Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Oct 29:11:1486995.
doi: 10.3389/fmed.2024.1486995. eCollection 2024.

Artificial intelligence assisted common maternal fetal planes prediction from ultrasound images based on information fusion of customized convolutional neural networks

Fatima Rauf  1 , Muhammad Attique Khan  2 , Hussain M Albarakati  3 , Kiran Jabeen  1 , Shrooq Alsenan  4 , Ameer Hamza  1 , Sokea Teng  5 , Yunyoung Nam  5
Affiliations

Artificial intelligence assisted common maternal fetal planes prediction from ultrasound images based on information fusion of customized convolutional neural networks

Fatima Rauf et al. Front Med (Lausanne). .

Abstract

Ultrasound imaging is frequently employed to aid with fetal development. It benefits from being real-time, inexpensive, non-intrusive, and simple. Artificial intelligence is becoming increasingly significant in medical imaging and can assist in resolving many problems related to the classification of fetal organs. Processing fetal ultrasound (US) images increasingly uses deep learning (DL) techniques. This paper aims to assess the development of existing DL classification systems for use in a real maternal-fetal healthcare setting. This experimental process has employed two publicly available datasets, such as FPSU23 Dataset and Fetal Imaging. Two novel deep learning architectures have been designed in the proposed architecture based on 3-residual and 4-residual blocks with different convolutional filter sizes. The hyperparameters of the proposed architectures were initialized through Bayesian Optimization. Following the training process, deep features were extracted from the average pooling layers of both models. In a subsequent step, the features from both models were optimized using an improved version of the Generalized Normal Distribution Optimizer (GNDO). Finally, neural networks are used to classify the fused optimized features of both models, which were first combined using a new fusion technique. The best classification scores, 98.5 and 88.6% accuracy, were obtained after multiple steps of analysis. Additionally, a comparison with existing state-of-the-art methods revealed a notable improvement in the suggested architecture's accuracy.

Keywords: deep learning; information fusion; maternal fetal; optimization; residual blocks; ultrasound.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
A framework for maternal-fetal classification using ultrasound images.
Figure 2
Figure 2
A few sample images of the FPSU23 dataset for classification purposes.
Figure 3
Figure 3
A few sample images of the fetal dataset.
Figure 4
Figure 4
A visual architecture of 3-residual blocks CNN.
Figure 5
Figure 5
Detailed layered architecture of 3-residual blocks CNN.
Figure 6
Figure 6
A visual architecture of proposed 4-residual blocks CNN.
Figure 7
Figure 7
Layered architecture of the CNN with 4- residual blocks.
Figure 8
Figure 8
The visual process of hyperparameters selection using BO.
Figure 9
Figure 9
A framework of GNDO for best feature selection.
Figure 10
Figure 10
Confusion matrix of MN2 for 3-residual blocks CNN.
Figure 11
Figure 11
Confusion matrix of WN2 for 4-residual blocks CNN.
Figure 12
Figure 12
MN2 confusion matrix after the fusion of best features for FPSU23 dataset.
Figure 13
Figure 13
WN2 classifier confusion matrix after the fusion process using fetal dataset.
Figure 14
Figure 14
Comparison in term of accuracy for FPSU23 dataset by using several neural networks.
Figure 15
Figure 15
Comparison in term of accuracy for maternal fetal dataset by using several neural networks.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Radan AP, Aleksandra Polowy J, Heverhagen A, Simillion C, Baumann M, Raio L, et al. . Cervico-vaginal placental α-macroglobulin-1 combined with cervical length for the prediction of preterm birth in women with threatened preterm labor. Acta Obstet Gynecol Scand. (2020) 99:357–63. doi: 10.1111/aogs.13744, PMID: - DOI - PubMed
    1. Baldisserotto ML, Theme Filha MM. Construct validity and reliability of the Brazilian version of the maternal-fetal attachment scale (MFAS): a proposal for a 12-item short version. Cad Saude Publica. (2023) 39:e00133922. doi: 10.1590/0102-311xen133922, PMID: - DOI - PubMed
    1. Ye J., Liu R., Zou B., Zhang H., Han C., Yang Y., et al. ., A deep convolutional neural network based hybrid framework for fetal head standard plane identification. Authorea Preprints; (2020).
    1. Ryou H, Yaqub M, Cavallaro A, Papageorghiou AT, Alison Noble J. Automated 3D ultrasound image analysis for first trimester assessment of fetal health. Phys Med Biol. (2019) 64:185010. doi: 10.1088/1361-6560/ab3ad1, PMID: - DOI - PubMed
    1. Mirzamoradi M, Mokhtari Torshizi H, Abaspour M, Ebrahimi A, Ameri A. A neural network-based approach to prediction of preterm birth using non-invasive tests. J Biomed Phys Eng. (2022) 14:503–8. doi: 10.31661/jbpe.v0i0.2201-1449 - DOI - PMC - PubMed

LinkOut - more resources