Advancing real-time echocardiographic diagnosis with a hybrid deep learning model DOI Open Access
А.К. Bolshibayeva, Sabina Rakhmetulayeva, B.M. Ukibassov

et al.

Eastern-European Journal of Enterprise Technologies, Journal Year: 2024, Volume and Issue: 6(9 (132)), P. 60 - 70

Published: Dec. 30, 2024

This research focuses on developing a novel hybrid deep learning architecture designed for real-time analysis of ultrasound heart images. The object the study is diagnostic accuracy and efficiency in detecting pathologies such as atrial septal defect (ASD) aortic stenosis (AS) from data. problem insufficient generalizability existing models cardiac image analysis, which limits their practical clinical application. To solve this, convolutional neural networks (CNNs), combining local feature extraction was integrated with global contextual understanding structures. Additionally, YOLOv7 precise segmentation detection utilized. results demonstrate that model achieves an overall 92 % ASD 90 AS detection, representing 7 improvement over standard model. These improvements are attributed to architecture's ability simultaneously capture fine-grained anatomical details broader structural relationships, enhancing subtle anomalies. findings suggest combination CNNs enhances pattern recognition leading better key features contributing solving include detailed context simultaneously. In terms, can be applied settings require assessment using medical imaging equipment. Its computational high make it suitable even resource-constrained environments, reducing time clinicians, supporting personalized treatment plans, potentially improving patient outcomes cardiology

Language: Английский

Diagnostic accuracy of artificial intelligence models in detecting congenital heart disease in the second-trimester fetus through prenatal cardiac screening: a systematic review and meta-analysis DOI Creative Commons
Lies Dina Liastuti, Yosilia Nursakina

Frontiers in Cardiovascular Medicine, Journal Year: 2025, Volume and Issue: 12

Published: Feb. 24, 2025

Congenital heart disease (CHD) is a major contributor to morbidity and infant mortality imposes the highest burden on global healthcare costs. Early diagnosis prompt treatment of CHD contribute enhanced neonatal outcomes survival rates; however, there shortage proficient examiners in remote regions. Artificial intelligence (AI)-powered ultrasound provides potential solution improve diagnostic accuracy fetal screening. A literature search was conducted across seven databases for systematic review. Articles were retrieved based PRISMA Flow 2020 inclusion exclusion criteria. Eligible data further meta-analyzed, risk bias tested using Quality Assessment Diagnostic Accuracy Studies-Artificial Intelligence. total 374 studies screened eligibility, but only 9 included. Most utilized deep learning models either or echocardiographic images. Overall, AI performed exceptionally well accurately identifying normal abnormal meta-analysis these nine resulted pooled sensitivity 0.89 (0.81-0.94), specificity 0.91 (0.87-0.94), an area under curve 0.952 random-effects model. Although several limitations must be addressed before can implemented clinical practice, has shown promising results diagnosis. Nevertheless, prospective with bigger datasets more inclusive populations are needed compare algorithms conventional methods. https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023461738, PROSPERO (CRD42023461738).

Language: Английский

Citations

0
The Artificial Intelligence-Enhanced Echocardiographic Detection of Congenital Heart Defects in the Fetus: A Mini-Review DOI Creative Commons

Khadiza Tun Suha,

Hugh Lubenow,

Stefania Soria-Zurita

et al.

Medicina, Journal Year: 2025, Volume and Issue: 61(4), P. 561 - 561

Published: March 21, 2025

Artificial intelligence (AI) is rapidly gaining attention in radiology and cardiology for accurately diagnosing structural heart disease. In this review paper, we first outline the technical background of AI echocardiography then present an array clinical applications, including image quality control, cardiac function measurements, defect detection, classifications. Collectively, answer how integrating technologies can help improve detection congenital defects. Particularly, superior sensitivity AI-based (CHD) fetus (>90%) allows it to be potentially translated into workflow as effective screening tool obstetric setting. However, current still have many limitations, more technological developments are required enable these reach their full potential. Also, diagnostic should resolve ethical concerns. Otherwise, deploying may not address low-resource populations’ healthcare access disadvantages. Instead, will further exacerbate disparities. We envision that, through combination tele-echocardiography AI, medical facilities gain CHD at prenatal stage.

Language: Английский

Citations

0
Fetal cardiac diagnostics in Indonesia: a study of screening and echocardiography DOI
Muhammad Adrianes Bachnas, Wiku Andonotopo, Adhi Pribadi

et al.

Journal of Perinatal Medicine, Journal Year: 2025, Volume and Issue: unknown

Published: April 15, 2025

Abstract Introduction Congenital heart defects (CHDs) are a leading cause of neonatal morbidity and mortality globally. Accurate prenatal detection is crucial to improving outcomes. In Indonesia, two primary methods used: fetal cardiac screening (FCS), which accessible but limited in sensitivity (40–60 %), echocardiography (FE), the gold standard with over 90 % access due infrastructural financial challenges. Content This review analyzes Indonesia’s diagnostic disparities, highlighting how rural regions rely heavily on FCS, while FE remains restricted urban centers. Emerging technologies, such as AI-enhanced diagnostics telemedicine, show promise bridging gaps by increasing FCS accuracy extending through remote consultations. Summary AI has potential boost up 30 %, making it an effective preliminary tool, telemedicine platforms connect practitioners specialists. However, barriers like insufficient infrastructure, regulatory issues, training hinder widespread adoption. Outlook Addressing these requires standardized national protocols, capacity-building initiatives, public-private partnerships finance infrastructure reduce costs. With technology integration systemic reforms, Indonesia can achieve equitable CHD diagnostics, maternal outcomes aligning global standards.

Language: Английский

Citations

0
A cluster-based ensemble approach for congenital heart disease prediction DOI
Ishleen Kaur, Tanvir Ahmad

Computer Methods and Programs in Biomedicine, Journal Year: 2023, Volume and Issue: 243, P. 107922 - 107922

Published: Nov. 7, 2023

Language: Английский

Citations

7
Empowering Prenatal Care Using AI Image Processing for Early Detection of Pregnancy Complications DOI
Kanishk Bansal

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 51 - 64

Published: July 12, 2024

AI image processing has emerged as a transformative tool in the realm of maternal healthcare, particularly early detection pregnancy complications. By harnessing power artificial intelligence, healthcare providers can now leverage advanced algorithms to analyze medical images such ultrasound scans, MRI images, and fetal monitoring data with unprecedented accuracy efficiency. These AI-based systems excel at detecting subtle abnormalities anomalies that may indicate potential risks health, including markers growth restriction, placental abnormalities, congenital anomalies. facilitating earlier intervention, empowers proactively manage complications, thereby improving outcomes for both mother baby. predictive models enable assess risk complications tailor interventions accordingly.

Language: Английский

Citations

1
A Systematic Review of Fetal Cardiac Abnormality with Future Directions DOI
Kulvinder Singh,

Shirly Edward. A,

D. Anto Sahaya Dhas

et al.

Published: Feb. 21, 2024

Globally, the fetal cardiac abnormality is primary reason for morality. However, understanding huge amount of "Electrocardiogram (ECG)" signals generated from sensors exhausting. The machine learning approaches can be employed to assist evaluation these images and support identifying any dangerous anomalies in fetus. But, traditional techniques still need improvements. Thus, this survey analyzes existing strategies utilized detection tasks. multimodal data performance measures supported tasks are categorized. research gaps challenges provided improve new mechanisms future.

Language: Английский

Citations

0
Identifying At-Risk Patients for Congenital Heart Disease Using Integrated Predictive Models and Fuzzy Clustering Analysis: A Cross-Sectional Study DOI Creative Commons
Amirreza Salehi, Majid Khedmati

Heliyon, Journal Year: 2024, Volume and Issue: 10(20), P. e39609 - e39609

Published: Oct. 1, 2024

Language: Английский

Citations

0
Advancing real-time echocardiographic diagnosis with a hybrid deep learning model DOI Open Access
А.К. Bolshibayeva, Sabina Rakhmetulayeva, B.M. Ukibassov

et al.

Eastern-European Journal of Enterprise Technologies, Journal Year: 2024, Volume and Issue: 6(9 (132)), P. 60 - 70

Published: Dec. 30, 2024

This research focuses on developing a novel hybrid deep learning architecture designed for real-time analysis of ultrasound heart images. The object the study is diagnostic accuracy and efficiency in detecting pathologies such as atrial septal defect (ASD) aortic stenosis (AS) from data. problem insufficient generalizability existing models cardiac image analysis, which limits their practical clinical application. To solve this, convolutional neural networks (CNNs), combining local feature extraction was integrated with global contextual understanding structures. Additionally, YOLOv7 precise segmentation detection utilized. results demonstrate that model achieves an overall 92 % ASD 90 AS detection, representing 7 improvement over standard model. These improvements are attributed to architecture's ability simultaneously capture fine-grained anatomical details broader structural relationships, enhancing subtle anomalies. findings suggest combination CNNs enhances pattern recognition leading better key features contributing solving include detailed context simultaneously. In terms, can be applied settings require assessment using medical imaging equipment. Its computational high make it suitable even resource-constrained environments, reducing time clinicians, supporting personalized treatment plans, potentially improving patient outcomes cardiology

Language: Английский

Citations

0