS

Machine learning integration of diagnostic CTA and clinical data may improve identification of patients with myocardial ischemia and those requiring early revascularization at the individual level. This could potentially aid in sparing the need for subsequent advanced imaging and better identifying patients in ultimate need for revascularization. While ML integrating all CTA variables did not outperform expert CTA interpretation, ML data integration from different sources consistently improves diagnostic performance.

Computed tomography for myocardial characterization in ischemic heart disease: a state-of-the-art review

This review provides an overview of the currently available computed tomography (CT) techniques for myocardial tissue characterization in ischemic heart disease, including CT perfusion and late iodine enhancement. CT myocardial perfusion imaging can be performed with static and dynamic protocols for the detection of ischemia and infarction using either single- or dual-energy CT modes. Late iodine enhancement may be used for the analysis of myocardial infarction. The accuracy of these CT techniques is highly dependent on the imaging protocol, including acquisition timing and contrast administration. Additionally, the options for qualitative and quantitative analysis and the accuracy of each technique are discussed.

Integrating the STOP-BANG Score and Clinical Data to Predict Cardiovascular Events After Infarction: A Machine Learning Study

BACKGROUND

OSA conveys worse clinical outcomes in patients with coronary artery disease. The STOP-BANG score is a simple tool that evaluates the risk of OSA and can be added to the large number of clinical variables and scores that are obtained during the management of patients with myocardial infarction (MI). Currently, machine learning (ML) is able to select and integrate numerous variables to optimize prediction tasks.

RESEARCH QUESTION

Can the integration of STOP-BANG score with clinical data and scores through ML better identify patients who experienced an in-hospital cardiovascular event after acute MI?

STUDY DESIGN AND METHODS

This is a prospective observational cohort study of 124 patients with acute MI of whom the STOP-BANG score classified 34 as low (27.4%), 30 as intermediate (24.2%), and 60 as high (48.4%) OSA-risk patients who were followed during hospitalization. ML implemented feature selection and integration across 47 variables (including STOP-BANG score, Killip class, GRACE score, and left ventricular ejection fraction) to identify those patients who experienced an in-hospital cardiovascular event (ie, death, ventricular arrhythmias, atrial fibrillation, recurrent angina, reinfarction, stroke, worsening heart failure, or cardiogenic shock) after definitive MI treatment. Receiver operating characteristic curves were used to compare ML performance against STOP-BANG score, Killip class, GRACE score, and left ventricular ejection fraction, independently.

RESULTS

There were an increasing proportion of cardiovascular events across the low, intermediate, and high OSA risk groups (P = .005). ML selected 7 accessible variables (ie, Killip class, leukocytes, GRACE score, c reactive protein, oxygen saturation, STOP-BANG score, and N-terminal prohormone of B-type natriuretic peptide); their integration outperformed all comparators (area under the curve, 0.83 [95% CI, 0.74-0.90]; P < .01).

INTERPRETATION

The integration of the STOP-BANG score into clinical evaluation (considering Killip class, GRACE score, and simple laboratory values) of subjects who were admitted for an acute MI because of ML can significantly optimize the identification of patients who will experience an in-hospital cardiovascular event.

Machine learning for predicting cardiac events: what does the future hold?

Introduction: With the increase in the number of patients with cardiovascular diseases, better risk-prediction models for cardiovascular events are needed. Statistical-based risk-prediction models for cardiovascular events (CVEs) are available, but they lack the ability to predict individual-level risk. Machine learning (ML) methods are especially equipped to handle complex data and provide accurate risk-prediction models at the individual level.Areas covered: In this review, the authors summarize the literature comparing the performance of machine learning methods to that of traditional, statistical-based models in predicting CVEs. They provide a brief summary of ML methods and then discuss risk-prediction models for CVEs such as major adverse cardiovascular events, heart failure and arrhythmias.Expert opinion: Current evidence supports the superiority of ML methods over statistical-based models in predicting CVEs. Statistical models are applicable at the population level and are subject to overfitting, while ML methods can provide an individualized risk level for CVEs. Further prospective research on ML-guided treatments to prevent CVEs is needed.