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
. 2025 May 26;25(1):183.
doi: 10.1186/s12880-025-01709-x.

Detecting microcephaly and macrocephaly from ultrasound images using artificial intelligence

Abraham Keffale Mengistu  1 , Bayou Tilahun Assaye  2 , Addisu Baye Flatie  2 , Zewdie Mossie  3
Affiliations

Detecting microcephaly and macrocephaly from ultrasound images using artificial intelligence

Abraham Keffale Mengistu et al. BMC Med Imaging. .

Abstract

Background: Microcephaly and macrocephaly, which are abnormal congenital markers, are associated with developmental and neurologic deficits. Hence, there is a medically imperative need to conduct ultrasound imaging early on. However, resource-limited countries such as Ethiopia are confronted with inadequacies such that access to trained personnel and diagnostic machines inhibits the exact and continuous diagnosis from being met.

Objective: This study aims to develop a fetal head abnormality detection model from ultrasound images via deep learning.

Methods: Data were collected from three Ethiopian healthcare facilities to increase model generalizability. The recruitment period for this study started on November 9, 2024, and ended on November 30, 2024. Several preprocessing techniques have been performed, such as augmentation, noise reduction, and normalization. SegNet, UNet, FCN, MobileNetV2, and EfficientNet-B0 were applied to segment and measure fetal head structures using ultrasound images. The measurements were classified as microcephaly, macrocephaly, or normal using WHO guidelines for gestational age, and then the model performance was compared with that of existing industry experts. The metrics used for evaluation included accuracy, precision, recall, the F1 score, and the Dice coefficient.

Results: This study was able to demonstrate the feasibility of using SegNet for automatic segmentation, measurement of abnormalities of the fetal head, and classification of macrocephaly and microcephaly, with an accuracy of 98% and a Dice coefficient of 0.97. Compared with industry experts, the model achieved accuracies of 92.5% and 91.2% for the BPD and HC measurements, respectively.

Conclusion: Deep learning models can enhance prenatal diagnosis workflows, especially in resource-constrained settings. Future work needs to be done on optimizing model performance, trying complex models, and expanding datasets to improve generalizability. If these technologies are adopted, they can be used in prenatal care delivery.

Clinical trial number: Not applicable.

Keywords: BPD; Congenital abnormality; HC; Macrocephaly; Microcephaly.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: The study received ethical clearance from Debre Markos University CMHS (College of Medicine and Health Sciences) IRERC (Institutional Review and Ethics Review Committee) with Reference: RCSTTD/397/01/17, accredited under ICH-GCP and IORG standards, and our study adhered to the Declaration of Helsinki. Written informed consent was obtained from all adult participants before their inclusion. The consent process, conducted by the participating health institution, was documented and verified by the radiologist responsible for image collection, ensuring adherence to ethical protocols. No minors were included in the study. No personal identifiers were collected to safeguard privacy, and all ultrasound data were anonymized before analysis. Data integrity was maintained through secure protection systems that were compliant with international standards for medical imaging research. Collaborations with health institutions emphasized accountability and ethical rigor in handling imaging data, with oversight from the ethics committee to ensure full compliance. Consent for publication: Not applicable. No identifying details, images, or personal information of participants are included in this manuscript. All data were anonymized before analysis, and no individual consent for publication was required. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Raw images annotated and measured by gynecologists
Fig. 2
Fig. 2
Model framework
Fig. 3
Fig. 3
The optimized SegNet model architecture used for the final training
Fig. 4
Fig. 4
First experimental results
Fig. 5
Fig. 5
UNet model performance after optimization
Fig. 6
Fig. 6
Optimized SegNet performance at 25 Epochs
Fig. 7
Fig. 7
Performance of the SegNet model after tuning at 50 epochs
Fig. 8
Fig. 8
Performance of the SegNet model after tuning for 100 epochs
Fig. 9
Fig. 9
Segmentation result of optimized segNet the model
Fig. 10
Fig. 10
Segmentation result of the model with predicted mask and ground truth
Fig. 11
Fig. 11
Measurement of HC and BPD
Fig. 12
Fig. 12
Model prototype output
Fig. 13
Fig. 13
Model prototype output
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Namburete AIL, et al. Normative Spatiotemporal fetal brain maturation with satisfactory development at 2 years. Nature. 2023;623(7985):106–14. 10.1038/s41586-023-06630-3. - PMC - PubMed
    1. Xue J, Xue J, Ru Y, Zhang G, Yin H, Liu D. Ultrasound assessment of insular development in adequate-for-gestational-age fetuses and fetuses with early-onset fetal growth restriction using 3D-ICRV technology. Front Med (Lausanne). 2024;11:1393115. - PMC - PubMed
    1. DeSilva M, Munoz FM, Mcmillan M, Kawai AT, Marshall H, Macartney KK, et al. Congenital anomalies: Case definition and guidelines for data collection, analysis, and presentation of immunization safety data. Vaccine. 2016;34(49):6015–26. 10.1016/j.vaccine.2016.03.047. - PMC - PubMed
    1. Nelson KM, Irvin-Choy ND, Hoffman MK, Gleghorn JP, Day ES. Diseases and conditions that impact maternal and fetal health and the potential for nanomedicine therapies. 01 Mar 2021. 10.1016/j.addr.2020.09.013 - PMC - PubMed
    1. Arroyo J et al. No sonographer, no radiologist: New system for automatic prenatal detection of fetal biometry, fetal presentation, and placental location, PLoS One. Feb. 2022;17(2). 10.1371/journal.pone.0262107 - PMC - PubMed

LinkOut - more resources