Fetal sonography is a cornerstone of prenatal care, enabling noninvasive monitoring of fetal growth and early detection of congenital anomalies. Despite its clinical value, its effectiveness can be limited by operator dependency, subjective interpretation, and variability in image quality. To address these issues, researchers have suggested using deep learning (DL) models as a maneuver to assist sonographers.
Materials and Methods:
A search of the current literature was conducted using PubMed, IEEE Xplore, SpringerLink, and Scopus, to create a targeted and current review on the use of DL in obstetric sonography. These platforms are renowned for their high-quality, peer-reviewed publications in both medical imaging and artificial intelligence. The timeframe is selected between 2019 and May 2025, which aligned with the period that DL experienced rapid expansion, into clinical applications.
Results:
The systematic review found that DL has numerous therapeutic uses in prenatal imaging, including classifying aberrant and normal anatomy and measuring fetal biometry. This review consolidated recent developments in the application of DL such as classification, segmentation, and automation in obstetric processes.
Conclusion:
Deep learning has a great potential to guide future diagnostic directions for sonographers, clinicians, and researchers involved in fetal sonography.
DavidALSpencerRN: Clinical assessment of fetal well-being and fetal safety indicators. J Clin Pharmacol2022;62(S1):S67–S78. doi:10.1002/jcph.2126.
2.
BaschatAAGalanHLLeeW, et al: The role of the fetal biophysical profile in the management of fetal growth restriction. Am J Obstet Gynecol2022;226(4):475–486. doi:10.1016/j.ajog.2022.01.020.
3.
DrukkerLNobleJAPapageorghiouAT: Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol2020;56(4):498–505. doi:10.1002/uog.22122.
4.
RamkumarGSrinivasanRKarthikeyanN, et al: IoT-based patient monitoring system for predicting heart disease using deep learning. Measurement2023;218:113235. doi:10.1016/j.measurement.2023.113235.
5.
AlharbiMAlzahraniAAlqahtaniA, et al: Plant disease classification based on ConvLSTM U-net with fully connected convolutional layers. Trait Signal2023;40(1):157–166. doi:10.18280/ts.400114.
6.
HeFWangYXiuYZhangYChenL: Artificial intelligence in prenatal ultrasound diagnosis. Front Med (Lausanne)2021;8:729978. doi:10.3389/fmed.2021.729978.
7.
YazdiBZankerPWagnerP, et al: Optimal caliper placement: manual vs automated methods. Ultrasound Obstet Gynecol2014;43(2):170–175. doi:10.1002/uog.12509.
8.
RajendranSKhalafOIAlotaibiYAlghamdiS: MapReduce-based big data classification model using feature subset selection and hyperparameter tuned deep belief network. Sci Rep2021;11(1):24138. doi:10.1038/s41598-021-03019-y.
9.
SakaiAKomatsuMKomatsuR, et al: Medical professional enhancement using explainable artificial intelligence in fetal cardiac ultrasound screening. Biomedicines2022;10(3):551. doi:10.3390/biomedicines10030551.
10.
AbdullahMAbrhaFBKedirBTagesseTT: A hybrid deep learning CNN model for COVID-19 detection from chest X-rays. Heliyon2024;10(5):e26938. doi:10.1016/j.heliyon.2024.e26938.
11.
AbdullahMKedirBAlemayehuKAHabtemariumHT: A single-objective GA and PSO for multimodal palmprint recognition. Math Probl Eng2023;2023:7621550. doi:10.1155/2023/7621550.
12.
BakkerMKBergmanJEHKrikovS, et al: Prenatal diagnosis and prevalence of critical congenital heart defects. BMJ Open2019;9:e028139. doi:10.1136/bmjopen-2018-028139.
13.
van NisselrooijAELTeunissenAKKClurSA, et al: Why arecongenital heart defects being missed?Ultrasound Obstet Gynecol2020;55(6):747–757. doi:10.1002/uog.20358.
14.
MengLZhaoDYangZWangB: Automatic fetal brain plane display and measurements using 3D ultrasound. J Clin Ultrasound2020;48(2):82–88. doi:10.1002/jcu.22762.
15.
SarrisIIoannouCChamberlainP, et al: Intra- and interobserver variability in fetal ultrasound measurements. Ultrasound Obstet Gynecol2012;39(3):266–273. doi:10.1002/uog.10082.
16.
DrukkerL: Real-time identification of fetal anomalies using artificial intelligence. Ultrasound Obstet Gynecol2022;59(3):285–287. doi:10.1002/uog.24869.
17.
SinclairMBaumgartnerCFMatthewJet al: Human-level performance on automatic head biometrics in fetal ultrasound. Annu Int Conf IEEE Eng Med Biol Soc2018;2018:714–717. doi:10.1109/EMBC.2018.8512278.
18.
RasheedKJunejoFMalikASaqibM: Automated fetal head classification and segmentation using ultrasound video. IEEE Access2021;9:160249–160267. doi:10.1109/ACCESS.2021.3131518.
19.
ZhuFLiuMWangF, et al: Automatic measurement of fetal femur length using machine learning. Math Biosci Eng2021;18(6):7790–7805. doi:10.3934/mbe.2021387.
20.
BanoSDromeyBVasconcelosF, et al: AutoFB: automating fetal biometry estimation, in de BruijneMCattinPCCotinSPadoyNSpeidelSZhengYEssertC, (eds): Medical Image Computing and Computer-Assisted Intervention -MICCAI 2021. Cham: Springer; 2021, pp 228–238. doi:10.48550/arXiv.2107.05255.
21.
PłotkaSWłodarczykTKlasaA, et al: FetalNet: multi-task deep learning framework, in MantoroTLeeMAyuMAWongKWHidayantoAN, (eds): Neural Information Processing—ICONIP 2021. Cham: Springer; 2021, pp 257–265. doi:10.48550/arXiv.2107.06943.
22.
Ghelich OghliMShabanzadehAMoradiS, et al: Automatic fetal biometry prediction using deep CNNs. Phys Med2021;88:127–137. doi:10.1016/j.ejmp.2021.06.020.
23.
LiJWangYLeiB, et al: Automatic fetal head circumference measurement. IEEE J Biomed Health Inform2018;22(1):215–223. doi:10.1109/JBHI.2017.2703890.
24.
RameshJBacherVEidMC, et al: Automated fetal biometry with deep ensembles. arXiv2025. doi:10.48550/arXiv.2505.14572.
25.
Burgos-ArtizzuXPCoronado-GutiérrezDValenzuela-AlcarazB, et al: Evaluation of deep CNNs for fetal ultrasound plane classification. Sci Rep2020;10:10200. doi:10.1038/s41598-020-67076-5.
26.
SalomonLJAlfirevicZBerghellaV, et al: ISUOG Practice Guidelines: mid-trimester fetal ultrasound scan. Ultrasound Obstet Gynecol2022;59(6):840–856. doi:10.1002/uog.24888.
27.
BilardoCMChaouiRHyettJA, et al: ISUOG Practice Guidelines: 11–14-week ultrasound scan. Ultrasound Obstet Gynecol2023;61(1):127–143. doi:10.1002/uog.26106.
28.
CarvalhoJSAxt-FliednerRChaouiR, et al: ISUOG Practice Guidelines: fetal cardiac screening. Ultrasound Obstet Gynecol2023;61(6):788–803. doi:10.1002/uog.26224.
29.
ChenHNiDQinJ, et al: Standard plane localization via domain-transferred deep networks. IEEE J Biomed Health Inform2015;19(5):1627–1636. doi:10.1109/JBHI.2015.2425041.
30.
LiaoHBaloccoSWangG, et al: Machine learning and medical engineering for cardiovascular health and intravascular imaging and computer assisted stenting. Paper presented at the Proceedings of the CVII-STENT; October2019; Shenzhen, China.
31.
PatraANobleJA: Multi-anatomy localization in fetal echocardiography videos. Paper presented at the Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI);April 2019; Venice, Italy. doi:10.1109/ISBI.2019.8759551.
XuLLiuMZhangJHeY: CNN-based segmentation of apical four-chamber view. IEEE Access2020;8:80437–80446. doi:10.1109/ACCESS.2020.2984630.
34.
NurmainiSRachmatullahMNSapitriAI, et al: Deep learning-based fetal echocardiography for CHD detection. Sensors2021;21(23):8007. doi:10.3390/s21238007.
35.
DozenAKomatsuMSakaiA, et al: Ventricular septum segmentation using time-series DL. Biomolecules2020;10(11):1526. doi:10.3390/biom10111526.
36.
ArnaoutRCurranLZhaoY, et al: Expert-level prenatal detection of complex CHD. Nat Med2021;27:882–891. doi:10.1038/s41591-021-01342-5.
37.
MebergA: Outcome of congenital heart defects. Acta Paediatr2000;89:1344–1351. doi:10.1080/080352500300002552.
38.
BonnetDColtriAButeraG, et al: Detection of TGA reduces neonatal mortality. Circulation1999;99:916–918. doi:10.1161/01.cir.99.7.916.
39.
TworetzkyWMcElhinneyDBReddyVM, et al: Improved outcome after fetal diagnosis of HLHS. Circulation2001;103:1269–1273. doi:10.1161/01.cir.103.9.1269.
40.
SimpsonLL: Screening for congenital heart disease. Obstet Gynecol Clin North Am2004;31:51–59. doi:10.1016/j.ogc.2003.12.001.
41.
QiaoSPangSLuoG, et al: RLDS: An explainable residual learning diagnosis system for fetal congenital heart disease. Future Gener Comput Syst2022;128:205–218. doi:10.1016/j.future.2021.10.001.
42.
GongYZhangYZhuH, et al: DGACNN-based fetal CHD screening. IEEE Trans Med Imaging2020;39(4):1206–1222. doi:10.1109/TMI.2019.2946059.
43.
KomatsuMSakaiAKomatsuR, et al: Detection of cardiac abnormalities using DL. Appl Sci2021;11(1):371. doi:10.3390/app11010371.
44.
TanJAuAMengQ, et al: Automated CHD detection, in HuYLicandroRNobleJAHutterJMelbourneAAylwardSTurkEATorrents BarrenaJ, (eds): Lecture Notes in Computer Science. Cham: Springer; 2020, pp 243–252. doi:10.1007/978-3-030-60334-2_24.
45.
NurmainiSRachmatullahMNSapitriAI, et al: Accurate detection of septal defects with fetal ultrasonography images using deep learning-based multiclass instance segmentation. IEEE Access2020;8:196160–196174. doi:10.1109/ACCESS.2020.3034367.
46.
BuddSSinclairMDayT, et al: Detecting hypo-plastic left heart syndrome in fetal ultrasound via disease-specific atlas maps, in de BruijneMCattinPCCotinSPadoyNSpeidelSZhengYEssertC, (eds): International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing; 2021, pp 207–217. doi:10.48550/arXiv.2107.02643.
47.
MalingerGPaladiniDHaratzKK, et al: ISUOG CNS guidelines. Ultrasound Obstet Gynecol2020;56:476–484. doi:10.1002/uog.22145.
48.
CaiYDrosteRSharmaH, et al: Spatio-temporal attention for plane navigation. Med Image Anal2020;65:101762. doi:10.1016/j.media.2020.101762.
49.
MeijerinkLWyburdMNambureteAIL, et al: Deep learning assessment of fetal brain maturation on 3D ultrasound volumes in early-onset fetal growth restriction. Ultrasound in Obstetrics & Gynecology 2026. doi:10.1002/uog.70168.
50.
LeeLHBradburnEPapageorghiouATNobleJA: Calibrated Bayesian neural networks to estimate gestational age and its uncertainty on fetal brain ultrasound images, in HuYNobleJAMelbourneA, (eds): International Workshop on Advances in Simplifying Medical Ultrasound. Cham: Springer International Publishing; 2020, pp 13–22. doi:10.1007/978-3-030-60334-2_2.
51.
XieHNWangNHeM, et al: Using deep-learning algorithms to classify fetal brain ultrasound images as normal or abnormal. Ultrasound Obstet Gynecol2020;56(4):579–587. doi:10.1002/uog.21967.
52.
XieBLeiTWangN, et al: CAD for fetal brain ultrasound. Int J Comput Assist Radiol Surg2020;15:1303–1312. doi:10.1007/s11548-020-02182-3.
53.
DuránJMJongsmaKR: Trust in medical AI. J Med Ethics2021;47:329–335. doi:10.1136/medethics-2020-106820.
54.
BinsonVAThomasSSubramoniamMArunJNaveenSMadhuS: A review of machine learning algorithms for biomedical applications. Ann Biomed Eng2024;52(5):1159–1183. doi:10.1007/s10439-024-03459-3.
55.
ChenLTianYDengY: NN-based 3D ultrasound for spina bifida diagnosis. Sci Program2021;2021:3605739. doi:10.1155/2021/3605739.
56.
SinghTKudavellySRVenkataSK: Deep learning based fetal face detection and visualization in prenatal ultrasound. Paper presented at the IEEE 18th International Symposium on Biomedical Imaging (ISBI);April 2021; Nice, France. doi:10.1109/ISBI48211.2021.9433915.
57.
YuZNiDChenS, et al: Fetal facial plane recognition. Paper presented at the Proceedings of the IEEE Engineering in Medicine and Biology Society (EMBS);October 2016; Orlando, FL. doi:10.1109/EMBC.2016.7590780.
58.
VazeSNambureteAIL: Segmentation of fetal adipose tissue, in LinguraruMGBaustMZhouSK, (eds): Lecture Notes in Computer Science (LNCS). Cham: Springer; 2018, pp 55–65. doi:10.1007/978-3-030-00807-9_6.
59.
HermawatiFATjandrasaHSuciatiN: Phase-based segmentation of fetal thigh. J King Saud Univ Comput Inf Sci2022;34:4448–4460. doi:10.1016/j.jksuci.2021.02.004.
60.
YinJLiJHuangQ, et al: DL segmentation of fetal lung. J Biosci Med2021;9(1):146–153. doi:10.4236/jbm.2021.91012.
61.
QaziMAAlamMTAlmakkyI, et al: Multi-task biometric estimation, in AlamMTAlmakkyIAwaisMMahmoodT, (eds): MICAD 2023. Cham: Springer; 2023, pp 52–61. doi:10.1007/978-981-97-1335-6_5.
62.
YanLLingSMaoRXiHWangF: DL framework for three-vessel view segmentation. Biomed Eng Online2024;23:39. doi:10.1186/s12938-024-01230-2.
63.
TianYUcurumEHanX, et al: Diffusion models for fetal plane classification. arXiv2025:2501.15248. doi:10.48550/arXiv.2501.15248.
64.
VenturiniLBuddSFarruggiaA, et al: Whole-exam AI fetal biometrics. NPJ Digit Med2025;8:22. doi:10.1038/s41746-024-01406-z.
65.
Sendra-BacellsMCampelloVMTorrents-BarrenaJ, et al: Generalisability of fetal ultrasound DL models. Sci Rep2023;13(1):2728. doi:10.1038/s41598-023-29490-3.
66.
Burgos-ArtizzuXPCoronado-GutiérrezDValenzuela-AlcarazB, et al: FETAL_PLANES_DB Dataset. Zenodo: Switzerland; 2020. doi:10.1038/s41598-020-67076-5.
67.
van den HeuvelTLAde BruijnDde KorteCL, et al: Automated fetal head circumference. PLoS ONE2018;13:e0200416. doi:10.1371/journal.pone.0200412.
68.
MaaniFSaeedNSaleemT, et al: FetalCLIP foundation model. arXiv2025:2502.14807. doi:10.48550/arXiv.2502.14807.
69.
CabezasMDiezYMartinez-DiagoCMarotoA: Benchmark for 2D fetal brain ultrasound. Sci Data2024;11:923. doi:10.1038/s41597-024-03774-3.
70.
FiorentinoMCMocciaSCosmoMDFrontoniEGiovanolaBTiribelliS: Uncovering ethical biases in publicly available fetal ultrasound datasets. NPJ Digit Med2025;8(1):355. doi:10.1038/s41746-025-01739-3.
71.
DayTGKainzBHajnalJRazaviRSimpsonJM: AI and fetal echocardiography. Prenat Diagn2021;41(6):733–742. doi:10.1002/pd.5892.
72.
DeepaJRamyaDRishabKS, et al: Swin transformer based COVID-19 identification and its severity quantification, in SugumaranDPalSLeD-NZamanN, (eds): Recent Trends in Computational Intelligence and Its Application. Boca Raton, FL: CRC Press; 2023, pp 304–312.
73.
JauniauxECollinsSBurtonGJ: Placenta accreta spectrum. Am J Obstet Gynecol2018;218(1):75–87.
74.
ContinoSCruciataLGambinoOPirroneR: IOD for deep learning in DICOM. Comput Methods Programs Biomed2024;248:108113. doi:10.1016/j.cmpb.2024.108113.
75.
ZechJRBadgeleyBLiuC, et al: MOMO for DICOM study routing. NPJ Digit Med2022;5:113.
European Medicines Agency: Medical Device Regulation. Amsterdam, The Netherlands, European Medicines Agency, 2022.
81.
International Electrotechnical Commission: IEC 62304: Medical Device Software. Geneva, Switzerland, International Electrotechnical Commission, 2015.
82.
SalcedoEMDPapageorghiouATKhandwalaS, et al: AI in obstetric ultrasound. Ultrasound Obstet Gynecol2022;60(3):339–350.
83.
NobleJHWangYWangQ, et al: AI in medical ultrasound. NPJ Digit Med2024;7:128. doi:10.1038/s41746-024-01328-w.
84.
DaumNBlaivasMGoudieAHoffmannBJenssenCNeubauerRReckerFMogaTVZervidesCDietrichCF: AI in ultrasound education. Ultrasound J2024;16:1–13. doi:10.1186/s13089-024-00382-5.
85.
SeeKSWCheungLPTanHHS: AI-enhanced ultrasound education. J Med Imaging Health Inform2024;14(3):642–650. doi:10.1166/jmihi.2024.4412.
86.
American Registry for Diagnostic Medical Sonography: AI and Ultrasound Education. Rockville, MD, American Registry for Diagnostic Medical Sonography, 2024.
87.
LeeCHNgAH: The good, bad, and ugly of AI in imaging. Eur Med J Radiol2024;9(1):45–52. doi:10.33590/emjradiol/JTPO7801.
88.
KhosraviRKGhasemiFAlizadehS, et al: Bias in AI for medical imaging. Diagn Interv Radiol2024;30(1):14–26. doi:10.4274/dir.2024.242854.
89.
RunkleJSuggMBoaseDGalvinSLCoulsonC: Use of wearable sensors for pregnancy health and environmental monitoring: descriptive findings from the perspective of patients and providers. Digit Health2019;5:2055207619828220. doi:10.1177/2055207619828220.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
