Accurate segmentation of fetal heart in echocardiography images is essential for detecting the structural abnormalities such as congenital heart defects (CHDs). Due to the wide variations attributed to different factors, such as maternal obesity, abdominal scars, amniotic fluid volume, and great vessel connections, this process is still a challenging problem. CHDs detection with expertise in general are substandard; the accuracy of measurements remains highly dependent on humans’ training, skills, and experience. To make such a process automatic, this study proposes deep learning-based computer-aided fetal heart echocardiography examinations with an instance segmentation approach, which inherently segments the four standard heart views and detects the defect simultaneously. We conducted several experiments with 1149 fetal heart images for predicting 24 objects, including four shapes of fetal heart standard views, 17 objects of heart-chambers in each view, and three cases of congenital heart defect. The result showed that the proposed model performed satisfactory performance for standard views segmentation, with a 79.97% intersection over union and 89.70% Dice coefficient similarity. It also performed well in the CHDs detection, with mean average precision around 98.30% for intra-patient variation and 82.42% for inter-patient variation. We believe that automatic segmentation and detection techniques could make an important contribution toward improving congenital heart disease diagnosis rates.

Early prenatal screening with an ultrasound (US) can significantly lower newborn mortality caused by congenital heart diseases (CHDs). However, the need for expertise in fetal cardiologists and the high volume of screening cases limit the practically achievable detection rates. Hence, automated prenatal screening to support clinicians is desirable. This paper presents and analyses potential deep learning (DL) techniques to diagnose CHDs in fetal USs. Four convolutional neural network architectures were compared to select the best classifier with satisfactory results. Hence, dense convolutional network (DenseNet) 201 architecture was selected for the classification of seven CHDs, such as ventricular septal defect, atrial septal defect, atrioventricular septal defect, Ebstein’s anomaly, tetralogy of Fallot, transposition of great arteries, hypoplastic left heart syndrome, and a normal control. The sensitivity, specificity, and accuracy of the DenseNet201 model were 100%, 100%, and 100%, respectively, for the intra-patient scenario and 99%, 97%, and 98%, respectively, for the inter-patient scenario. We used the intra-patient DL prediction model to validate our proposed model against the prediction results of three expert fetal cardiologists. The proposed model produces a satisfactory result, which means that our model can support expert fetal cardiologists to interpret the decision to improve CHD diagnostics. This work represents a step toward the goal of assisting front-line sonographers with CHD diagnoses at the population level.

Physicians manually interpret an electrocardiogram (ECG) signal morphology in routine clinical practice. This activity is a monotonous and abstract task that relies on the experience of understanding ECG waveform meaning, including P-wave, QRS-complex, and T-wave. Such a manual process depends on signal quality and the number of leads. ECG signal classification based on deep learning (DL) has produced an automatic interpretation; however, the proposed method is used for specific abnormality conditions. When the ECG signal morphology change to other abnormalities, it cannot proceed automatically. To generalize the automatic interpretation, we aim to delineate ECG waveform. However, the output of delineation process only ECG waveform duration classes for P-wave, QRS-complex, and T-wave. It should be combined with a medical knowledge rule to produce the abnormality interpretation. The proposed model is applied for atrial fibrillation (AF) identification. This study meets the AF criteria with RR irregularities and the absence of P-waves in essential oscillations for even more accurate identification. The QT database by Physionet is utilized for developing the delineation model, and it validates with The Lobachevsky University Database. The results show that our delineation model works properly, with 98.91% sensitivity, 99.01% precision, 99.79% specificity, 99.79% accuracy, and a 98.96% F1 score. We use about 4058 normal sinus rhythm records and 1804 AF records from the experiment to identify AF conditions that are taken from three datasets. The comprehensive testing has produced higher negative predictive value and positive predictive value. This means that the proposed model can identify AF conditions from ECG signal delineation. Our approach can considerably contribute to AF diagnosis with these results.

Fetal heart monitoring during pregnancy plays a critical role in diagnosing congenital heart disease (CHD). A noninvasive fetal electrocardiogram (fECG) provides additional clinical information for fetal heart monitoring. To date, the analysis of noninvasive fECG is challenging due to the cancellation of maternal QRS-complexes, despite significant advances in electrocardiography. Fetal QRS-complex is highly considered to measure fetal heart rate to detect some fetal abnormalities such as arrhythmia. In this study, we proposed a deep learning (DL) framework that stacked a convolutional layer and bidirectional long short-term memory for fetal QRS-complexes classification. The fECG signals are first preprocessed using discrete wavelet transform (DWT) to remove the noise or inferences. The following step beats and QRS-complex segmentation. The last step is fetal QRS-complex classification based on DL. In the experiment of Physionet/Computing in Cardiology Challenge 2013, this study achieved 100% accuracy, sensitivity, specificity, precision, and F1-score. A stacked DL model demonstrates an effective tool for fetal QRS-complex classification and contributes to clinical applications for long-term maternal and fetal monitoring.

Background: Signal delineation of a standard 12-lead electrocardiogram (ECG) is a decisive step for retrieving complete information and extracting signal characteristics for each lead in cardiology clinical practice. However, it is arduous to manually assess the leads, as a variety of signal morphological variations in each lead have potential defects in recording, noise, or irregular heart rhythm/beat. Method: A computer-aided deep-learning algorithm is considered a state-of-the-art delineation model to classify ECG waveform and boundary in terms of the P-wave, QRS-complex, and T-wave and indicated the satisfactory result. This study implemented convolution layers as a part of convolutional neural networks for automated feature extraction and bidirectional long short-term memory as a classifier. For beat segmentation, we have experimented beat-based and patient-based approach. Results: The empirical results using both beat segmentation approaches, with a total of 14,588 beats were showed that our proposed model performed excellently well. All performance metrics above 95% and 93%, for beat-based and patient-based segmentation, respectively. Conclusions: This is a significant step towards the clinical pertinency of automated 12-lead ECG delineation using deep learning.

Echocardiographic interpretation during the prenatal or postnatal period is important for diagnosing cardiac septal abnormalities. However, manual interpretation can be time consuming and subject to human error. Automatic segmentation of echocardiogram can support cardiologists in making an initial interpretation. However, such a process does not always provide straightforward information to make a complete interpretation. The segmentation process only identifies the region of cardiac septal abnormality, whereas complete interpretation should determine based on the position of defect. In this study, we proposed a stacked residual-dense network model to segment the entire region of cardiac and classifying their defect positions to generate automatic echocardiographic interpretation. We proposed the generalization model with incorporated two modalities: prenatal and postnatal echocardiography. To further evaluate the effectiveness of our model, its performance was verified by five cardiologists. We develop a pipeline process using 1345 echocardiograms for training data and 181 echocardiograms for unseen data from prospective patients acquired during standard clinical practice at Muhammad Hoesin General Hospital in Indonesia. As a result, the proposed model produced of 58.17% intersection over union (IoU), 75.75% dice similarity coefficient (DSC), and 76.36% mean average precision (mAP) for the validation data. Using unseen data, we achieved 42.39% IoU, 55.72% DSC, and 51.04% mAP. Further, the classification of defect positions using unseen data had approximately 92.27% accuracy, 94.33% specificity, and 92.05% sensitivity. Finally, our proposed model is validated with human expert with varying Kappa value. On average, these results hold promise of increasing suitability in clinical practice as a supporting diagnostic tool for establishing the diagnosis.