Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning

Ventricular septal defect (VSD) is congenital cardiac defect that accounts for 26% of all congenital heart disorders (CHDs) and has an incidence rate of 3.5 per 1,000 live births. It results from chromosomal abnormalities, sequence variants, and euploidy, among other genetic pre-dispositions, as wel...

Descripción completa

Detalles Bibliográficos
Autores: Mittal, Ruchi, Bhushan, Megha
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2026
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:dnet:idus________::e6f864653634ae7d7662cff4ee2df7f6
Acceso en línea:https://hdl.handle.net/11441/186308
https://doi.org/10.1007/s10489-026-07174-5
Access Level:acceso abierto
Palabra clave:Ventricular septal defect
Congenital heart diseases
Deep learning
Fetal ultrasound
Feature extraction
Optimal feature selection
id ES_ce6c6065b60a2ca0fb3f9d933cc83116
oai_identifier_str oai:dnet:idus________::e6f864653634ae7d7662cff4ee2df7f6
network_acronym_str ES
network_name_str España
repository_id_str
spelling Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learningMittal, RuchiBhushan, MeghaVentricular septal defectCongenital heart diseasesDeep learningFetal ultrasoundFeature extractionOptimal feature selectionVentricular septal defect (VSD) is congenital cardiac defect that accounts for 26% of all congenital heart disorders (CHDs) and has an incidence rate of 3.5 per 1,000 live births. It results from chromosomal abnormalities, sequence variants, and euploidy, among other genetic pre-dispositions, as well as environmental variables. Also, 20%–30% of CHDs are caused by genetic factors, and 36.8% of VSD cases have inherited causes. Although surgical procedures often result in positive outcomes, the prognosis for VSDs linked to genetic disorders is frequently less encouraging. Together with ultrasound screening, early prenatal genetic examination improves diagnostic precision, aids in parental decision-making, maximizes prenatal treatment, and lowers newborn mortality from CHD. Obstacles like high demand for fetal cardiologists and the great number of screening cases restrict the effectiveness of detection. To increase the precision of fetal cardiac VSD identification; this work presents a sophisticated prenatal diagnostic model that makes use of hybrid deep learning (DL). Over the course of four years (2021–2024), a dataset of 1,350 2D ultrasound fetal heart pictures was gathered from online sources and a private scanning centre, guaranteeing adherence to the Helsinki Declaration and World Medical Association ethical criteria. The proposed model follows a structured pipeline, including speckle noise removal, optimal ROI segmentation, feature extraction using attention mechanism, optimal feature selection, and a DL based diagnostic system for VSD detection and classification. According to experimental results, the suggested model outperforms state-of-the-art models by 6.4%, achieved excellent prediction accuracy of 98.5%. These findings suggest that the model improves diagnostic precision and speeds up doctors’ decision-making when diagnosing VSD.SpringerLenguajes y Sistemas InformáticosTIC276: Diverso Lab - International ComputingMinisterio de Ciencia, Innovación y Universidades (MICIU). España2026info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/186308https://doi.org/10.1007/s10489-026-07174-5reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésApplied Intelligence, 56 (5), 177-19 p.. PID2022-138486OB-I00https://link.springer.com/article/10.1007/s10489-026-07174-5info:eu-repo/semantics/openAccessoai:dnet:idus________::e6f864653634ae7d7662cff4ee2df7f62026-06-17T12:51:07Z
dc.title.none.fl_str_mv Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning
title Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning
spellingShingle Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning
Mittal, Ruchi
Ventricular septal defect
Congenital heart diseases
Deep learning
Fetal ultrasound
Feature extraction
Optimal feature selection
title_short Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning
title_full Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning
title_fullStr Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning
title_full_unstemmed Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning
title_sort Optimal prenatal diagnosis model for fetal heart ventricular septal defect detection using hybrid deep learning
dc.creator.none.fl_str_mv Mittal, Ruchi
Bhushan, Megha
author Mittal, Ruchi
author_facet Mittal, Ruchi
Bhushan, Megha
author_role author
author2 Bhushan, Megha
author2_role author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
TIC276: Diverso Lab - International Computing
Ministerio de Ciencia, Innovación y Universidades (MICIU). España
dc.subject.none.fl_str_mv Ventricular septal defect
Congenital heart diseases
Deep learning
Fetal ultrasound
Feature extraction
Optimal feature selection
topic Ventricular septal defect
Congenital heart diseases
Deep learning
Fetal ultrasound
Feature extraction
Optimal feature selection
description Ventricular septal defect (VSD) is congenital cardiac defect that accounts for 26% of all congenital heart disorders (CHDs) and has an incidence rate of 3.5 per 1,000 live births. It results from chromosomal abnormalities, sequence variants, and euploidy, among other genetic pre-dispositions, as well as environmental variables. Also, 20%–30% of CHDs are caused by genetic factors, and 36.8% of VSD cases have inherited causes. Although surgical procedures often result in positive outcomes, the prognosis for VSDs linked to genetic disorders is frequently less encouraging. Together with ultrasound screening, early prenatal genetic examination improves diagnostic precision, aids in parental decision-making, maximizes prenatal treatment, and lowers newborn mortality from CHD. Obstacles like high demand for fetal cardiologists and the great number of screening cases restrict the effectiveness of detection. To increase the precision of fetal cardiac VSD identification; this work presents a sophisticated prenatal diagnostic model that makes use of hybrid deep learning (DL). Over the course of four years (2021–2024), a dataset of 1,350 2D ultrasound fetal heart pictures was gathered from online sources and a private scanning centre, guaranteeing adherence to the Helsinki Declaration and World Medical Association ethical criteria. The proposed model follows a structured pipeline, including speckle noise removal, optimal ROI segmentation, feature extraction using attention mechanism, optimal feature selection, and a DL based diagnostic system for VSD detection and classification. According to experimental results, the suggested model outperforms state-of-the-art models by 6.4%, achieved excellent prediction accuracy of 98.5%. These findings suggest that the model improves diagnostic precision and speeds up doctors’ decision-making when diagnosing VSD.
publishDate 2026
dc.date.none.fl_str_mv 2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/186308
https://doi.org/10.1007/s10489-026-07174-5
url https://hdl.handle.net/11441/186308
https://doi.org/10.1007/s10489-026-07174-5
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Applied Intelligence, 56 (5), 177-19 p..
PID2022-138486OB-I00
https://link.springer.com/article/10.1007/s10489-026-07174-5
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419989752086528
score 15,811543

Similares en LA Referencia