Computer-aided assessment for enlarged fetal heart with deep learning model

Summary: Enlarged fetal heart conditions may indicate congenital heart diseases or other complications, making early detection through prenatal ultrasound essential. However, manual assessments by sonographers are often subjective, time-consuming, and inconsistent. This paper proposes a deep learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: Siti Nurmaini, Ade Iriani Sapitri, Muhammad Taufik Roseno, Muhammad Naufal Rachmatullah, Putri Mirani, Nuswil Bernolian, Annisa Darmawahyuni, Bambang Tutuko, Firdaus Firdaus, Anggun Islami, Akhiar Wista Arum, Rio Bastian
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:iScience
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589004225005498
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712841795305472
author Siti Nurmaini
Ade Iriani Sapitri
Muhammad Taufik Roseno
Muhammad Naufal Rachmatullah
Putri Mirani
Nuswil Bernolian
Annisa Darmawahyuni
Bambang Tutuko
Firdaus Firdaus
Anggun Islami
Akhiar Wista Arum
Rio Bastian
author_facet Siti Nurmaini
Ade Iriani Sapitri
Muhammad Taufik Roseno
Muhammad Naufal Rachmatullah
Putri Mirani
Nuswil Bernolian
Annisa Darmawahyuni
Bambang Tutuko
Firdaus Firdaus
Anggun Islami
Akhiar Wista Arum
Rio Bastian
author_sort Siti Nurmaini
collection DOAJ
description Summary: Enlarged fetal heart conditions may indicate congenital heart diseases or other complications, making early detection through prenatal ultrasound essential. However, manual assessments by sonographers are often subjective, time-consuming, and inconsistent. This paper proposes a deep learning approach using the You Only Look Once (YOLO) architecture to automate fetal heart enlargement assessment. Using a set of ultrasound videos, YOLOv8 with a CBAM module demonstrated superior performance compared to YOLOv11 with self-attention. Incorporating the ResNeXtBlock—a residual network with cardinality—additionally enhanced accuracy and prediction consistency. The model exhibits strong capability in detecting fetal heart enlargement, offering a reliable computer-aided tool for sonographers during prenatal screenings. Further validation is required to confirm its clinical applicability. By improving early and accurate detection, this approach has the potential to enhance prenatal care, facilitate timely interventions, and contribute to better neonatal health outcomes.
format Article
id doaj-art-e30121f1e9674bb4b16b097041cb7f8a
institution DOAJ
issn 2589-0042
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series iScience
spelling doaj-art-e30121f1e9674bb4b16b097041cb7f8a2025-08-20T03:14:08ZengElsevieriScience2589-00422025-05-0128511228810.1016/j.isci.2025.112288Computer-aided assessment for enlarged fetal heart with deep learning modelSiti Nurmaini0Ade Iriani Sapitri1Muhammad Taufik Roseno2Muhammad Naufal Rachmatullah3Putri Mirani4Nuswil Bernolian5Annisa Darmawahyuni6Bambang Tutuko7Firdaus Firdaus8Anggun Islami9Akhiar Wista Arum10Rio Bastian11Intelligent System Research Group, Universitas Sriwijaya, Palembang, Indonesia; Corresponding authorIntelligent System Research Group, Universitas Sriwijaya, Palembang, IndonesiaComputer Science Department, Universitas Sumatera Selatan, Palembang, IndonesiaIntelligent System Research Group, Universitas Sriwijaya, Palembang, IndonesiaDepartment of Obstetrics and Gynecology, Fetomaternal Division, Bunda Hospital, Palembang, IndonesiaDepartment of Obstetrics and Gynecology, Fetomaternal Division, Dr. Mohammad Hoesin General Hospital, Palembang, IndonesiaIntelligent System Research Group, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Universitas Sriwijaya, Palembang, IndonesiaSummary: Enlarged fetal heart conditions may indicate congenital heart diseases or other complications, making early detection through prenatal ultrasound essential. However, manual assessments by sonographers are often subjective, time-consuming, and inconsistent. This paper proposes a deep learning approach using the You Only Look Once (YOLO) architecture to automate fetal heart enlargement assessment. Using a set of ultrasound videos, YOLOv8 with a CBAM module demonstrated superior performance compared to YOLOv11 with self-attention. Incorporating the ResNeXtBlock—a residual network with cardinality—additionally enhanced accuracy and prediction consistency. The model exhibits strong capability in detecting fetal heart enlargement, offering a reliable computer-aided tool for sonographers during prenatal screenings. Further validation is required to confirm its clinical applicability. By improving early and accurate detection, this approach has the potential to enhance prenatal care, facilitate timely interventions, and contribute to better neonatal health outcomes.http://www.sciencedirect.com/science/article/pii/S2589004225005498Machine learningartificial intelligenceCardiovascular medicine
spellingShingle Siti Nurmaini
Ade Iriani Sapitri
Muhammad Taufik Roseno
Muhammad Naufal Rachmatullah
Putri Mirani
Nuswil Bernolian
Annisa Darmawahyuni
Bambang Tutuko
Firdaus Firdaus
Anggun Islami
Akhiar Wista Arum
Rio Bastian
Computer-aided assessment for enlarged fetal heart with deep learning model
iScience
Machine learning
artificial intelligence
Cardiovascular medicine
title Computer-aided assessment for enlarged fetal heart with deep learning model
title_full Computer-aided assessment for enlarged fetal heart with deep learning model
title_fullStr Computer-aided assessment for enlarged fetal heart with deep learning model
title_full_unstemmed Computer-aided assessment for enlarged fetal heart with deep learning model
title_short Computer-aided assessment for enlarged fetal heart with deep learning model
title_sort computer aided assessment for enlarged fetal heart with deep learning model
topic Machine learning
artificial intelligence
Cardiovascular medicine
url http://www.sciencedirect.com/science/article/pii/S2589004225005498
work_keys_str_mv AT sitinurmaini computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT adeirianisapitri computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT muhammadtaufikroseno computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT muhammadnaufalrachmatullah computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT putrimirani computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT nuswilbernolian computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT annisadarmawahyuni computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT bambangtutuko computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT firdausfirdaus computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT anggunislami computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT akhiarwistaarum computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel
AT riobastian computeraidedassessmentforenlargedfetalheartwithdeeplearningmodel