Jun 2026· Journal of the American Society of Echocardiography· 0 citations
Medicine
TL;DR
A comprehensive AI system that provides accurate, immediate, and interpretable feedback on echocardiographic quality is successfully developed and clinically deployed, demonstrating strong potential to standardize image acquisition, enhance diagnostic confidence, and improve the efficiency of both clinical practice and sonographer training.
Abstract
Background
Quality control (QC) in echocardiography is crucial but is often subjective, retrospective, and labor-intensive. Artificial intelligence (AI) offers a path to objective, real-time assessment, yet many systems lack clinical interpretability and broad applicability.
Purpose
To develop, validate, and clinically deploy an interpretable, rule-based AI system for the real-time quality assessment of standard echocardiographic views.
Materials And Methods
We first designed a novel, quantifiable scoring rubric for nine standard views, evaluating four key domains: visualized structures, cardiac axis, depth, and gain. This rubric was then automated using a modular AI pipeline, featuring a SlowFast-Echo model for view classification and specialized deep learning models (including SSD and U-Net) for domain-specific assessment. The system was developed on 2,966 videos from a single center, prospectively validated on a temporally distinct cohort of 1,801 videos against an expert-consensus reference standard, and externally validated across three publicly available external datasets(n=1,821 videos).
Results
The view classification model achieved an average accuracy of 98.6%. In classifying overall image quality, the complete AI system demonstrated high agreement with expert consensus, achieving an accuracy of 95.0% on the prospective test set. High performance was maintained across all individual quality domains (accuracy 94.7%-98.7%). The system also showed robust generalizability from 91.7% to 92.3% accuracy across the publicly available external datasets and operated efficiently with a mean inference time of 303 ms per video, confirming its suitability for real-time clinical deployment.
Conclusion
We successfully developed and clinically deployed a comprehensive AI system that provides accurate, immediate, and interpretable feedback on echocardiographic quality. By translating expert criteria into an objective and automated framework for nine standard views, this tool demonstrates strong potential to standardize image acquisition, enhance diagnostic confidence, and improve the efficiency of both clinical practice and sonographer training.
BACKGROUND
Echocardiography is essential for assessing cardiac structure and function, yet accurate interpretation requires specialized expertise, creating challenges in emergency care and in regions with limited access to experienced echocardiographers. Although artificial intelligence-based interpretation is increasingly studied, most existing models rely on still images or single views and do not reflect the video-based, multiview integration used in clinical practice.
OBJECTIVES
The authors aim to develop and evaluate a multiview video-language model that integrates cardiac motion and multiple standard echocardiographic views.
METHODS
We trained a vision-language model on 577,061 transthoracic echocardiography videos paired with Japanese clinical reports from 46,852 examinations acquired at a single tertiary center (2015-2023). For each examination, features from 5 standard views (parasternal long-axis and short-axis; apical 2-, 3-, and 4-chamber) were aggregated. Performance was assessed in a retrieval task selecting the correct report from 16,436 candidate reports in the test cohort based on video input; the primary metric was correct match retrieval probability within the top 10 candidates (ie, R@10).
RESULTS
The image-based baseline achieved an R@10 of 1.3%. Using video input increased R@10 to 4.2%. Integrating 5 views further improved R@10 to 6.0% (95% CI: 5.5%-6.4%). Gains were greatest for findings that depended on temporal dynamics and multiview assessment, including left ventricular wall motion abnormality and left ventricular dilation.
CONCLUSIONS
A multiview video-language framework improved report retrieval compared with conventional image-based approaches. These findings support the utility of video-based, multiview representation learning for echocardiographic report retrieval.
R. Takizawa, Chiemi Yamazaki, S. Kodera et al.· JACC: Asia· 0 citations
Echocardiography is a central modality for cardiac diagnosis; rising clinical demand and advances in machine learning have accelerated AI development for automated analysis. As these systems may influence high-stakes decisions, model interpretability is essential for clinical trust and accountability. In this review, we define interpretable AI model approaches as strategies that improve interpretability through intrinsically interpretable components within transparent models or post hoc explainable AI (XAI) for black-box models. We synthesized 170 echocardiography studies using interpretable AI model approaches and mapped model types, explanation strategies, and evaluation practices. To compare approach-specific patterns, studies were categorized into multistep and end-to-end frameworks, representing intermediate representation versus direct prediction. Multistep studies were more prevalent and typically combined convolutional neural network (CNN)-based upstream models with intrinsically interpretable downstream approaches. End-to-end studies included more complex architectures, with the most common pairing being CNN-based models with class activation mapping-based visualizations. Evaluation practices also differed by framework. Multistep studies more frequently reported quantitatively defined clinical metrics and included several studies demonstrating prospective, application-level implementation. In contrast, at the model-approach instance level, end-to-end instances relied more often on qualitative-grounded evaluation than multistep upstream instances (23/57, 40.4% vs. 2/122, 1.6%). Collectively, these findings highlight the distinct challenges and promising research directions for each approach: multistep models may benefit from more advanced architectures, whereas end-to-end models require more deliberate post hoc explanation methods and stronger quantitative evaluation to support clinical translation. This work, therefore, provides a structured foundation and classification approach to meaningfully evaluate and advance interpretable AI model approaches in echocardiography.
Ryoma Ishii, Roger A. Edwards, Patrick E. Gelbach et al.· Journal of imaging informati...· 0 citations
Transthoracic echocardiography is a widely used, noninvasive tool for cardiac imaging, but the quality of image acquisition remains highly operator-dependent. Existing artificial intelligence-based systems often require large amounts of labeled data and provide only global quality scores, limiting their utility in real-time clinical applications. We propose a multi-task guidance framework that jointly performs supervised view classification and cardiac structure segmentation, and reuses their outputs to enable label-efficient, structure-specific image quality scoring through entropy-based metrics without additional quality annotations. A lightweight maneuver predictor then uses these features to suggest one of seven corrective probe maneuvers in real-time. To train and validate the system, we constructed a 43-case maneuver-tagged dataset capturing intentional transitions from standard to nonstandard views. The proposed quality metric successfully distinguished standard from nonstandard views across multiple cardiac structures (AUC: 0.901-0.987). The maneuver predictor achieved a top-1 accuracy of 85.1% (mAP: 0.904) and inference time of 17 ms per frame, supporting its feasibility for real-time use. This system can assist novice or trainee users in consistently acquiring acceptable echocardiographic views with minimal additional annotation, which can improve clinical efficiency and reliability.
Hyunseok Jeong, J. Jeon, Y. Yoon et al.· IEEE journal of biomedical a...· 0 citations
MitralVision reliably distinguishes clinically significant MR using single-view B-mode echocardiography without Doppler input for model inference and may support more standardized MR screening.
R. Sandler, J. Sokol, S.G. Pawar et al.· Journal of the American Soci...· 0 citations
Echocardiography is the cornerstone for risk stratification, diagnosis, and monitoring of cancer therapy–related cardiac dysfunction (CTRCD)(1). Artificial intelligence (AI)–guided echocardiography has shown high accuracy and reliability in diverse cardiac populations and may reduce variability while improving workflow efficiency(2, 3). However, this technology has not yet been validated in a dedicated cohort of patients with cancer.
To evaluate the accuracy and reliability of AI-guided echocardiography in assessing left ventricular ejection fraction (LVEF) and additional parameters, compared with conventional echocardiography, in a cardio-oncology population.
This study included patients identified retrospectively from a cardio-oncology registry. Studies, that had already been analysed manually by expert sonographers and reported using AGFA PACS system, were uploaded to the US2.ai platform for automated analysis. The primary outcome was the level of agreement (LoA) between AI-guided and standard echocardiography for LVEF. Secondary outcomes included LoA for additional echocardiographic parameters and LoA between AI- LVEF and 3D LVEF. The performance of the deep learning (DL) algorithm in identifying LVEF <50% was evaluated using the area under the receiver operating characteristic curve (ROC-AUC). Subgroup analyses were performed in predefined populations clinically relevant in cardio-oncology.
A total of 282 patients were included. Mean age was 60 ± 16 years, and 61% were women. Breast cancer was the most frequent malignancy (30.5%), followed by haematological malignancies (16.7%) and gastrointestinal tumours (10.6%). Manual median 2D LVEF was 60% (IQR: 55-64) and AI-derived LVEF was 59.2% (IQR: 53-64) showing good agreement and correlation (bias: −0.138, SD: 5.38, 95% LoA: −10.7 to 10.4, ICC: 0.791, 95% CI: 0.742–0.831, Spearman ρ: 0.718,), Table 1. Comparison between 3D echocardiography LVEF and AI-derived 2D LVEF showed similar agreement with narrower limits (bias: −0.13, 95% LoA: −9.51 to 9.26). The DL algorithm accurately identified LVEF <50% (ROC-AUC: 0.918, 95% CI: 0.875–0.961), Figure 1. Subgroup analyses demonstrated consistent agreement in patients with breast cancer, body mass index >30, prior radiotherapy and pericardial effusion.
In a large real-world cardio-oncology cohort, AI-guided echocardiography demonstrated strong agreement with conventional echocardiography for LVEF assessment and high accuracy for detecting clinically relevant LV dysfunction. Performance was consistent across key subgroups, supporting the feasibility, reliability, and potential clinical value of integrating DL-based analysis into routine cardio-oncology echocardiographic workflows.Agreement between manual and AI-echo AUC-ROC curve for LVEF<50%
M. Andres, V. Maharajan, M. C. Llamedo et al.· European Heart Journal, Supp...· 0 citations
The role of AI-enhanced cardiovascular ultrasound in the transition from descriptive imaging toward predictive and personalized medicine is examined, with AI-enhanced cardiovascular ultrasound poised to become a central tool of precision cardiology.
Ancuța Elena Țupu, Simona Steliana Tudor, C. Dumitru et al.· Journal of Clinical Medicine· 0 citations