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.

Automated Segmentation and Quantification of the Right Ventricle in 2-D Echocardiography.

OBJECTIVE: The right ventricle receives less attention than its left counterpart in echocardiography research, practice and development of automated solutions. In the work described here, we sought to determine that the deep learning methods for automated segmentation of the left ventricle in 2-D echocardiograms are also valid for the right ventricle. Additionally, here we describe and explore a keypoint detection approach to segmentation that guards against erratic behavior often displayed by segmentation models. METHODS: We used a data set of echo images focused on the right ventricle from 250 participants to train and evaluate several deep learning models for segmentation and keypoint detection. We propose a compact architecture (U-Net KP) employing the latter approach. The architecture is designed to balance high speed with accuracy and robustness. RESULTS: All featured models achieved segmentation accuracy close to the inter-observer variability. When computing the metrics of right ventricular systolic function from contour predictions of U-Net KP, we obtained the bias and 95% limits of agreement of 0.8 ± 10.8% for the right ventricular fractional area change measurements, -0.04 ± 0.54 cm for the tricuspid annular plane systolic excursion measurements and 0.2 ± 6.6% for the right ventricular free wall strain measurements. These results were also comparable to the semi-automatically derived inter-observer discrepancies of 0.4 ± 11.8%, -0.37 ± 0.58 cm and -1.0 ± 7.7% for the aforementioned metrics, respectively. CONCLUSION: Given the appropriate data, automated segmentation and quantification of the right ventricle in 2-D echocardiography are feasible with existing methods. However, keypoint detection architectures may offer higher robustness and information density for the same computational cost.

Automatic measurements of left ventricular volumes and ejection fraction by artificial intelligence: clinical validation in real time and large databases.

AIMS: Echocardiography is a cornerstone in cardiac imaging, and left ventricular (LV) ejection fraction (EF) is a key parameter for patient management. Recent advances in artificial intelligence (AI) have enabled fully automatic measurements of LV volumes and EF both during scanning and in stored recordings. The aim of this study was to evaluate the impact of implementing AI measurements on acquisition and processing time and test-retest reproducibility compared with standard clinical workflow, as well as to study the agreement with reference in large internal and external databases. METHODS AND RESULTS: Fully automatic measurements of LV volumes and EF by a novel AI software were compared with manual measurements in the following clinical scenarios: (i) in real time use during scanning of 50 consecutive patients, (ii) in 40 subjects with repeated echocardiographic examinations and manual measurements by 4 readers, and (iii) in large internal and external research databases of 1881 and 849 subjects, respectively. Real-time AI measurements significantly reduced the total acquisition and processing time by 77% (median 5.3 min, P < 0.001) compared with standard clinical workflow. Test-retest reproducibility of AI measurements was superior in inter-observer scenarios and non-inferior in intra-observer scenarios. AI measurements showed good agreement with reference measurements both in real time and in large research databases. CONCLUSION: The software reduced the time taken to perform and volumetrically analyse routine echocardiograms without a decrease in accuracy compared with experts.

Echocardiographic Reference Ranges of Global Longitudinal Strain for All Cardiac Chambers Using Guideline-Directed Dedicated Views.

BACKGROUND: Myocardial deformation by echocardiographic strain imaging is a key measurement in cardiology, providing valuable diagnostic and prognostic information. Reference ranges for strain should be established from large healthy populations with minimal methodologic biases and variability. OBJECTIVES: The aim of this study was to establish echocardiographic reference ranges, including lower normal limits of global strains for all 4 cardiac chambers, by guideline-directed dedicated views from a large healthy population and to evaluate the influence of subject-specific characteristics on strain. METHODS: In total, 1,329 healthy participants from HUNT4Echo, the echocardiographic substudy of the 4th wave of the Trøndelag Health Study, were included. Echocardiographic recordings specific for each chamber were optimized according to current recommendations. Two experienced sonographers recorded all echocardiograms using GE HealthCare Vivid E95 scanners. Analyses were performed by experts using GE HealthCare EchoPAC. RESULTS: The reference ranges for left ventricular (LV) global longitudinal strain and right ventricular free-wall strain were -24% to -16% and -35% to -17%, respectively. Correspondingly, left atrial (LA) and right atrial (RA) reservoir strains were 17% to 49% and 17% to 59%. All strains showed lower absolute values with higher age, except for LA and RA contractile strains, which were higher. The feasibility for strain was overall good (LV 96%, right ventricular 83%, LA 94%, and RA 87%). All chamber-specific strains were associated with age, and LV strain was associated with sex. CONCLUSIONS: Reference ranges of strain for all cardiac chambers were established based on guideline-directed chamber-specific recordings. Age and sex were the most important factors influencing reference ranges and should be considered when using strain echocardiography.

Deep Learning for Improved Precision and Reproducibility of Left Ventricular Strain in Echocardiography: A Test-Retest Study.

AIMS: Assessment of left ventricular (LV) function by echocardiography is hampered by modest test-retest reproducibility. A novel artificial intelligence (AI) method based on deep learning provides fully automated measurements of LV global longitudinal strain (GLS) and may improve the clinical utility of echocardiography by reducing user-related variability. The aim of this study was to assess within-patient test-retest reproducibility of LV GLS measured by the novel AI method in repeated echocardiograms recorded by different echocardiographers and to compare the results to manual measurements. METHODS: Two test-retest data sets (n = 40 and n = 32) were obtained at separate centers. Repeated recordings were acquired in immediate succession by 2 different echocardiographers at each center. For each data set, 4 readers measured GLS in both recordings using a semiautomatic method to construct test-retest interreader and intrareader scenarios. Agreement, mean absolute difference, and minimal detectable change (MDC) were compared to analyses by AI. In a subset of 10 patients, beat-to-beat variability in 3 cardiac cycles was assessed by 2 readers and AI. RESULTS: Test-retest variability was lower with AI compared with interreader scenarios (data set I: MDC = 3.7 vs 5.5, mean absolute difference = 1.4 vs 2.1, respectively; data set II: MDC = 3.9 vs 5.2, mean absolute difference = 1.6 vs 1.9, respectively; all P < .05). There was bias in GLS measurements in 13 of 24 test-retest interreader scenarios (largest bias, 3.2 strain units). In contrast, there was no bias in measurements by AI. Beat-to-beat MDCs were 1,5, 2.1, and 2.3 for AI and the 2 readers, respectively. Processing time for analyses of GLS by the AI method was 7.9 ± 2.8 seconds. CONCLUSION: A fast AI method for automated measurements of LV GLS reduced test-retest variability and removed bias between readers in both test-retest data sets. By improving the precision and reproducibility, AI may increase the clinical utility of echocardiography.

Real-Time Echocardiography Guidance for Optimized Apical Standard Views.

Measurements of cardiac function such as left ventricular ejection fraction and myocardial strain are typically based on 2-D ultrasound imaging. The reliability of these measurements depends on the correct pose of the transducer such that the 2-D imaging plane properly aligns with the heart for standard measurement views and is thus dependent on the operator's skills. We propose a deep learning tool that suggests transducer movements to help users navigate toward the required standard views while scanning. The tool can simplify echocardiography for less experienced users and improve image standardization for more experienced users. Training data were generated by slicing 3-D ultrasound volumes, which permits simulation of the movements of a 2-D transducer. Neural networks were further trained to calculate the transducer position in a regression fashion. The method was validated and tested on 2-D images from several data sets representative of a prospective clinical setting. The method proposed the adequate transducer movement 75% of the time when averaging over all degrees of freedom and 95% of the time when considering transducer rotation solely. Real-time application examples illustrate the direct relation between the transducer movements, the ultrasound image and the provided feedback.

Can a Dinosaur Think? Implementation of Artificial Intelligence in Extracorporeal Shock Wave Lithotripsy.

BACKGROUND: Extracorporeal shock wave lithotripsy (ESWL) of kidney stones is losing ground to more expensive and invasive endoscopic treatments. OBJECTIVE: This proof-of-concept project was initiated to develop artificial intelligence (AI)-augmented ESWL and to investigate the potential for machine learning to improve the efficacy of ESWL. DESIGN SETTING AND PARTICIPANTS: Two-dimensional ultrasound videos were captured during ESWL treatments from an inline ultrasound device with a video grabber. An observer annotated 23 212 images from 11 patients as either in or out of focus. The median hit rate was calculated on a patient level via bootstrapping. A convolutional neural network with U-Net architecture was trained on 57 ultrasound images with delineated kidney stones from the same patients annotated by a second observer. We tested U-Net on the ultrasound images annotated by the first observer. Cross-validation with a training set of nine patients, a validation set of one patient, and a test set of one patient was performed. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Classical metrics describing classifier performance were calculated, together with an estimation of how the algorithm would affect shock wave hit rate. RESULTS AND LIMITATIONS: The median hit rate for standard ESWL was 55.2% (95% confidence interval [CI] 43.2-67.3%). The performance metrics for U-Net were accuracy 63.9%, sensitivity 56.0%, specificity 74.7%, positive predictive value 75.3%, negative predictive value 55.2%, Youden's J statistic 30.7%, no-information rate 58.0%, and Cohen's κ 0.2931. The algorithm reduced total mishits by 67.1%. The main limitation is that this is a proof-of-concept study involving only 11 patients. CONCLUSIONS: Our calculated ESWL hit rate of 55.2% (95% CI 43.2-67.3%) supports findings from earlier research. We have demonstrated that a machine learning algorithm trained on just 11 patients increases the hit rate to 75.3% and reduces mishits by 67.1%. When U-Net is trained on more and higher-quality annotations, even better results can be expected. PATIENT SUMMARY: Kidney stones can be treated by applying shockwaves to the outside of the body. Ultrasound scans of the kidney are used to guide the machine delivering the shockwaves, but the shockwaves can still miss the stone. We used artificial intelligence to improve the accuracy in hitting the stone being treated.

Artificial Intelligence for Automatic Measurement of Left Ventricular Strain in Echocardiography.

OBJECTIVES: This study sought to examine if fully automated measurements of global longitudinal strain (GLS) using a novel motion estimation technology based on deep learning and artificial intelligence (AI) are feasible and comparable with a conventional speckle-tracking application. BACKGROUND: GLS is an important parameter when evaluating left ventricular function. However, analyses of GLS are time consuming and demand expertise, and thus are underused in clinical practice. METHODS: In this study, 200 patients with a wide range of left ventricle (LV) function were included. Three standard apical cine-loops were analyzed using the AI pipeline. The AI method measured GLS and was compared with a commercially available semiautomatic speckle-tracking software (EchoPAC v202, GE Healthcare. RESULTS: The AI method succeeded to both correctly classify all 3 standard apical views and perform timing of cardiac events in 89% of patients. Furthermore, the method successfully performed automatic segmentation, motion estimates, and measurements of GLS in all examinations, across different cardiac pathologies and throughout the spectrum of LV function. GLS was -12.0 ± 4.1% for the AI method and -13.5 ± 5.3% for the reference method. Bias was -1.4 ± 0.3% (95% limits of agreement: 2.3 to -5.1), which is comparable with intervendor studies. The AI method eliminated measurement variability and a complete GLS analysis was processed within 15 s. CONCLUSIONS: Through the range of LV function this novel AI method succeeds, without any operator input, to automatically identify the 3 standard apical views, perform timing of cardiac events, trace the myocardium, perform motion estimation, and measure GLS. Fully automated measurements based on AI could facilitate the clinical implementation of GLS.

Myocardial Function Imaging in Echocardiography Using Deep Learning.

Deformation imaging in echocardiography has been shown to have better diagnostic and prognostic value than conventional anatomical measures such as ejection fraction. However, despite clinical availability and demonstrated efficacy, everyday clinical use remains limited at many hospitals. The reasons are complex, but practical robustness has been questioned, and a large inter-vendor variability has been demonstrated. In this work, we propose a novel deep learning based framework for motion estimation in echocardiography, and use this to fully automate myocardial function imaging. A motion estimator was developed based on a PWC-Net architecture, which achieved an average end point error of (0.06±0.04) mm per frame using simulated data from an open access database, on par or better compared to previously reported state of the art. We further demonstrate unique adaptability to image artifacts such as signal dropouts, made possible using trained models that incorporate relevant image augmentations. Further, a fully automatic pipeline consisting of cardiac view classification, event detection, myocardial segmentation and motion estimation was developed and used to estimate left ventricular longitudinal strain in vivo. The method showed promise by achieving a mean deviation of (-0.7±1.6)% compared to a semi-automatic commercial solution for N=30 patients with relevant disease, within the expected limits of agreement. We thus believe that learning-based motion estimation can facilitate extended use of strain imaging in clinical practice.

LU-Net: A Multistage Attention Network to Improve the Robustness of Segmentation of Left Ventricular Structures in 2-D Echocardiography.

Segmentation of cardiac structures is one of the fundamental steps to estimate volumetric indices of the heart. This step is still performed semiautomatically in clinical routine and is, thus, prone to interobserver and intraobserver variabilities. Recent studies have shown that deep learning has the potential to perform fully automatic segmentation. However, the current best solutions still suffer from a lack of robustness in terms of accuracy and number of outliers. The goal of this work is to introduce a novel network designed to improve the overall segmentation accuracy of left ventricular structures (endocardial and epicardial borders) while enhancing the estimation of the corresponding clinical indices and reducing the number of outliers. This network is based on a multistage framework where both the localization and segmentation steps are optimized jointly through an end-to-end scheme. Results obtained on a large open access data set show that our method outperforms the current best-performing deep learning solution with a lighter architecture and achieved an overall segmentation accuracy lower than the intraobserver variability for the epicardial border (i.e., on average a mean absolute error of 1.5 mm and a Hausdorff distance of 5.1mm) with 11% of outliers. Moreover, we demonstrate that our method can closely reproduce the expert analysis for the end-diastolic and end-systolic left ventricular volumes, with a mean correlation of 0.96 and a mean absolute error of 7.6 ml. Concerning the ejection fraction of the left ventricle, results are more contrasted with a mean correlation coefficient of 0.83 and an absolute mean error of 5.0%, producing scores that are slightly below the intraobserver margin. Based on this observation, areas for improvement are suggested.

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.

Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography.

Delineation of the cardiac structures from 2D echocardiographic images is a common clinical task to establish a diagnosis. Over the past decades, the automation of this task has been the subject of intense research. In this paper, we evaluate how far the state-of-the-art encoder-decoder deep convolutional neural network methods can go at assessing 2D echocardiographic images, i.e., segmenting cardiac structures and estimating clinical indices, on a dataset, especially, designed to answer this objective. We, therefore, introduce the cardiac acquisitions for multi-structure ultrasound segmentation dataset, the largest publicly-available and fully-annotated dataset for the purpose of echocardiographic assessment. The dataset contains two and four-chamber acquisitions from 500 patients with reference measurements from one cardiologist on the full dataset and from three cardiologists on a fold of 50 patients. Results show that encoder-decoder-based architectures outperform state-of-the-art non-deep learning methods and faithfully reproduce the expert analysis for the end-diastolic and end-systolic left ventricular volumes, with a mean correlation of 0.95 and an absolute mean error of 9.5 ml. Concerning the ejection fraction of the left ventricle, results are more contrasted with a mean correlation coefficient of 0.80 and an absolute mean error of 5.6%. Although these results are below the inter-observer scores, they remain slightly worse than the intra-observer's ones. Based on this observation, areas for improvement are defined, which open the door for accurate and fully-automatic analysis of 2D echocardiographic images.

Real-Time Standard View Classification in Transthoracic Echocardiography Using Convolutional Neural Networks.

Transthoracic echocardiography examinations are usually performed according to a protocol comprising different probe postures providing standard views of the heart. These are used as a basis when assessing cardiac function, and it is essential that the morphophysiological representations are correct. Clinical analysis is often initialized with the current view, and automatic classification can thus be useful in improving today's workflow. In this article, convolutional neural networks (CNNs) are used to create classification models predicting up to seven different cardiac views. Data sets of 2-D ultrasound acquired from studies totaling more than 500 patients and 7000 videos were included. State-of-the-art accuracies of 98.3% ± 0.6% and 98.9% ± 0.6% on single frames and sequences, respectively, and real-time performance with 4.4 ± 0.3 ms per frame were achieved. Further, it was found that CNNs have the potential for use in automatic multiplanar reformatting and orientation guidance. Using 3-D data to train models applicable for 2-D classification, we achieved a median deviation of 4° ± 3° from the optimal orientations.

Evaluating the effectiveness and efficacy of unguided internet-based self-help intervention for the prevention of depression: a randomized controlled trial.

The Internet has the potential to increase the capacity and accessibility of mental health services. This study aimed to investigate whether an unguided Internet-based self-help intervention delivered without human support or guidance can reduce symptoms of depression in young people at risk of depression. The study also aimed to explore the usage of such sites in a real-life setting, to estimate the effects of the intervention for those who received a meaningful intervention dose and to evaluate user satisfaction. Young adults were recruited by means of a screening survey sent to all students at the University of Tromsø. Of those responding to the survey, 163 students (mean age 28.2 years) with elevated psychological distress were recruited to the trial and randomized to an Internet intervention condition or the waiting list control group. The Internet condition comprised a depression information website and a self-help Web application delivering automated cognitive behavioural therapy. The participants in the waiting list condition were free to access formal or informal help as usual. Two-thirds of the users who completed the trial initially reported an unmet need for help. The findings demonstrated that an unguided intervention was effective in reducing symptoms of depression and negative thoughts and in increasing depression literacy in young adults. Significant improvements were found at 2-month follow up. Internet-based interventions can be effective without tracking and thus constitute a minimal cost intervention for reaching a large number of people. User satisfaction among participants was high.