Artificial Intelligence in Obstetric Ultrasound: An Update and Future Applications

Zhiyi Chen, Zhenyu Liu, Meng Du, Ziyao Wang, Zhiyi Chen, Zhenyu Liu, Meng Du, Ziyao Wang

Abstract

Artificial intelligence (AI) can support clinical decisions and provide quality assurance for images. Although ultrasonography is commonly used in the field of obstetrics and gynecology, the use of AI is still in a stage of infancy. Nevertheless, in repetitive ultrasound examinations, such as those involving automatic positioning and identification of fetal structures, prediction of gestational age (GA), and real-time image quality assurance, AI has great potential. To realize its application, it is necessary to promote interdisciplinary communication between AI developers and sonographers. In this review, we outlined the benefits of AI technology in obstetric ultrasound diagnosis by optimizing image acquisition, quantification, segmentation, and location identification, which can be helpful for obstetric ultrasound diagnosis in different periods of pregnancy.

Keywords: artificial intelligence; automatic measurement; classification; obstetric ultrasound; segmentation; ultrasound telemedicine.

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Copyright © 2021 Chen, Liu, Du and Wang.

Figures

Figure 1
Figure 1
AI in measurement of NT thickness (12, 13). (a) Original image, (b) after histogram equalization, (c–e) detection results of different methods (directional edge image, SRAD edge image, and KAD edge image), (f) binary the direction edge image.
Figure 2
Figure 2
Optimization of fetal facial 3D ultrasound imaging. (A) Facial occlusion with umbilical cord, (B) elimination of facial occlusion, (C) facial edge incomplete reconstruction, (D) facial imaging optimization.

References

    1. Abinader R, Warsof SL. Benefits and pitfalls of ultrasound in obstetrics and gynecology. Obstetr Gynecol Clin North Am. (2019). 46:367. 10.1016/j.ogc.2019.01.011
    1. Ondeck CL, Pretorius D, McCaulley J, Kinori M, Maloney T, Hull A, et al. . Ultrasonographic prenatal imaging of fetal ocular and orbital abnormalities. Surv Ophthalmol. (2018) 63:745–53. 10.1016/j.survophthal.2018.04.006
    1. Bellussi F, Ghi T, Youssef A, Salsi G, Giorgetta F, Parma D, et al. . The use of intrapartum ultrasound to diagnose malpositions and cephalic malpresentations. Am J Obstet Gynecol. (2017) 217:633–41. 10.1016/j.ajog.2017.07.025
    1. Pramanik M, Gupta M, Krishnan KB. Enhancing reproducibility of ultrasonic measurements by new users. In: Abbey CK, Mello-Thoms CR, editors. Medical Imaging 2013: Image Perception, Observer Performance, and Technology Assessment, Vol. 8673. Bellingham, WA: SPIE; (2013).
    1. Carneiro G, Georgescu B, Good S. Knowledge-Based Automated Fetal Biometrics Using Syngo Auto OB. Erlangen: Siemens Medical Solutions; (2008).
    1. Espinoza J, Good S, Russell E, Lee W. Does the use of automated fetal biometry improve clinical work flow efficiency? J Ultrasound Med. (2013) 32:847–50. 10.7863/ultra.32.5.847
    1. Dhombres F, Maurice P, Guilbaud L, Franchinard L, Dias B, Charlet J, et al. . A novel intelligent scan assistant system for early pregnancy diagnosis by ultrasound: clinical decision support system evaluation study. J Med Internet Res. (2019) 21:e14286. 10.2196/14286
    1. Liu C, Jiao D, Liu Z. Artificial intelligence (AI)-aided disease prediction. BIO Integr. (2020) 1:130–6. 10.15212/bioi-2020-0017
    1. Smeets NA, Dvinskikh NA, Winkens B, Oei SG. A new semi-automated method for fetal volume measurements with three-dimensional ultrasound: preliminary results. Prenat Diagn. (2012) 32:770–6. 10.1002/pd.3900
    1. Yang X, Yu L, Li S, Wen H, Luo D, Bian C, et al. . Towards automated semantic segmentation in prenatal volumetric ultrasound. IEEE Trans Med Imaging. (2019) 38:180–93. 10.1109/TMI.2018.2858779
    1. Ryou H, Yaqub M, Cavallaro A, Papageorghiou AT, Alison Noble J. Automated 3D ultrasound image analysis for first trimester assessment of fetal health. Phys Med Biol. (2019) 64:185010. 10.1088/1361-6560/ab3ad1
    1. Moratalla J, Pintoffl K, Minekawa R, Lachmann R, Wright D, Nicolaides KH. Semi-automated system for measurement of nuchal translucency thickness. Ultrasound Obstet Gynecol. (2010). 36:B412–6. 10.1002/uog.7737
    1. Nie S, Yu J, Chen P, Wang Y, Zhang JQ. Automatic detection of standard sagittal plane in the first trimester of pregnancy using 3-D ultrasound data. Ultrasound Med Biol. (2017) 43:286–300. 10.1016/j.ultrasmedbio.2016.08.034
    1. Sobhaninia Z, Rafiei S, Emami A, Karimi N, Najarian K, Samavi S, et al. . Fetal ultrasound image segmentation for measuring biometric parameters using multi-task deep learning. Annu Int Conf IEEE Eng Med Biol Soc. (2019) 2019:6545–8. 10.1109/EMBC.2019.8856981
    1. van den Heuvel TLA, Petros H, Santini S, de Korte CL, van Ginneken B. Automated fetal head detection and circumference estimation from free-hand ultrasound sweeps using deep learning in resource-limited countries. Ultrasound Med Biol. (2019) 45:773–85. 10.1016/j.ultrasmedbio.2018.09.015
    1. 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) 13:e0200412. 10.1371/journal.pone.0200412
    1. Yang X, Wang X, Wang Y, Dou H, Li S, Wen H, et al. . Hybrid attention for automatic segmentation of whole fetal head in prenatal ultrasound volumes. Comput Methods Programs Biomed. (2020) 194:105519. 10.1016/j.cmpb.2020.105519
    1. Yang X, Li HM, Liu L, Ni D. Scale-aware auto-context-guided Fetal US segmentation with structured random forests. BIO Integr. (2020) 1:118–29. 10.15212/bioi-2020-0016
    1. 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. 10.3389/fneur.2020.00526
    1. Pluym ID, Afshar Y, Holliman K, Kwan L. Accuracy of three-dimensional automated ultrasound imaging of biometric measurements of the fetal brain. Ultrasound Obstetr Gynecol. (2020) 57:798–803. 10.1002/uog.22171
    1. Yu Z, Tan EL Ni D, Qin J, Chen S, Li S, et al. . A deep convolutional neural network based framework for automatic fetal facial standard plane recognition. IEEE J Biomed Health Inform. (2018) 22:874–85. 10.1109/JBHI.2017.2705031
    1. Yu Z, Ni D, Chen S, Li S, Wang T, Lei B. Fetal facial standard plane recognition via very deep convolutional networks. Conf Proc IEEE Eng Med Biol Soc. (2016) 2016:627–30. 10.1109/EMBC.2016.7590780
    1. Tsai PY, Chen HC, Huang HH, Chang CH, Fan PS, Huang CI, et al. . A new automatic algorithm to extract craniofacial measurements from fetal three-dimensional volumes. Ultrasound Obstet Gynecol. (2012) 39:642–7. 10.1002/uog.10104
    1. Caetano AC, Zamarian AC, Araujo Júnior E, Cavalcante RO, Simioni C, Silva CP, et al. . Assessment of intracranial structure volumes in fetuses with growth restriction by 3-dimensional sonography using the extended imaging virtual organ computer-aided analysis method. J Ultrasound Med. (2015) 34:1397–405. 10.7863/ultra.34.8.1397
    1. 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) 21:72–86. 10.1016/j.media.2014.12.006
    1. Akhilraj V., Gadagkar K.S., Shreedhara. Features based IUGR diagnosis using variational level set method and classification using artificial neural networks. Fifth International Conference on Signal and Image Processing. Chennai: IEEE Computer Society; (2014).
    1. Ambroise Grandjean G, Hossu G, Bertholdt C, Noble P, Morel O, Grangé G. Artificial intelligence assistance for fetal head biometry: assessment of automated measurement software. Diagn Interv Imaging. (2018) 99:709–16. 10.1016/j.diii.2018.08.001
    1. 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) 15:1303–12. 10.1007/s11548-020-02182-3
    1. Jang J, Park Y, Kim B, Lee SM, Kwon JY, Seo JK. Automatic estimation of fetal abdominal circumference from ultrasound images. IEEE J Biomed Health Inform. (2018) 22:1512–20. 10.1109/JBHI.2017.2776116
    1. Chen H, Ni D, Qin J, Li S, Yang X, Wang T, et al. . Standard plane localization in fetal ultrasound via domain transferred deep neural networks. IEEE J Biomed Health Inform. (2015) 19:1627–36. 10.1109/JBHI.2015.2425041
    1. Cobo T, Bonet-Carne E, Martínez-Terrón M, Perez-Moreno A, Elías N, Luque J, et al. . Feasibility and reproducibility of fetal lung texture analysis by automatic quantitative ultrasound analysis and correlation with gestational age. Fetal Diagn Ther. (2012) 31:230–6. 10.1159/000335349
    1. Palacio M, Cobo T, Martínez-Terrón M, Rattá GA, Bonet-Carné E, Amat-Roldán I, et al. . Performance of an automatic quantitative ultrasound analysis of the fetal lung to predict fetal lung maturity. Am J Obstet Gynecol. (2012). 207:504.e1–5. 10.1016/j.ajog.2012.09.027
    1. Ghorayeb SR, Bracero LA, Blitz MJ, Rahman Z, Lesser ML. Quantitative ultrasound texture analysis for differentiating preterm from term fetal lungs. J Ultrasound Med. (2017) 36:1437–43. 10.7863/ultra.16.06069
    1. Bonet-Carne E, Palacio M, Cobo T, Perez-Moreno A, Lopez M, Piraquive JP, et al. . Quantitative ultrasound texture analysis of fetal lungs to predict neonatal respiratory morbidity. Ultrasound Obstet Gynecol. (2015) 45:427–33. 10.1002/uog.13441
    1. Perez-Moreno A, Dominguez M, Migliorelli F, Gratacos E, Palacio M, Bonet-Carne E. Clinical feasibility of quantitative ultrasound texture analysis: a robustness study using fetal lung ultrasound images. J Ultrasound Med. (2019) 38:1459–76. 10.1002/jum.14824
    1. Arnaout R, Curran L, Zhao Y, Levine JC, Chinn E, Moon-Grady AJ. An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart disease. Nat Med. (2021) 27:882–91. 10.1038/s41591-021-01342-5
    1. Femina M, Raajagopalan S. Anatomical structure segmentation from early fetal ultrasound sequences using global pollination CAT swarm optimizer–based Chan-Vese model. Med Biol Eng Comput. (2019) 57:1763–82. 10.1007/s11517-019-01991-2
    1. Chaoui R, Abuhamad A, Martins J, Heling KS. Recent development in three and four dimension fetal echocardiography. Fetal Diagn Ther. (2020) 47:345–53. 10.1159/000500454
    1. Bridge CP, Ioannou C, Noble JA. Automated annotation and quantitative description of ultrasound videos of the fetal heart. Med Image Anal. (2017) 36:147–61. 10.1016/j.media.2016.11.006
    1. Xu L, Liu M, Shen Z, Wang H, Liu X, Wang X, et al. . DW-Net: a cascaded convolutional neural network for apical four-chamber view segmentation in fetal echocardiography. Comput Med Imaging Graph. (2020) 80:101690. 10.1016/j.compmedimag.2019.101690
    1. Dong J, Liu S, Liao Y, Wen H, Lei B, Li S, et al. . A generic quality control framework for fetal ultrasound cardiac four-chamber planes. IEEE J Biomed Health Inform. (2020) 24:931–42. 10.1109/JBHI.2019.2948316
    1. Barros FS, Rolo LC, Rocha LA, Martins WP, Nardozza LM, Moron AF, et al. . Reference ranges for the volumes of fetal cardiac ventricular walls by three-dimensional ultrasound using spatiotemporal image correlation and virtual organ computer-aided analysis and its validation in fetuses with congenital heart diseases. Prenat Diagn. (2015) 35:65–73. 10.1002/pd.4480
    1. Barreto EQ, Araujo Júnior E, Martins WP, Rolo LC, Milani HJ, Nardozza LM, et al. . New technique for assessing fetal heart growth using three-dimensional ultrasonography: description of the technique and reference curves. J Matern Fetal Neonatal Med. (2015). 28:1087–93. 10.3109/14767058.2014.943176
    1. Rolo LC, Santana EF, da Silva PH, Costa Fda S, Nardozza LM, Tonni G, et al. . Fetal cardiac interventricular septum: volume assessment by 3D/4D ultrasound using spatio-temporal image correlation (STIC) and virtual organ computer-aided analysis (VOCAL). J Matern Fetal Neonatal Med. (2015) 28:1388–93. 10.3109/14767058.2014.955005
    1. Yeo L, Markush D, Romero R. Prenatal diagnosis of tetralogy of Fallot with pulmonary atresia using: Fetal Intelligent Navigation Echocardiography (FINE). J Matern Fetal Neonatal Med. (2019) 32:3699–702. 10.1080/14767058.2018.1484088
    1. Baños N, Perez-Moreno A, Migliorelli F, Triginer L, Cobo T, Bonet-Carne E, et al. . Quantitative analysis of the cervical texture by ultrasound and correlation with gestational age. Fetal Diagn Ther. (2017) 41:265–72. 10.1159/000448475
    1. Baños N, Perez-Moreno A, Julià C, Murillo-Bravo C, Coronado D, Gratacós E, et al. . Quantitative analysis of cervical texture by ultrasound in mid-pregnancy and association with spontaneous preterm birth. Ultrasound Obstet Gynecol. (2018) 51:637–43. 10.1002/uog.17525
    1. Bahado-Singh RO, Sonek J, McKenna D, Cool D, Aydas B, Turkoglu O, et al. . Artificial intelligence and amniotic fluid multiomics: prediction of perinatal outcome in asymptomatic women with short cervix. Ultrasound Obstet Gynecol. (2019) 54:110–8. 10.1002/uog.20168
    1. Miyagi Y, Miyake T. Potential of artificial intelligence for estimating Japanese fetal weights. Acta Med Okayama. (2020) 74:483–93. 10.18926/AMO/61207
    1. Fung R, Villar J, Dashti A, Ismail LC, Staines-Urias E, Ohuma EO, et al. . Achieving accurate estimates of fetal gestational age and personalised predictions of fetal growth based on data from an international prospective cohort study: a population-based machine learning study. Lancet Digit Health. (2020) 2:e368–75. 10.1016/S2589-7500(20)30131-X
    1. 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) 56:579–87. 10.1002/uog.21967
    1. Shozu K, Komatsu M, Sakai A, Komatsu R, Dozen A, Machino H, et al. . Model-agnostic method for thoracic wall segmentation in fetal ultrasound videos. Biomolecules. (2020) 10:1691. 10.3390/biom10121691
    1. Dozen A, Komatsu M, Sakai A, Komatsu R, Shozu K, Machino H, et al. . Image segmentation of the ventricular septum in fetal cardiac ultrasound videos based on deep learning using time-series information. Biomolecules. (2020) 10:1526. 10.3390/biom10111526
    1. Torrents-Barrena J, Monill N, Piella G, Gratacós E, Eixarch E, Ceresa M, et al. . Assessment of radiomics and deep learning for the segmentation of fetal and maternal anatomy in magnetic resonance imaging and ultrasound. Acad Radiol. (2021) 28:173–88. 10.1016/j.acra.2019.11.006
    1. Smith VJ, Marshall A, Lie MLS, Bidmead E, Beckwith B, Van Oudgaarden E, et al. . Implementation of a fetal ultrasound telemedicine service: women's views and family costs. BMC Pregnancy Childbirth. (2021) 21:38. 10.1186/s12884-020-03532-4
    1. Toscano M, Marini TJ, Drennan K, Baran TM, Kan J, Garra B, et al. . Testing telediagnostic obstetric ultrasound in Peru: a new horizon in expanding access to prenatal ultrasound. BMC Pregnancy Childbirth. (2021) 21:328. 10.1186/s12884-021-03720-w
    1. Ebert J, Tutschek B. Virtual reality objects improve learning efficiency and retention of diagnostic ability in fetal ultrasound. Ultrasound Obstet Gynecol. (2019) 53:525–8. 10.1002/uog.19177
    1. Popovici R, Pristavu A, Sava A. Three dimensional ultrasound and hdlive technology as possible tools in teaching embryology. Clin Anat. (2017) 30:953–7. 10.1002/ca.22963

Source: PubMed

Sponsors et collaborateurs

Les conditions médicales

Interventions en matière de drogue

3
S'abonner