Use of Artificial Intelligence in Fetal Brain Ultrasound Examination: A review

doi:10.26599/AUDT.2026.250061

Abstract

Abstract:

Ultrasound has become the primary modality for fetal central nervous system examination and diagnosing malformations. However, the effectiveness of fetal brain examinations remains highly operator-dependent. Deep learning, a key branch of artificial intelligence (AI), has demonstrated significant advantages in image recognition, proving particularly valuable in medical imaging. Consequently, several studies have proposed the use of deep learning models as tools for fetal brain ultrasound examinations. AI has achieved clinical applications in fetal brain ultrasonography, encompassing standard plane recognition, biometric measurements, structural identification, and malformation diagnosis. This review systematically analyzes the applications of AI in fetal brain ultrasound examination and discusses unmet clinical needs and future development.

Key words: Artificial intelligence; Fetal brain; Obstetric ultrasound; Deep learning

Cui Yuanjie, Guo Cuixia, Li Zhen, Zhang Juan, Wu Yuting, Wu Qingqing, Sun Lijuan. Use of Artificial Intelligence in Fetal Brain Ultrasound Examination: A review. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(2): 90-97.

/ Recommend

Figures/Tables 4

Table 1

Table 2

Table 3

Table 4

References 61

[1]	Koufos K, EI Haloui K, Dianati M, Higgins M, Elmirghani J, Imran MA, et al. Trends in intelligent communication systems: Review of standards, major research projects, and identification of research gaps. Journal of Sensor and Actuator Networks 2021; 104: 60 doi: 10.3390/jsan10040060
[2]	He F, Wang Y, Xiu Y, Zhang Y, Chen L. Artificial intelligence in prenatal ultrasound diagnosis. Frontiers in Medicine 2021; 8: 729978 doi: 10.3389/fmed.2021.729978
[3]	Suzuki K. Overview of deep learning in medical imaging. Radiological Physics and Technology 2017; 10: 257-273. doi: 10.1007/s12194-017-0406-5
[4]	Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Medical Image Analysis 2017; 42: 60-88. doi: 10.1016/j.media.2017.07.005
[5]	Liu S, Wang Y, Yang X, Lei B, Liu L, Li SX, et al. Deep learning in medical ultrasound analysis: a review. Engineering 2019; 52: 261-275.
[6]	Drukker L, Noble J, Papageorghiou A. Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound in Obstetrics & Gynecology 2020; 564: 498-505.
[7]	Shazly SA, Trabuco EC, Ngufor CG, Famuyide AO. Introduction to machine learning in obstetrics and gynecology. Obstetrics & Gynecology 2022; 1394: 669-679.
[8]	Ramirez Zegarra R, Ghi T. Use of artificial intelligence and deep learning in fetal ultrasound imaging. Ultrasound in Obstetrics & Gynecology 2023; 622: 185-194.
[9]	Sreelakshmy R, Titus A, Sasirekha N, Logashanmugam E, Begam RB, Ramkumar G, et al. [Retracted] An automated deep learning model for the cerebellum segmentation from fetal brain images. BioMed Research International 2022; 20221: 8342767 doi: 10.1155/2023/9852080
[10]	Yousefpour Shahrivar R, Karami F, Karami E. Enhancing fetal anomaly detection in ultrasonography images: a review of machine learning-based approaches. Biomimetics 2023; 87: 519 doi: 10.3390/biomimetics8070519
[11]	Salomon L, Alfirevic Z, Berghella V, Bilardo C, Chalouhi G, Costa FDS, et al. ISUOG Practice Guidelines updated): performance of the routine mid-trimester fetal ultrasound scan. Ultrasound in Obstetrics and Gynecology 2022; 596: 840-856.
[12]	Critchley M, Frederiks J, Vinken PJ, Bruyn G. Handbook of clinical neurology: North-Holland 1978.
[13]	Cater SW, Boyd BK, Ghate SV. Abnormalities of the Fetal Central Nervous System: Prenatal US Diagnosis with Postnatal Correlation. Radiographics 2020; 405: 1458-1472. doi: 10.1148/rg.2020200034
[14]	Griffiths PD, Bradburn M, Campbell MJ, Cooper CL, Graham R, Jarvis D, et al. Use of MRI in the diagnosis of fetal brain abnormalities in utero MERIDIAN): a multicentre, prospective cohort study. Lancet 2017; 38910068: 538-546. doi: 10.1097/ogx.0000000000000454
[15]	van Nisselrooij AEL, Teunissen AKK, Clur SA, Rozendaal L, Pajkrt E, Linskens IH, et al. Why are congenital heart defects being missed?. Ultrasound Obstet Gynecol 2020; 556: 747-757.
[16]	Pinto NM, Keenan HT, Minich LL, Puchalski MD, Heywood M, Botto LD. Barriers to prenatal detection of congenital heart disease: a population-based study. Ultrasound Obstet Gynecol 2012; 404: 418-425. doi: 10.1002/uog.10116
[17]	Fadda GM, Capobianco G, Balata A, Litta P, Ambrosini G, D'Antona D, et al. Routine second trimester ultrasound screening for prenatal detection of fetal malformations in Sassari University Hospital, Italy: 23 years of experience in 42,256 pregnancies. Eur J Obstet Gynecol Reprod Biol 2009; 1442: 110-114. doi: 10.1016/j.ejogrb.2009.02.045
[18]	Rydberg C, Tunón K. Detection of fetal abnormalities by second‐trimester ultrasound screening in a non‐selected population. Acta obstetricia et gynecologica Scandinavica 2017; 962: 176-182. doi: 10.1111/aogs.13037
[19]	Zhang Q, Zhang S, Pan Y, Sun L, Li J, Qiao Y, et al. Deep learning to diagnose Hashimoto's thyroiditis from sonographic images. Nat Commun 2022; 131: 3759
[20]	Gao Y, Zeng S, Xu X, Li H, Yao S, Song K, et al. Deep learning-enabled pelvic ultrasound images for accurate diagnosis of ovarian cancer in China: a retrospective, multicentre, diagnostic study. Lancet Digit Health 2022; 43: e179-e187.
[21]	Fiorentino MC, Villani FP, Di Cosmo M, Frontoni E, Moccia S. A review on deep-learning algorithms for fetal ultrasound-image analysis. Med Image Anal 2023; 83: 102629 doi: 10.1016/j.media.2022.102629
[22]	Guo W, Li S, Yu X, Wen H, Yuan Y, Yang X. Artificial intelligence in prenatal ultrasound: clinical application and prospect. Advanced Ultrasound in Diagnosis & Therapy AUDT 2023; 72: 82-90. doi: 10.37015/audt.2023.230024
[23]	Malinger G, Paladini D, Haratz KK, Monteagudo A, Pilu GL, Timor-Tritsch IE. ISUOG Practice Guidelines updated: sonographic examination of the fetal central nervous system. Part 1: performance of screening examination and indications for targeted neurosonography. Ultrasound Obstet Gynecol 2020; 563: 476-484.
[24]	Paladini D, Malinger G, Birnbaum R, Monteagudo A, Pilu G, Salomon LJ, et al. ISUOG Practice Guidelines updated): sonographic examination of the fetal central nervous system. Part 2: performance of targeted neurosonography. Ultrasound Obstet Gynecol 2021; 574: 661-671.
[25]	Zhang B, Liu H, Luo H, Li K. Automatic quality assessment for 2D fetal sonographic standard plane based on multitask learning. Medicine Baltimore 2021; 1004: e24427 doi: 10.1097/md.0000000000024427
[26]	Qu R, Xu G, Ding C, Jia W, Sun M. Standard plane identification in fetal brain ultrasound scans using a differential convolutional neural network. IEEE Access 2020; 8: 83821-83830. doi: 10.1109/ACCESS.2020.2991845
[27]	Cai Y, Droste R, Sharma H, Chatelain P, Drukker L, Papageorghiou AT, et al. Spatio-temporal visual attention modelling of standard biometry plane-finding navigation. Med Image Anal 2020; 65: 101762 doi: 10.1016/j.media.2020.101762
[28]	Xiao S, Zhang J, Zhu Y, Zhang Z, Cao H, Xie M, et al. Application and progress of artificial intelligence in fetal ultrasound. J Clin Med 2023; 129: 3298
[29]	Liang J, Huang R, Kong P, Li S, Wang T, Lei B. SPRNet: Automatic fetal standard plane recognition network for ultrasound images. International Workshop on Preterm, Perinatal and Paediatric Image Analysis 2019; Proceedings: 38-46.
[30]	Kong P, Ni D, Chen S, Li S, Wang T, Lei B. Automatic and efficient standard plane recognition in fetal ultrasound images via multi-scale dense networks. International Workshop on Preterm, Perinatal and Paediatric Image Analysis; 2018; Proceedings: 160-168.
[31]	Lin Z, Li S, Ni D, Liao Y, Wen H, Du J, et al. Multi-task learning for quality assessment of fetal head ultrasound images. Med Image Anal 2019; 58: 101548 doi: 10.1016/j.media.2019.101548
[32]	Salomon LJ, Alfirevic Z, Da Silva Costa F, Deter RL, Figueras F, Ghi T, et al. ISUOG Practice Guidelines: ultrasound assessment of fetal biometry and growth. Ultrasound Obstet Gynecol 2019; 536: 715-723. doi: 10.1002/uog.20409
[33]	Foi A, Maggioni M, Pepe A, Rueda S, Noble JA, Papageorghiou AT, et al. Difference of Gaussians revolved along elliptical paths for ultrasound fetal head segmentation. Comput Med Imaging Graph 2014; 388: 774-784. doi: 10.1016/j.compmedimag.2014.09.006
[34]	Sinclair M, Baumgartner CF, Matthew J, Bai W, Martinez JC, Li Y, et al. Human-level performance on automatic head biometrics in fetal ultrasound using fully convolutional neural networks. 2018 40th Annual International Conference of the IEEE Engineering In Medicine And Biology Society EMBC 2018;714-717.
[35]	Zeng Y, Tsui PH, Wu W, Zhou Z, Wu S. Fetal ultrasound image segmentation for automatic head circumference biometry using deeply supervised attention-gated v-net. J Digit Imaging 2021; 341: 134-148. doi: 10.1007/s10278-020-00410-5
[36]	Zhang J, Petitjean C, Ainouz S. Segmentation-based vs. regression-based biomarker estimation: a case study of fetus head circumference assessment from ultrasound images. J Imaging 2022; 8: 23
[37]	van den Heuvel TLA, de Bruijn D, de Korte CL, Ginneken BV. Automated measurement of fetal head circumference using 2D ultrasound images. PLoS One 2018; 138: e0200412 doi: 10.1371/journal.pone.0200412
[38]	Płotka S, Klasa A, Lisowska A, Seliga-Siwecka J, Lipa M, Trzciński T, et al. Deep learning fetal ultrasound video model match human observers in biometric measurements. Phys Med Biol 2022;67.
[39]	Pluym ID, Afshar Y, Holliman K, Kwan L, Bolagani A, Mok T, et al. Accuracy of automated three-dimensional ultrasound imaging technique for fetal head biometry. Ultrasound Obstet Gynecol 2021; 575: 798-803. doi: 10.1002/uog.22171
[40]	Chen X, He M, Dan T, Wang N, Lin M, Zhang L, et al. Automatic measurements of fetal lateral ventricles in 2d ultrasound images using deep learning. Front Neurol 2020; 11: 526 doi: 10.3389/fneur.2020.00526
[41]	Namburete AI, Stebbing RV, Kemp B, Yaqub M, Papageorghiou AT, Alison Noble J. Learning-based prediction of gestational age from ultrasound images of the fetal brain. Med Image Anal 2015; 211: 72-86. doi: 10.1016/j.media.2014.12.006
[42]	Wyburd MK, Hesse LS, Aliasi M, Jenkinson M, Papageorghiou AT, Haak MC, et al. Assessment of regional cortical development through fissure based gestational age estimation in 3D fetal ultrasound. International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging 2021:12959;242-252.
[43]	Yang F, Leung KY, Lee YP, Chan HY, Tang MH. Fetal biometry by an inexperienced operator using two- and three-dimensional ultrasound. Ultrasound Obstet Gynecol 2010; 355: 566-571.
[44]	Welp A, Gembicki M, Rody A, Weichert J. Validation of a semiautomated volumetric approach for fetal neurosonography using 5DCNS+ in clinical data from > 1100 consecutive pregnancies. Childs Nerv Syst 2020; 3612: 2989-2995. doi: 10.1007/s00381-020-04607-5
[45]	Gembicki M, Welp A, Scharf JL, Dracopoulos C, Weichert J. A clinical approach to semiautomated three-dimensional fetal brain biometry-comparing the strengths and weaknesses of two diagnostic tools: 5DCNS+TM and SonoCNSTM. J Clin Med 2023; 12: 5334 doi: 10.3390/jcm12165334
[46]	Weichert J, Scharf JL. Advancements in artificial intelligence for fetal neurosonography: a comprehensive review. J Clin Med 2024; 13: 5626 doi: 10.3390/jcm13185626
[47]	Wyburd MK, Jenkinson M, Namburete AI. Cortical plate segmentation using CNNs in 3D fetal ultrasound. Annual Conference on Medical Image Understanding and Analysis 2020; 1248: 56-68. doi: 10.1007/978-3-030-52791-4_5
[48]	Venturini L, Papageorghiou AT, Noble JA, Namburete AI. Multi-task CNN for structural semantic segmentation in 3D fetal brain ultrasound. Medical Image Understanding and Analysis 2020; 1065: 164-173. doi: 10.1007/978-3-030-39343-4_14
[49]	Wu Y, Shen K, Chen Z, Wu J, editors. Automatic measurement of fetal cavum septum pellucidum from ultrasound images using deep attention network. 2020 IEEE International Conference on image processing ICIP 2020:2511-2515.
[50]	Wang S, Hua Y, Cao Y, Song T, Xue Z, Gong X, et al., editors. Deep learning based fetal middle cerebral artery segmentation in large-scale ultrasound images. 2018 IEEE International Conference on Bioinformatics and Biomedicine BIBM 2018:532-539.
[51]	Xie B, Lei T, Wang N, Cai H, Xian J, He M, et al. Computer-aided diagnosis for fetal brain ultrasound images using deep convolutional neural networks. Int J Comput Assist Radiol Surg 2020; 158: 1303-1312.
[52]	Xie HN, Wang N, He M, Zhang LH, Cai HM, Xian JB, et al. Using deep-learning algorithms to classify fetal brain ultrasound images as normal or abnormal. Ultrasound Obstet Gynecol 2020; 564: 579-587. doi: 10.1002/uog.21967
[53]	Lin M, He X, Guo H, He M, Zhang L, Xian J, et al. Use of real-time artificial intelligence in detection of abnormal image patterns in standard sonographic reference planes in screening for fetal intracranial malformations. Ultrasound Obstet Gynecol 2022; 593: 304-316.
[54]	Lin M, Zhou Q, Lei T, Shang N, Zheng Q, He X, et al. Deep learning system improved detection efficacy of fetal intracranial malformations in a randomized controlled trial. NPJ Digit Med 2023; 61: 191 doi: 10.1038/s41746-023-00932-6
[55]	Shirsat KP, Gawade S, Chopade S, Gujare RV, Bhandwalkar R. Fetal brain anomaly detection via ultrasound imaging using traditional and separable cnns with xception. Journal of Neonatal Surgery 2025; 1422S: 804-813.
[56]	Olsen MDS, Ambsdorf J, Lin M, Taksøe-Vester C, Svendsen MBS, Christensen AN, et al. Unsupervised detection of fetal brain anomalies using denoising diffusion models. International Workshop on Advances in Simplifying Medical Ultrasound 2024; 15186: 209-219. doi: 10.1007/978-3-031-73647-6_20
[57]	Mykula H, Gasser L, Lobmaier S, Schnabel JA, Zimmer V, Bercea CI. Diffusion models for unsupervised anomaly detection in fetal brain ultrasound. International Workshop on Advances in Simplifying Medical Ultrasound 2024; 15186: 220-230.
[58]	D'Alberti E, Patey O, Smith C, Šalović B, Hernandez-Cruz N, Noble JA, et al. Artificial intelligence-enabled prenatal ultrasound for the detection of fetal cardiac abnormalities: a systematic review and meta-analysis. EClinicalMedicine 2025; 84: 103250 doi: 10.1016/j.eclinm.2025.103250
[59]	Day T, Matthew J, Budd S, Venturini L, Wright R, Farruggia A, et al. Interaction between clinicians and artificial intelligence to detect fetal atrioventricular septal defects on ultrasound: how can we optimize collaborative performance?. Ultrasound in Obstetrics & Gynecology 2024; 641: 28-35.
[60]	Codaccioni C, Arthuis C, Deloison B, Bault JP, Henry C, Mahallati H, et al. Offline ultrasound–MRI fusion imaging for assessment of normal fetal brain development. Ultrasound in Obstetrics & Gynecology 2025; 664: 509-517. doi: 10.1002/uog.29312
[61]	Salomon LJ, Bernard J-P, Millischer A-E, Sonigo P, Brunelle F, Boddaert N, et al. MRI and ultrasound fusion imaging for prenatal diagnosis. American Journal of Obstetrics and Gynecology 2013; 2092: 148 doi: 10.1097/01.ruq.0000450896.78339.b9

Paper	Model architecture	Plane	Dataset size	Performance metrics (For fetal brain)
FASP, fetal abdomen standard plane; FFSP, fetal facial standard plane; FFASP, fetal face axial standard plane; 4CH, four chamber view; FBSP, fetal brain standard plane; FFESP, fetal femur standard plane; CNN, convolutional neural network; 2D, two-dimensional ultrasound; ACC, accuracy; Rec, recall; Sen, sensitivity; Spe, specificity
Zhang 2021	Feature Extraction Network, Region Proposal Network and Class Prediction Network	FASP, FBSP, 4CH	3280 2D	Prec = 0.95, Sen = 0.92, ACC = 0.95
Qu 2020	differential-CNN	FBSPs	19142 2D	Prec = 0.93, Rec = 0.92, ACC = 0.93
Cai 2020	Temporal SonoEyeNet (TSEN)	FBSP, FASP, FFESP	280 Videos	Vecsim = 0.98, Pre = 0.89, Rec = 0.85
Kong 2018	multi-scale dense networks (MSDNet)	FBSP, FASP, 4CH, FFSPs	22715 2D	Pre = 1.00, Rec = 1.00
Liang 2019	SPRNet	4CH, FASP, FBSP, FFASP, coronal FFSP	22295 2D	ACC = 0.99, Sen = 0.99, Spe = 0.99
Lin 2019	MF R-CNN	FBSP	1771 2D	ACC = 0.93, Prec = 0.89 Sen = 0.96

Paper	Model architecture	Biometry	Dataset size	Performance metrics
DSC, dice similarity coefficient; MSD, maximum symmetric contour distance; MAE, mean absolute error; ATC, average time consumed; RMSE, root-mean-squared error; SF, sylvian fissure; POF, parieto-occipital fissure; CLC, calcarine sulcus; HC, head circumference; BPD, biparietal diameter; AC, abdominal circumference; FL, femur length; TCD, transcerebellar diameter; CM, cisterna magna; Vp, posterior horn of the lateral ventricle; CNN, convolutional neural network; GA, gestation age; 2D, two-dimensional ultrasound; 3D, three-dimensional ultrasound.
Foi 2014	Difference of Gaussians revolved along Elliptical paths	BPD, HC, OFD	90 2D	DSC = 0.98, MSD = 2.3 mm
Sinclair 2018	Fully Convolutional Networks (FCN)	HC, BPD	HC18	DSC = 0.98
Zeng 2021	DAG) V-Net	HC	HC18	DSC = 0.98, MAE = 1.77 mm
Zhang 2022	Regression CNN Model, CNN Segmentation Model	HC	HC18	MAE = 1.08 mm (Segmentation) vs. 1.83 mm (Regression)
van den Heuvel 2018	Random Forest Classifier, Hough transform, Dynamic Programming, Ellipse fit	HC	1334 2D	DSC = 0.97, MAE = 2.8 mm
Płotka 2022	U-Net	BPD, HC, AC, Fl	750 videos	DSC = 0.96, MAE = 1.04, (HC), 0.27 (BPD)
Pluym 2021	SonoCNS	BPD, HC, TCD, CM, Vp	143 women	ICC of the automated approach compared to the manual measurements for BPD (0.81), HC (0.88), TCD (0.50), CM (0.23), Vp (0.26)
Chen 2020	Mask R-CNN	lateral ventricles	2900 2D	MAE = 1.8 mm, ATC = 0.13 s
Namburete 2015	Regression forest	GA	635 3D	RMSE = 6.10 days, r = 0.98
Wyburd 2021	CNN	SF, POF, CLC	811 3D	MAE = 4.1 (SF), 5.1 (POF), 4.9 (CLC)

Paper	Model architecture	Plane/Structure	Dataset size	Performance metrics
MSP, midsagittal plane; TT, transthalamic plane; TV, transventricular plane; TC, transcerebellar plane; TFc, transfrontal plane (coronal); TCaudc, transcaudate plane (coronal); TTc, transthalamic plane (coronal); TCc, transcerebellar plane (coronal); PSP, parasagittal plane; 3D, three-dimensional ultrasound; 2D, two-dimensional ultrasound; CSP, cavum septi pellucidi; MCA, middle cerebral artery; HC, head circumference
Welp 2020	5DCNS+	MSP, TT, TV, TC, TFc, TCaudc, TTc, TCc, PSP	1019 3D	999/1019 (98%) of the volumes, ≥ 8 planes were sufficiently visualized, 958/1019 (94%) all nine planes were sufficiently visualized
Wyburd 2020	U-Net	cortical plate	307 fetuses	DSC = 0.82
Venturini 2019	DAG V-Net	HC	528 3D	DSC= 0.81 (thalamus), 0.82 (brainstem), 0.77 (cerebellum), 0.92 (white matter)
Wu 2020	U-Net	CSP	448 2D	DSC = 0.77, Pre = 0.79
Wang 2018	MCANet	MCA	4005 2D	DSC = 0.77

Paper	Model architecture	Malformation	Dataset size	Performance metrics
IOU, intersection over union; 2D, two-dimensional; ACC, accuracy; Sen, sensitivity; Spe, specificity; DSC, dice similarity coefficient; AUPRC, area under precision-recall curve; AUROC, area under ROC curve
Xie 2020	CNN	Ventriculomegaly, hydrocephalus, Blake pouch cyst, Dandy–Walker malformations, cerebellar vermis hypoplasia	54990 2D	DSC = 0.942 (craniocerebral region segmentation), average F1-score=0.96 on classification, average mean IOU of 0.497 on lesion localization
Xie 2020	CNN	Binary classification as normal or abnormal	29419 2D	ACC = 0.96, Sen = 0.97, Spe = 0.96, AUC = 0.99
Lin 2022	PAICS	Normal and 9 intracranial malformations	43890 2D, 169 Video	Macro- and microaverage AUC = 0.93 and 0.98 (e internal validation image dataset), 0.90 and 0.90 (e external validation image dataset), 0.97 and 0.98 (real-time scan setting
Shirsat 2025	CNN	Normal and 15 intracranial malformations	1786 2D	ACC = 0.54 (Standard CNN), 0.63 (Separable CNN), 0.88 (Xception); Prec = 0.54 (Standard CNN), 0.56 (Separable CNN), 0.89 (Xception)
Olsen 2024	DDPM-iNAAD	Intracranial malformations	14760 2D	AUROC: 0.62 (Gaussian), 0.58 (Simplex), 0.57 (Pyramid)
Mykula 2024	DDPM	Intracranial malformations	252 2D	AUPRC = 0.79 (AnoDDPM with Simplex) and 0.80 (AutoDDPM with Gaussian)