Artificial Intelligence-Assisted Left Ventricular Diastolic Function Assessment and Grading: Multiview Versus Single View.

BACKGROUND: Clinical assessment and grading of left ventricular diastolic function (LVDF) requires quantification of multiple echocardiographic parameters interpreted according to established guidelines, which depends on experienced clinicians and is time consuming. The aim of this study was to develop an artificial intelligence (AI)-assisted system to facilitate the clinical assessment of LVDF. METHODS: In total, 1,304 studies (33,404 images) were used to develop a view classification model to select six specific views required for LVDF assessment. A total of 2,238 studies (16,794 two-dimensional [2D] images and 2,198 Doppler images) to develop 2D and Doppler segmentation models, respectively, to quantify key metrics of diastolic function. We used 2,150 studies with definite LVDF labels determined by two experts to train single-view classification models by AI interpretation of strain metrics or video. The accuracy and efficiency of these models were tested in an external data set of 388 prospective studies. RESULTS: The view classification model identified views required for LVDF assessment with good sensitivity (>0.9), and view segmentation models successfully outlined key regions of these views with intersection over union > 0.8 in the internal validation data set. In the external test data set of 388 cases, AI quantification of 2D and Doppler images showed narrow limits of agreement compared with the two experts (e.g., left ventricular ejection fraction, -12.02% to 9.17%; E/e' ratio, -3.04 to 2.67). These metrics were used to detect LV diastolic dysfunction (DD) and grade DD with accuracy of 0.9 and 0.92, respectively. Concerning the single-view method, the overall accuracy of DD detection was 0.83 and 0.75 by strain-based and video-based models, and the accuracy of DD grading was 0.85 and 0.8, respectively. These models could achieve diagnosis and grading of LVDD in a few seconds, greatly saving time and labor. CONCLUSION: AI models successfully achieved LVDF assessment and grading that compared favorably with human experts reading according to guideline-based algorithms. Moreover, when Doppler variables were missing, AI models could provide assessment by interpreting 2D strain metrics or videos from a single view. These models have the potential to save labor and cost and to facilitate work flow of clinical LVDF assessment.

Echocardiography-based AI for detection and quantification of atrial septal defect.

Objectives: We developed and tested a deep learning (DL) framework applicable to color Doppler echocardiography for automatic detection and quantification of atrial septal defects (ASDs). Background: Color Doppler echocardiography is the most commonly used non-invasive imaging tool for detection of ASDs. While prior studies have used DL to detect the presence of ASDs from standard 2D echocardiographic views, no study has yet reported automatic interpretation of color Doppler videos for detection and quantification of ASD. Methods: A total of 821 examinations from two tertiary care hospitals were collected as the training and external testing dataset. We developed DL models to automatically process color Doppler echocardiograms, including view selection, ASD detection and identification of the endpoints of the atrial septum and of the defect to quantify the size of defect and the residual rim. Results: The view selection model achieved an average accuracy of 99% in identifying four standard views required for evaluating ASD. In the external testing dataset, the ASD detection model achieved an area under the curve (AUC) of 0.92 with 88% sensitivity and 89% specificity. The final model automatically measured the size of defect and residual rim, with the mean biases of 1.9 mm and 2.2 mm, respectively. Conclusion: We demonstrated the feasibility of using a deep learning model for automated detection and quantification of ASD from color Doppler echocardiography. This model has the potential to improve the accuracy and efficiency of using color Doppler in clinical practice for screening and quantification of ASDs, that are required for clinical decision making.

Echocardiography-based AI detection of regional wall motion abnormalities and quantification of cardiac function in myocardial infarction.

Objective: To compare the performance of a newly developed deep learning (DL) framework for automatic detection of regional wall motion abnormalities (RWMAs) for patients presenting with the suspicion of myocardial infarction from echocardiograms obtained with portable bedside equipment versus standard equipment. Background: Bedside echocardiography is increasingly used by emergency department setting for rapid triage of patients presenting with chest pain. However, compared to images obtained with standard equipment, lower image quality from bedside equipment can lead to improper diagnosis. To overcome these limitations, we developed an automatic workflow to process echocardiograms, including view selection, segmentation, detection of RWMAs and quantification of cardiac function that was trained and validated on image obtained from bedside and standard equipment. Methods: We collected 4,142 examinations from one hospital as training and internal testing dataset and 2,811 examinations from other hospital as the external test dataset. For data pre-processing, we adopted DL model to automatically recognize three apical views and segment the left ventricle. Detection of RWMAs was achieved with 3D convolutional neural networks (CNN). Finally, DL model automatically measured the size of cardiac chambers and left ventricular ejection fraction. Results: The view selection model identified the three apical views with an average accuracy of 96%. The segmentation model provided good agreement with manual segmentation, achieving an average Dice of 0.89. In the internal test dataset, the model detected RWMAs with AUC of 0.91 and 0.88 respectively for standard and bedside ultrasound. In the external test dataset, the AUC were 0.90 and 0.85. The automatic cardiac function measurements agreed with echocardiographic report values (e. g., mean bias is 4% for left ventricular ejection fraction). Conclusion: We present a fully automated echocardiography pipeline applicable to both standard and bedside ultrasound with various functions, including view selection, quality control, segmentation, detection of the region of wall motion abnormalities and quantification of cardiac function.

Cardiac Adaptation to Prolonged High Altitude Migration Assessed by Speckle Tracking Echocardiography.

Objective: Exposure to high altitudes represents physiological stress that leads to significant changes in cardiovascular properties. However, long-term cardiovascular adaptions to high altitude migration of lowlanders have not been described. Accordingly, we measured changes in cardiovascular properties following prolonged hypoxic exposure in acclimatized Han migrants and Tibetans. Methods: Echocardiographic features of recently adapted Han migrant (3-12 months, n = 64) and highly adapted Han migrant (5-10 years, n = 71) residence in Tibet (4,300 m) using speckle tracking echocardiography were compared to those of age-matched native Tibetans (n = 75) and Han lowlanders living at 1,400 m (n = 60). Results: Short-term acclimatized migrants showed increased estimated pulmonary artery systolic pressure (PASP) (32.6 ± 5.1 mmHg vs. 21.1 ± 4.2 mmHg, p < 0.05), enlarged right ventricles (RVs), and decreased fractional area change (FAC) with decreased RV longitudinal strain (-20 ± 2.8% vs. -25.5 ± 3.9%, p < 0.05). While left ventricular ejection fraction (LVEF) was preserved, LV diameter (41.7 ± 3.1 mm vs. 49.7 ± 4.8 mm, p < 0.05) and LV longitudinal strain (-18.8 ± 3.2% vs. -22.9 ± 3.3%, p < 0.05) decreased. Compared with recent migrants, longer-term migrants had recovered RV structure and functions with slightly improved RV and LV longitudinal strain, though still lower than lowlander controls; LV size remained small with increased mass index (68.3 ± 12.7 vs. 59.3 ± 9.6, p < 0.05). In contrast, native Tibetans had slightly increased PASP (26.1 ± 3.4 mmHg vs. 21.1 ± 4.2 mmHg, p < 0.05) with minimally altered cardiac deformation compared to lowlanders. Conclusion: Right ventricular systolic function is impaired in recent (<1 year) migrants to high altitudes but improved during the long-term dwelling. LV remodeling persists in long-term migrants (>5 years) but without impairment of LV systolic or diastolic function. In contrast, cardiac size, structure, and function of native Tibetans are more similar to those of lowland dwelling Hans.

Automated Analysis of Doppler Echocardiographic Videos as a Screening Tool for Valvular Heart Diseases.

OBJECTIVES: This study sought to develop a deep learning (DL) framework to automatically analyze echocardiographic videos for the presence of valvular heart diseases (VHDs). BACKGROUND: Although advances in DL have been applied to the interpretation of echocardiograms, such techniques have not been reported for interpretation of color Doppler videos for diagnosing VHDs. METHODS: The authors developed a 3-stage DL framework for automatic screening of echocardiographic videos for mitral stenosis (MS), mitral regurgitation (MR), aortic stenosis (AS), and aortic regurgitation (AR) that classifies echocardiographic views, detects the presence of VHDs, and, when present, quantifies key metrics related to VHD severities. The algorithm was trained (n = 1,335), validated (n = 311), and tested (n = 434) using retrospectively selected studies from 5 hospitals. A prospectively collected set of 1,374 consecutive echocardiograms served as a real-world test data set. RESULTS: Disease classification accuracy was high, with areas under the curve of 0.99 (95% CI: 0.97-0.99) for MS; 0.88 (95% CI: 0.86-0.90) for MR; 0.97 (95% CI: 0.95-0.99) for AS; and 0.90 (95% CI: 0.88-0.92) for AR in the prospective test data set. The limits of agreement (LOA) between the DL algorithm and physician estimates of metrics of valve lesion severities compared to the LOAs between 2 experienced physicians spanned from -0.60 to 0.77 cm2 vs -0.48 to 0.44 cm2 for MV area; from -0.27 to 0.25 vs -0.23 to 0.08 for MR jet area/left atrial area; from -0.86 to 0.52 m/s vs -0.48 to 0.54 m/s for peak aortic valve blood flow velocity (Vmax); from -10.6 to 9.5 mm Hg vs -10.2 to 4.9 mm Hg for average peak aortic valve gradient; and from -0.39 to 0.32 vs -0.31 to 0.32 for AR jet width/left ventricular outflow tract diameter. CONCLUSIONS: The proposed deep learning algorithm has the potential to automate and increase efficiency of the clinical workflow for screening echocardiographic images for the presence of VHDs and for quantifying metrics of disease severity.

Abnormal video homework automatic detection system.

Automatic abnormal detection of video homework is an effective method to improve the efficiency of homework marking. Based on the video homework review of "big data acquisition and processing project of actual combat" and other courses, this paper found some student upload their videos with poor images, face loss or abnormal video direction. However, it is time-consuming for teachers to pick out the abnormal video homework manually, which results in prompt feedback to students. This paper puts forward the AVHADS (Abnormal Video Homework Automatic Detection System). The system uses suffix and parameter identification, Open CV, and the audio classification model based on MFCC feature to realize the automatic detection and feedback of abnormal video homework. Experimental results show the AVHADS is feasible and effective.

Study of Gravity Effects on Titanium Laser Welding in the Vertical Position.

To obtain satisfactory welds in positional laser beam welding, it is necessary to know how process parameters will influence the quality of welds in different welding positions. In this study, the titanium alloy Ti6Al4V sheets were laser welded in two vertical welding positions (vertical up and vertical down), and the appearance, porosity, strength, and ductility of the laser joints were evaluated. Results show that undercuts of the vertical up welds were greater than that of vertical down welds, while the porosity contents were much higher in vertical down welds than that in vertical up welds. When welding with a higher heat input, the vertical up welding position resulted in poor weld profiles (undercuts and burn-through holes), whereas the vertical down welding position led to excessive porosity contents in welds. Both severe undercut and excessive porosity were detrimental to the tensile properties of the welds. Weld appearance was improved and porosity contents were reduced by using a lower heat input, achieving better weld quality. Therefore, it is suggested that process parameter settings with relatively high laser powers and welding speeds, which can result in lower heat inputs, are used when laser welding the Ti6Al4V titanium alloys vertically.