Deep Learning-Based Classification of Fetal Head Abnormalities from Ultrasound Images Using EfficientNet-B3
Abstract
Fetal brain abnormalities represent a critical concern in prenatal diagnostics due to their significant impact on neonatal survival and neurological development. Conventional ultrasound (USG) screening relies heavily on expert interpretation, which can be time-consuming and prone to subjectivity. To overcome this constraint, this research develops an automated classification approach employing deep learning techniques to recognize fetal head abnormalities captured through ultrasound scans. The dataset, obtained from a publicly available Kaggle repository, comprises fourteen diagnostic categories, including Arnold Chiari Malformation, Arachnoid Cyst, Cerebellar Hypoplasia, Holoprosencephaly, and Ventriculomegaly variations, among others. Each ultrasound image was subjected to a series of preprocessing operations, such as resizing to 224×224 pixels, applying normalization, and performing data augmentation, to enrich feature variability and strengthen the model’s generalization capability. A pretrained EfficientNet-B3 architecture was fine-tuned for multi-class classification, with the fully connected layer adapted to predict fourteen distinct abnormality classes. Model training was conducted for ten epochs using the Adam optimizer and cross-entropy loss function, with performance evaluated via training loss and validation accuracy metrics. The results demonstrate rapid convergence, with training loss decreasing from 1.7055 in the first epoch to 0.0387 in the final epoch. Concurrently, validation accuracy improved from 79.60% to a peak of 91.37%, indicating strong generalization capability. The consistent upward trend in accuracy and the downward trend in loss confirm the model’s stability and effective learning behavior. Overall, the proposed EfficientNet-B3–based approach achieves high accuracy and robustness, highlighting its potential as an assistive tool for automated prenatal diagnosis of fetal brain abnormalities
Downloads
References
H. R. Torres et al., “A review of image processing methods for fetal head and brain analysis in ultrasound images,” Mar. 01, 2022, Elsevier Ireland Ltd. doi: 10.1016/j.cmpb.2022.106629.
S. L. Connors et al., “Fetal Mechanisms in Neurodevelopmental Disorders,” Pediatr Neurol, vol. 38, no. 3, pp. 163–176, Mar. 2008, doi: 10.1016/j.pediatrneurol.2007.10.009.
F. Vahedifard et al., “Review of deep learning and artificial intelligence models in fetal brain magnetic resonance imaging.,” World J Clin Cases, vol. 11, no. 16, pp. 3725–3735, Jun. 2023, doi: 10.12998/wjcc.v11.i16.3725.
M. S. Arroyo, R. J. Hopkin, U. D. Nagaraj, B. Kline-Fath, and C. Venkatesan, “Fetal brain MRI findings and neonatal outcome of common diagnosis at a tertiary care center,” Journal of Perinatology, vol. 39, no. 8, pp. 1072–1077, Aug. 2019, doi: 10.1038/s41372-019-0407-9.
M. Whitworth, L. Bricker, and C. Mullan, “Ultrasound for fetal assessment in early pregnancy,” Jul. 14, 2015, John Wiley and Sons Ltd. doi: 10.1002/14651858.CD007058.pub3.
H. H. Bijma, A. van der Heide, and H. I. J. Wildschut, “Decision-Making after Ultrasound Diagnosis of Fetal Abnormality,” Reprod Health Matters, vol. 16, no. sup31, pp. 82–89, Jan. 2008, doi: 10.1016/S0968-8080(08)31372-X.
L. Meng, D. Zhao, Z. Yang, and B. Wang, “Automatic display of fetal brain planes and automatic measurements of fetal brain parameters by transabdominal three‐dimensional ultrasound,” Journal of Clinical Ultrasound, vol. 48, no. 2, pp. 82–88, Feb. 2020, doi: 10.1002/jcu.22762.
A. Ishaq, F. U. M. Ullah, P. Hamandawana, D. J. Cho, and T. S. Chung, “Improved EfficientNet Architecture for Multi-Grade Brain Tumor Detection,” Electronics (Switzerland), vol. 14, no. 4, Feb. 2025, doi: 10.3390/electronics14040710.
H. Zhao et al., “Memory-based unsupervised video clinical quality assessment with multi-modality data in fetal ultrasound,” Med Image Anal, vol. 90, Dec. 2023, doi: 10.1016/j.media.2023.102977.
T. Ciceri, L. Squarcina, A. Giubergia, A. Bertoldo, P. Brambilla, and D. Peruzzo, “Review on deep learning fetal brain segmentation from Magnetic Resonance images,” Sep. 01, 2023, Elsevier B.V. doi: 10.1016/j.artmed.2023.102608.
M. Alzubaidi, M. Agus, M. Makhlouf, F. Anver, K. Alyafei, and M. Househ, “Large-scale annotation dataset for fetal head biometry in ultrasound images,” Data Brief, vol. 51, Dec. 2023, doi: 10.1016/j.dib.2023.109708.
S. S. Płotka et al., “Deep learning for estimation of fetal weight throughout the pregnancy from fetal abdominal ultrasound,” Am J Obstet Gynecol MFM, vol. 5, no. 12, Dec. 2023, doi: 10.1016/j.ajogmf.2023.101182.
J. Lo, A. Lim, M. W. Wagner, B. Ertl-Wagner, and D. Sussman, “Fetal Organ Anomaly Classification Network for Identifying Organ Anomalies in Fetal MRI,” Front Artif Intell, vol. 5, Mar. 2022, doi: 10.3389/frai.2022.832485.
D. Mavaluru et al., “Advancing fetal ultrasound diagnostics: Innovative methodologies for improved accuracy in detecting down syndrome,” Med Eng Phys, vol. 126, Apr. 2024, doi: 10.1016/j.medengphy.2024.104132.
N. Hernandez-Cruz et al., “Detection of fetal congenital heart defects on three-vessel view ultrasound videos,” WFUMB Ultrasound Open, vol. 2, no. 2, Dec. 2024, doi: 10.1016/j.wfumbo.2024.100075.
J. He, L. Yang, B. Liang, S. Li, and C. Xu, “Fetal cardiac ultrasound standard section detection model based on multitask learning and mixed attention mechanism,” Neurocomputing, vol. 579, Apr. 2024, doi: 10.1016/j.neucom.2024.127443.
R. Ramirez Zegarra et al., “A deep learning approach to identify the fetal head position using transperineal ultrasound during labor,” European Journal of Obstetrics and Gynecology and Reproductive Biology, vol. 301, pp. 147–153, Oct. 2024, doi: 10.1016/j.ejogrb.2024.08.012.
W. Zhang et al., “A joint brain extraction and image quality assessment framework for fetal brain MRI slices,” Neuroimage, vol. 290, Apr. 2024, doi: 10.1016/j.neuroimage.2024.120560.
L. Wang, M. Fatemi, and A. Alizad, “Artificial intelligence in fetal brain imaging: Advancements, challenges, and multimodal approaches for biometric and structural analysis,” Jun. 01, 2025, Elsevier Ltd. doi: 10.1016/j.compbiomed.2025.110312.
P. Ahmed, M. S. U. Yusuf, S. Sarker, A. Chowdhury, A. Bhowmik, and F. Rahman, “A Comparative Study of Different Segmentation and Regression Models for Fetal Head Circumference Measurement,” in 2nd International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ic-ETITE58242.2024.10493596.
M. Gong and Q. Fei, “An Improved Light-weight Deep Transfer Learning for Fetal Lung Ultrasound Image Segmentation,” in 2024 3rd International Conference on Image Processing and Media Computing, ICIPMC 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 151–156. doi: 10.1109/ICIPMC62364.2024.10586709.
S. Abishek, A. Mathialagan, S. A. Hari Om Swarup, M. Goyal, and J. Mannar Mannan, “An Intelligent Fetal Prognostic System using Machine Learning Techniques,” in 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/IATMSI60426.2024.10503455.
M.-L. Zhang and Z.-H. Zhou, “A Review on Multi-Label Learning Algorithms,” IEEE Trans Knowl Data Eng, vol. 26, no. 8, pp. 1819–1837, Aug. 2014, doi: 10.1109/TKDE.2013.39.
M. A. Talukder, M. A. Layek, M. Kazi, M. A. Uddin, and S. Aryal, “Empowering COVID-19 detection: Optimizing performance through fine-tuned EfficientNet deep learning architecture,” Comput Biol Med, vol. 168, Jan. 2024, doi: 10.1016/j.compbiomed.2023.107789.
R. Raza et al., “Lung-EffNet: Lung cancer classification using EfficientNet from CT-scan images,” Eng Appl Artif Intell, vol. 126, Nov. 2023, doi: 10.1016/j.engappai.2023.106902.
V. Venugopal, N. I. Raj, M. K. Nath, and N. Stephen, “A deep neural network using modified EfficientNet for skin cancer detection in dermoscopic images,” Decision Analytics Journal, vol. 8, Sep. 2023, doi: 10.1016/j.dajour.2023.100278.
