Application Progress of Artificial Intelligence in Ultrasound Diagnosis of Fetal Central Nervous System
DOI:
https://doi.org/10.54097/tzzecd45Keywords:
Artificial Intelligence, Central Nervous System Diseases, Ultrasound, FetusAbstract
Fetal central nervous system (CNS) developmental abnormalities are common congenital malformations, and ultrasound imaging is the gold standard for prenatal assessment of fetal health. Three-dimensional (3D) ultrasound can improve the comprehensiveness of diagnostic information, but its diagnostic accuracy is highly dependent on the operator's professional experience, with a risk of missed diagnosis. Artificial intelligence (AI), especially deep learning (DL) methods, provides an important means to solve the above problems. In fetal craniocerebral ultrasound, AI mainly achieves three core applications: first, completing standard section recognition and key structure measurement, standardizing processes through algorithms, eliminating subjective deviations of operators, and promoting the transformation of fetal craniocerebral ultrasound from experience-dependent to standard-quantitative; second, assisting in malformation screening, detection, and classification diagnosis, reducing the dependence of diagnosis on doctors' experience, and narrowing the diagnostic gap between medical institutions at different levels; third, integrating multi-dimensional information to conduct risk assessment and prognosis prediction, providing quantitative basis for clinical consultation and personalized management. At present, the clinical application of AI still faces problems such as the scarcity of high-quality, large-sample, multi-center standardized ultrasound image databases, insufficient algorithm interpretability, poor compatibility with clinical systems, and unclear responsibility definition. In summary, AI has significantly improved the scientificity and reliability of fetal CNS ultrasound diagnosis. In the future, it is necessary to expand multi-center data sets and optimize algorithm performance to promote its clinical popularization and assist the precise development of prenatal medicine. This article reviews the application progress of artificial intelligence technology in ultrasound diagnosis of fetal central nervous system in recent years.
Downloads
References
[1] Tagliabue G, Tessandori R, Caramaschi F, et al. Descriptive epidemiology of selected birth defects, areas of Lombardy, Italy, 1999[J]. Popul Health Metr, 2007,5:4.
[2] YANG F, LI SL, LUO H E A. Expert Consensus on Prenatal Ultrasonic Examination of Fetal Central Nervous System (2020) [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2021,18(05):433-443.
[3] Atta C A M, Fiest K M, Frolkis A D, et al. Global Birth Prevalence of Spina Bifida by Folic Acid Fortification Status: A Systematic Review and Meta-Analysis[J]. Am J Public Health, 2016,106(1):e24-e34.
[4] Goldstein H E, Solomon R A. Epidemiology of cavernous malformations[J]. Handb Clin Neurol, 2017,143:241-247.
[5] Weichert J, Scharf J L. Advancements in Artificial Intelligence for Fetal Neurosonography: A Comprehensive Review[J]. J Clin Med, 2024,13(18).
[6] Andelija S, Tafti D. Sonography Fetal Assessment, Protocols, and Interpretation[J]. 2025.
[7] Huang Q, Zeng Z. A Review on Real-Time 3D Ultrasound Imaging Technology[J]. Biomed Res Int, 2017,2017:6027029.
[8] Alzubaidi M, Agus M, Shah U, et al. Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction[J]. Diagnostics (Basel), 2022,12(9).
[9] Xiao S, Zhang J, Zhu Y, et al. Application and Progress of Artificial Intelligence in Fetal Ultrasound[J]. J Clin Med, 2023,12(9).
[10] Marroquin J L, Vemuri B C, Botello S, et al. An accurate and efficient bayesian method for automatic segmentation of brain MRI[J]. IEEE Trans Med Imaging, 2002,21(8):934-945.
[11] Ciceri T, Squarcina L, Giubergia A, et al. Review on deep learning fetal brain segmentation from Magnetic Resonance images[J]. Artif Intell Med, 2023,143:102608.
[12] Mazher M, Qayyum A, Puig D, et al. Effective Approaches to Fetal Brain Segmentation in MRI and Gestational Age Estimation by Utilizing a Multiview Deep Inception Residual Network and Radiomics[J]. Entropy (Basel), 2022,24(12).
[13] Ghelich Oghli M, Shabanzadeh A, Moradi S, et al. Automatic fetal biometry prediction using a novel deep convolutional network architecture[J]. Phys Med, 2021,88:127-137.
[14] Men Q, Zhao H, Drukker L, et al. ScanAhead: Simplifying standard plane acquisition of fetal head ultrasound[J]. Med Image Anal, 2025,104:103614.
[15] Sivasubramanian A, Sasidharan D, Sowmya V, et al. Efficient feature extraction using light-weight CNN attention-based deep learning architectures for ultrasound fetal plane classification [J]. Phys Eng Sci Med, 2025,48(3):1079-1093.
[16] Chen X, He M, Dan T, et al. Automatic Measurements of Fetal Lateral Ventricles in 2D Ultrasound Images Using Deep Learning[J]. Front Neurol, 2020,11:526.
[17] Ishola A, Asaleye C M, Ayoola O O, et al. Reference Ranges of Fetal Cerebral Lateral Ventricle Parameters by Ultrasonography [J]. Rev Bras Ginecol Obstet, 2016,38 (9): 428-435.
[18] Gofer S, Haik O, Bardin R, et al. Machine Learning Algorithms for Classification of First-Trimester Fetal Brain Ultrasound Images[J]. J Ultrasound Med, 2022,41(7):1773-1779.
[19] Sun L, Yu J, Yao J, et al. A novel artificial intelligence model for measuring fetal intracranial markers during the first trimester based on two-dimensional ultrasound image[J]. Int J Gynaecol Obstet, 2024,167(3):1090-1100.
[20] Xie B, Lei T, Wang N, et al. Computer-aided diagnosis for fetal brain ultrasound images using deep convolutional neural networks [J]. Int J Comput Assist Radiol Surg, 2020,15(8): 1303-1312.
[21] Volpe N, Ghi T. Assessing the fetal lateral ventricles at first-trimester ultrasound may predict open spina bifida: a response [J]. Am J Obstet Gynecol MFM, 2025,7(4):101627.
[22] Group E W. Role of prenatal magnetic resonance imaging in fetuses with isolated mild or moderate ventriculomegaly in the era of neurosonography: international multicenter study[J]. Ultrasound Obstet Gynecol, 2020,56(3):340-347.
[23] Benkarim O, Piella G, Rekik I, et al. A novel approach to multiple anatomical shape analysis: Application to fetal ventriculomegaly [J]. Med Image Anal, 2020,64:101750.
[24] Xie H N, Wang N, He M, et al. Using deep-learning algorithms to classify fetal brain ultrasound images as normal or abnormal [J]. Ultrasound Obstet Gynecol, 2020,56(4):579-587.
[25] Napolitano R, Molloholli M, Donadono V, et al. International standards for fetal brain structures based on serial ultrasound measurements from Fetal Growth Longitudinal Study of INTERGROWTH-21(st) Project[J]. Ultrasound Obstet Gynecol, 2020,56(3):359-370.
[26] Hu W, Zhan X, Lu D, et al. Is choroid plexus growth altered in isolated ventriculomegaly on fetal neuro-ultrasound?[J]. Eur Radiol, 2025,35(1):463-473.
[27] Prasad S, Di Fabrizio C, Eltaweel N, et al. First-trimester choroid-plexus-to-lateral-ventricle disproportion and prediction of subsequent ventriculomegaly[J]. Ultrasound Obstet Gynecol, 2023,62(2):234-240.
[28] Labrosse K B, Buechel J, Guelmez H, et al. Presentation of ventriculomegaly at 11-14 weeks of gestation: An analysis of longitudinal data[J]. Prenat Diagn, 2023,43(7):910-918.
[29] Drukker L. Real-time identification of fetal anomalies on ultrasound using artificial intelligence: what's next?[J]. Ultrasound Obstet Gynecol, 2022,59(3):285-287.
[30] Laskin M D, Kingdom J, Toi A, et al. Perinatal and neurodevelopmental outcome with isolated fetal ventriculomegaly: a systematic review[J]. J Matern Fetal Neonatal Med, 2005,18(5):289-298.
[31] Wang L, Fatemi M, Alizad A. Artificial intelligence in fetal brain imaging: Advancements, challenges, and multimodal approaches for biometric and structural analysis[J]. Comput Biol Med, 2025,192(Pt A):110312.
[32] Cater S W, Boyd B K, Ghate S V. Abnormalities of the Fetal Central Nervous System: Prenatal US Diagnosis with Postnatal Correlation[J]. Radiographics, 2020,40(5):1458-1472.
[33] Hadjidekov G, Haynatzki G, Chaveeva P, et al. Concordance between US and MRI Two-Dimensional Measurement and Volumetric Segmentation in Fetal Ventriculomegaly[J]. Diagnostics (Basel), 2023,13(6).
[34] Tran C B N, Nedelec P, Weiss D A, et al. Development of Gestational Age-Based Fetal Brain and Intracranial Volume Reference Norms Using Deep Learning[J]. AJNR Am J Neuroradiol, 2023,44(1):82-90.
[35] Arechvo A, Lingman G, Thurn L, et al. Fusion imaging in brain structure measurements on a fetus phantom, combining real-time ultrasound with magnetic resonance imaging[J]. Australas J Ultrasound Med, 2021,24(3):161-172.
[36] Zhang Y, Yang X, Ji C, et al. Deep Learning Model for Real-Time Nuchal Translucency Assessment at Prenatal US[J]. Radiol Artif Intell, 2025,7(4): e240498.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

