Echocardiography without electrocardiogram

Cardiac Valve Event Timing in Echocardiography Using Deep Learning and Triplane Recordings

Cardiac valve event timing plays a crucial role when conducting clinical measurements using echocardiography. However, established automated approaches are limited by the need of external electrocardiogram sensors, and manual measurements often rely on timing from different cardiac cycles. Recent methods have applied deep learning to cardiac timing, but they have mainly been restricted to only detecting two key time points, namely end-diastole (ED) and end-systole (ES). In this work, we propose a deep learning approach that leverages triplane recordings to enhance detection of valve events in echocardiography. Our method demonstrates improved performance detecting six different events, including valve events conventionally associated with ED and ES. Of all events, we achieve an average absolute frame difference (aFD) of maximum 1.4 frames (29 ms) for start of diastasis, down to 0.6 frames (12 ms) for mitral valve opening when performing a ten-fold cross-validation with test splits on triplane data from 240 patients. On an external independent test consisting of apical long-axis data from 180 other patients, the worst performing event detection had an aFD of 1.8 (30 ms). The proposed approach has the potential to significantly impact clinical practice by enabling more accurate, rapid and comprehensive event detection, leading to improved clinical measurements.

Clinical Influence of Handheld Ultrasound, Supported by Automatic Quantification and Telemedicine, in Suspected Heart Failure

Early and correct heart failure (HF) diagnosis is essential to improvement of patient care. We aimed to evaluate the clinical influence of handheld ultrasound device (HUD) examinations by general practitioners (GPs) in patients with suspected HF with or without the use of automatic measurement of left ventricular (LV) ejection fraction (autoEF), mitral annular plane systolic excursion (autoMAPSE) and telemedical support. Five GPs with limited ultrasound experience examined 166 patients with suspected HF (median interquartile range = 70 (63-78) y; mean ± SD EF = 53 ± 10%). They first performed a clinical examination. Second, they added an examination with HUD, automatic quantification tools and, finally, telemedical support by an external cardiologist. At all stages, the GPs considered whether the patients had HF. The final diagnosis was made by one of five cardiologists using medical history and clinical evaluation including a standard echocardiography. Compared with the cardiologists' decision, the GPs correctly classified 54% by clinical evaluation. The proportion increased to 71% after adding HUDs, and to 74 % after telemedical evaluation. Net reclassification improvement was highest for HUD with telemedicine. There was no significant benefit of the automatic tools (p ≥ 0.58). Addition of HUD and telemedicine improved the GPs' diagnostic precision in suspected HF. Automatic LV quantification added no benefit. Refined algorithms and more training may be needed before inexperienced users benefit from automatic quantification of cardiac function by HUDs.

Multibeat echocardiographic phase detection using deep neural networks

BACKGROUND

Accurate identification of end-diastolic and end-systolic frames in echocardiographic cine loops is important, yet challenging, for human experts. Manual frame selection is subject to uncertainty, affecting crucial clinical measurements, such as myocardial strain. Therefore, the ability to automatically detect frames of interest is highly desirable.

METHODS

We have developed deep neural networks, trained and tested on multi-centre patient data, for the accurate identification of end-diastolic and end-systolic frames in apical four-chamber 2D multibeat cine loop recordings of arbitrary length. Seven experienced cardiologist experts independently labelled the frames of interest, thereby providing infallible annotations, allowing for observer variability measurements.

RESULTS

When compared with the ground-truth, our model shows an average frame difference of -0.09 ± 1.10 and 0.11 ± 1.29 frames for end-diastolic and end-systolic frames, respectively. When applied to patient datasets from a different clinical site, to which the model was blind during its development, average frame differences of -1.34 ± 3.27 and -0.31 ± 3.37 frames were obtained for both frames of interest. All detection errors fall within the range of inter-observer variability: [-0.87, -5.51]±[2.29, 4.26] and [-0.97, -3.46]±[3.67, 4.68] for ED and ES events, respectively.

CONCLUSIONS

The proposed automated model can identify multiple end-systolic and end-diastolic frames in echocardiographic videos of arbitrary length with performance indistinguishable from that of human experts, but with significantly shorter processing time.

Feasibility and Reliability of Automatic Quantitative Analyses of Mitral Annular Plane Systolic Excursion by Handheld Ultrasound Devices: A Pilot Study

OBJECTIVES

Handheld ultrasound devices (HUDs) have previously been limited to grayscale imaging without options for left ventricle (LV) quantification. We aimed to study the feasibility and reliability of automatic measurements of mitral annular plane systolic excursion (MAPSE) by HUDs.

METHODS

An algorithm that automatically measured MAPSE from live grayscale recordings was implemented in a HUD. Twenty patients at a university hospital were examined by either a cardiologist or a sonographer. Standard echocardiography using a high-end scanner was performed. The apical 4-chamber view was recorded 4 times by both echocardiography and the HUD. MAPSE was measured by M-mode and color tissue Doppler (cTD) during echocardiography and automatically by the HUD.

RESULTS

The automatic method underestimated mean MAPSE ± SD versus M-mode (9.6 ± 2.2 versus 10.9 ± 2.6 mm; difference, 1.2 ± 1.4 mm, P < .005). The difference between the automatic and cTD measurements was not significant (0.8 ± 1.8 mm; P = .073). The intraclass correlation coefficients (ICCs) between automatic and M-mode measurements was 0.85, and 0.81 for cTD measurements. There was good agreement between the methods, and the intra- and inter-rater ICCs were excellent for all methods (≥0.86).

CONCLUSIONS

In this novel study evaluating automatic quantification of LV longitudinal function by HUD, we showed the high feasibility and reliability of the method. Compared to M-mode imaging, the automatic method underestimated MAPSE by 8% to 10%, but the difference with cTD imaging was nonsignificant. We conclude that this study's method for automatic quantitative assessment of LV function can be integrated in HUDs.

Estimation of End-Diastole in Cardiac Spectral Doppler Using Deep Learning

Electrocardiogram (ECG) is often used together with a spectral Doppler ultrasound to separate heart cycles by determining the end-diastole locations. However, the ECG signal is not always recorded. In such cases, the cardiac cycles can be estimated manually from the ultrasound data retrospectively. We present a deep learning-based method for automatic detection of the end-diastoles in spectral Doppler spectrograms. The method uses a combination of a convolutional neural network (CNN) for extracting features and a recurrent neural network (RNN) for modeling temporal relations. In echocardiography, there are three Doppler spectrogram modalities, continuous wave, pulsed wave, and tissue velocity Doppler. Both the training and test data sets include all three modalities. The model was tested on 643 spectrograms coming from different hospitals than in the training data set. For the purposes described in this work, a valid end-diastole detection is defined as a prediction being closer than 60 ms to the reference value. We will refer to these as true detections. Similarly, a prediction farther away is defined as nonvalid or false detections. The method automatically rejects spectrograms where the detection of an end-diastole has low confidence. When setting the algorithm to reject 1.9%, the method achieved 97.7% true detections with a mean error of 14 ms and had 2.5% false detections on the remaining spectrograms.

Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

Volume and ejection fraction (EF) measurements of the left ventricle (LV) in 2-D echocardiography are associated with a high uncertainty not only due to interobserver variability of the manual measurement, but also due to ultrasound acquisition errors such as apical foreshortening. In this work, a real-time and fully automated EF measurement and foreshortening detection method is proposed. The method uses several deep learning components, such as view classification, cardiac cycle timing, segmentation and landmark extraction, to measure the amount of foreshortening, LV volume, and EF. A data set of 500 patients from an outpatient clinic was used to train the deep neural networks, while a separate data set of 100 patients from another clinic was used for evaluation, where LV volume and EF were measured by an expert using clinical protocols and software. A quantitative analysis using 3-D ultrasound showed that EF is considerably affected by apical foreshortening, and that the proposed method can detect and quantify the amount of apical foreshortening. The bias and standard deviation of the automatic EF measurements were -3.6 ± 8.1%, while the mean absolute difference was measured at 7.2% which are all within the interobserver variability and comparable with related studies. The proposed real-time pipeline allows for a continuous acquisition and measurement workflow without user interaction, and has the potential to significantly reduce the time spent on the analysis and measurement error due to foreshortening, while providing quantitative volume measurements in the everyday echo lab.

Cardiac Phase Detection in Echocardiograms With Densely Gated Recurrent Neural Networks and Global Extrema Loss

Accurate detection of end-systolic (ES) and end-diastolic (ED) frames in an echocardiographic cine series can be difficult but necessary pre-processing step for the development of automatic systems to measure cardiac parameters. The detection task is challenging due to variations in cardiac anatomy and heart rate often associated with pathological conditions. We formulate this problem as a regression problem and propose several deep learning-based architectures that minimize a novel global extrema structured loss function to localize the ED and ES frames. The proposed architectures integrate convolution neural networks (CNNs)-based image feature extraction model and recurrent neural networks (RNNs) to model temporal dependencies between each frame in a sequence. We explore two CNN architectures: DenseNet and ResNet, and four RNN architectures: long short-term memory, bi-directional LSTM, gated recurrent unit (GRU), and Bi-GRU, and compare the performance of these models. The optimal deep learning model consists of a DenseNet and GRU trained with the proposed loss function. On average, we achieved 0.20 and 1.43 frame mismatch for the ED and ES frames, respectively, which are within reported inter-observer variability for the manual detection of these frames.

Echocardiography without electrocardiogram using nonlinear dimensionality reduction methods

PURPOSE

The aim of this study is to evaluate the efficiency of a new automatic image processing technique, based on nonlinear dimensionality reduction (NLDR) to separate a cardiac cycle and also detect end-diastole (ED) (cardiac cycle start) and end-systole (ES) frames on an echocardiography system without using ECG.

METHODS

Isometric feature mapping (Isomap) and locally linear embeddings (LLE) are the most popular NLDR algorithms. First, Isomap algorithm is applied on recorded echocardiography images. By this approach, the nonlinear embedded information in sequential images is represented in a two-dimensional manifold and each image is characterized by a symbol on the constructed manifold. Cyclicity analysis of the resultant manifold, which is derived from the cyclic nature of the heart motion, is used to perform cardiac cycle length estimation. Then, LLE algorithm is applied on extracted left ventricle (LV) echocardiography images of one cardiac cycle. Finally, the relationship between consecutive symbols of the resultant manifold by the LLE algorithm, which is based on LV volume changes, is used to estimate ED (cycle start) and ES frames. The proposed algorithms are quantitatively compared to those obtained by a highly experienced echocardiographer from ECG as a reference in 20 healthy volunteers and 12 subjects with pathology.

RESULTS

Mean difference in cardiac cycle length, ED, and ES frame estimation between our method and ECG detection by the experienced echocardiographer is approximately 7, 17, and 17 ms (0.4, 1, and 1 frame), respectively.

CONCLUSION

The proposed image-based method, based on NLDR, can be used as a useful tool for estimation of cardiac cycle length, ED and ES frames in echocardiography systems, with good agreement to ECG assessment by an experienced echocardiographer in routine clinical evaluation.

Automated aortic Doppler flow tracing for reproducible research and clinical measurements

In clinical practice, echocardiographers are often unkeen to make the significant time investment to make additional multiple measurements of Doppler velocity. Main hurdle to obtaining multiple measurements is the time required to manually trace a series of Doppler traces. To make it easier to analyze more beats, we present the description of an application system for automated aortic Doppler envelope quantification, compatible with a range of hardware platforms. It analyses long Doppler strips, spanning many heartbeats, and does not require electrocardiogram to separate individual beats. We tested its measurement of velocity-time-integral and peak-velocity against the reference standard defined as the average of three experts who each made three separate measurements. The automated measurements of velocity-time-integral showed strong correspondence (R(2) = 0.94) and good Bland-Altman agreement (SD = 1.39 cm) with the reference consensus expert values, and indeed performed as well as the individual experts ( R(2) = 0.90 to 0.96, SD = 1.05 to 1.53 cm). The same performance was observed for peak-velocities; ( R(2) = 0.98, SD = 3.07 cm/s) and ( R(2) = 0.93 to 0.98, SD = 2.96 to 5.18 cm/s). This automated technology allows > 10 times as many beats to be analyzed compared to the conventional manual approach. This would make clinical and research protocols more precise for the same operator effort.

Feasibility and reliability of point-of-care pocket-size echocardiography performed by medical residents

Aims

To study the feasibility and reliability of pocket-size hand-held echocardiography (PHHE) by medical residents with limited experience in ultrasound.

Methods and results

A total of 199 patients admitted to a non-university medical department were examined with PHHE. Six out of 14 medical residents were randomized to use a focused protocol and examine the heart, pericardium, pleural space, and abdominal large vessels. Diagnostic corrections were made and findings were confirmed by standard diagnostics. The median time consumption for the examination was 5.7 min. Each resident performed a median of 27 examinations. The left ventricle was assessed to satisfaction in 97% and the pericardium in all patients. The aortic and atrioventricular valves were assessed in at least 76% and the abdominal aorta in 50%, respectively. Global left-ventricular function, pleural, and pericardial effusion showed very strong correlation with reference method (Spearman's r ≥ 0.8). Quantification of aortic stenosis and regurgitation showed strong correlation with r = 0.7. Regurgitations in the atrioventricular valves showed moderate correlations, r = 0.5 and r = 0.6 for mitral and tricuspid regurgitation, respectively, similar to dilatation of the left atrium (r = 0.6) and detection of regional dysfunction (r = 0.6). Quantification of the abdominal aorta (aneurysmatic or not) showed strong correlation, r = 0.7, while the inferior vena cava diameter correlated moderately, r = 0.5.

Conclusion

By adding a PHHE examination to standard care, medical residents were able to obtain reliable information of important cardiovascular structures in patients admitted to a medical department. Thus, focused examinations with PHHE performed by residents after a training period have the potential to improve in-hospital diagnostic procedures.

Diagnostic influence of cardiovascular screening by pocket-size ultrasound in a cardiac unit

AIMS

We aimed to study the diagnostic influence of adding a routine cardiovascular ultrasound screening of the cardiac anatomy and function, the pericardium, the pleura and the abdominal great vessels by the new pocket-size ultrasound device (pUS) with grey scale and colour Doppler imaging.

METHODS AND RESULTS

In 119 randomly selected patients admitted to a cardiac unit at a non-university hospital, routinely adding a cardiovascular ultrasonography of only 4.4 min with a pocket-size device corrected the primary diagnosis in 16% of patients. In addition, 29% had the primary diagnosis verified and in 10% an additional important diagnosis was made. Higher age predicted any diagnostic influence of pUS screening with an increase of 61% (P=0.003) per 10 years of higher age. Overall, the pUS screening had a sensitivity and specificity with respect to detecting at least moderate pathology of 97 and 93%. Positive and negative predictive values were 93 and 87%, respectively. In the sub-group of subjects with a change in the primary diagnosis following pUS there was no false-negative or false-positive findings.

CONCLUSION

Screening by pUS assessed vascular and cardiac anatomy and function accurately and enabled correction of the diagnosis in 16% of patients admitted to a cardiac unit. In 55% of the participants, the cardiovascular ultrasound screening had important diagnostic influence. We suggest that it would be appropriate to implement strategies and systems for routinely adding an ultrasound cardiovascular examination to patients in cardiac units.

Feasibility and reliability of point-of-care pocket-sized echocardiography

AIMS

To study the reliability and feasibility of point-of-care pocket-sized echocardiography (POCKET) at the bedside in patients admitted to a medical department at a non-university hospital.

METHODS AND RESULTS

One hundred and eight patients were randomized to bedside POCKET examination shortly after admission and later high-end echocardiography (HIGH) in the echo-lab. The POCKET examinations were done by cardiologists on their ward rounds. Assessments of global and regional left ventricular (LV) function, right ventricular (RV) function, valvular function, left atrial (LA) size, the pericardium and pleura were done with respect to effusion and measurements of inferior vena cava (IVC) and abdominal aorta (AA) were performed. Correlations between POCKET and HIGH/appropriate radiological technique for LV function, AA size and presence of pericardial effusion were almost perfect, with r ≥ 0.92. Strong correlation (r ≥ 0.81) was shown for RV and valvular function, except for grading of aortic stenosis (r = 0.62). The correlations were substantial for IVC and LA dimensions. Median time used for bedside screening with POCKET was 4.2 min (range: 2.3-13.0). There was excellent feasibility for cardiac structures and pleura, which was assessed to satisfaction in ≥ 94% of patients. Lower feasibility (71-79%) was seen for the abdominal great vessels.

CONCLUSION

Point-of-care semi-quantitative evaluation of cardiac anatomy and function showed high feasibility and correlation with the reference method for most indices. Pocket-sized echocardiographic examinations of ∼4 min length, performed at the bedside by experts, offers reliable assessment of cardiac structures, the pleural space and the large abdominal vessels.

CLINICAL TRIAL REGISTRATION

http://www.clinicaltrials.gov; unique ID: NCT01081210.