FetalDenseNet: multi-scale deep learning for enhanced early detection of fetal anatomical planes in prenatal ultrasound
Journal of Perinatal Medicine · 25.11.2025 · 53 (9) · 1296-1307
DOI: 10.1515/jpm-2025-0249 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Perinatal Medicine, online erschienen am 24.09.2025. Verfasst von Samrat Kumar Dey und 7 weiteren Autor:innen. Beteiligte Einrichtung: MU Institute for Data Science and Informatics, University of Missouri-Columbia, Columbia, MO, USA. Hauptthemen laut MEDLINE: Ultrasonography, Prenatal, Deep Learning, Fetus. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objectives
The study aims to improve the classification of fetal anatomical planes using Deep Learning (DL) methods to enhance the accuracy of fetal ultrasound interpretation.
Methods
Five Convolutional Neural Network (CNN) architectures, such as VGG16, ResNet50, InceptionV3, DenseNet169, and MobileNetV2, are evaluated on a large-scale, clinically validated dataset of 12,400 ultrasound images from 1,792 patients. Preprocessing methods, including scaling, normalization, label encoding, and augmentation, are applied to the dataset, and the dataset is split into 80 % for training and 20 % for testing. Each model was fine-tuned and evaluated based on its classification accuracy for comparison.
Results
DenseNet169 achieved the highest classification accuracy of 92 % among all the tested models.
Conclusions
The study shows that CNN-based models, particularly DenseNet169, significantly improve diagnostic accuracy in fetal ultrasound interpretation. This advancement reduces error rates and provides support for clinical decision-making in prenatal care.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- MU Institute for Data Science and Informatics, University of Missouri-Columbia, Columbia, MO, USA.
- School of Science and Technology, 421966 Bangladesh Open University , Gazipur, Bangladesh.
- Department of Computer and Communication Engineering, Patuakhali Science and Technology University, Dumki, Bangladesh.
- Department of Computer Science and Engineering, University of Barishal, Barishal, Bangladesh.
- Department of Physiology, Shaheed Suhrawardy Medical College, Dhaka, Bangladesh.
- Department of Computer Science and Engineering, Military Institute of Science and Technology, Dhaka, Bangladesh.
ORCID-Profile: Samrat Kumar Dey
Zitieren
APA
Dey, S. K., Howlader, A., Haider, M. S., Saha, T., Setu, D. M., Islam, T., Siddiqi, U. R., & Rahman, M. M. (2025). FetalDenseNet: multi-scale deep learning for enhanced early detection of fetal anatomical planes in prenatal ultrasound. Journal of Perinatal Medicine, 53(9), 1296-1307. https://doi.org/10.1515/jpm-2025-0249
Vancouver
Dey SK, Howlader A, Haider MS, Saha T, Setu DM, Islam T, et al. FetalDenseNet: multi-scale deep learning for enhanced early detection of fetal anatomical planes in prenatal ultrasound. Journal of Perinatal Medicine. 2025;53(9):1296-1307. doi:10.1515/jpm-2025-0249
BibTeX
@article{Dey2025,
author = {Dey, Samrat Kumar and Howlader, Arpita and Haider, Md Shabukta and Saha, Tonmoy and Setu, Deblina Mazumder and Islam, Tania and Siddiqi, Umme Raihan and Rahman, Md Mahbubur},
title = {FetalDenseNet: multi-scale deep learning for enhanced early detection of fetal anatomical planes in prenatal ultrasound},
journal = {Journal of Perinatal Medicine},
year = {2025},
volume = {53},
number = {9},
pages = {1296--1307},
doi = {10.1515/jpm-2025-0249}
}
EUVIMED