USING ARTIFICIAL INTELLIGENCE IN OBSTETRICS TO DIAGNOSE FETAL MALFORMATIONS AND PREVENT DISEASES
Main Article Content
Abstract
The purpose of the work – studying the possibilities of using artificial intelligence in obstetrics to diagnose fetal malformations and prevent the occurrence of various diseases.
Materials and methods of work. The search for scientific information was conducted using domestic and foreign Internet resources of Google Scholar, PubMed, Medscape, Scopus and Web of Science databases, etc., as well as on the web pages of international medical organizations. as well as on the web pages of international medical organizations using certain keywords: artificial intelligence, use of artificial intelligence in obstetrics and gynecology, diagnosis of fetal malformations, prevention of gynecological diseases, ultrasound in obstetrics and gynecology, trimesters of pregnancy, telemedicine in obstetrics and gynecology The depth of the search was 10 years.
Results. The effectiveness of using artificial intelligence and various algorithms based on it to improve the analysis of two-dimensional (2D) and three-dimensional (3D) ultrasound images of fetal structures, assessment of organ function and diagnosis of diseases was proved. The advantages of the application of artificial intelligence in ultrasound in obstetrics, as well as the disadvantages and prospects of its use are determined.
Significant advances in the application of artificial intelligence in obstetrics and gynecology are shown, identifying the need for further research and improvements with respect to achieving universality and improving the effectiveness of many of the models developed. It is indicated that the studies conducted have applied a significant number of mechanisms to overcome the dilemma of limited accuracy, among which the development of ensemble algorithms, the use of ultrasound videos, the incorporation of features in complementary imaging techniques and others have been applied.
It is proved that the development of algorithms for telemedicine fetal ultrasound service can combine a specialized fetal medicine center and a remote obstetric department, which will provide high-quality ultrasound and rapid specialist consultation, as well as significantly reduce family costs and time to get the patient to a hospital facility. In addition, these techniques are shown to be useful in transnational consultations due to the fact that telemedicine and telediagnostic services can significantly increase access to diagnostic obstetric ultrasound in resource-limited settings. Meanwhile, in medical education in obstetrics and gynecology, telemedicine and virtual reality become a new way of simulation-based ultrasound training, which significantly improves learning efficiency and knowledge retention during training.
Conclusion. Thus, the use of artificial intelligence in fetal ultrasound in different trimesters of pregnancy helps clinicians in the diagnosis of various conditions and diseases, as it can increase efficiency, reduce the number of misdiagnoses and missed diagnoses, effectively improve the quality of medical services and, finally, benefit patients.
Downloads
Article Details
Issue
Section
References
Abinader R, Warsof SL. Benefits and pitfalls of ultrasound in obstetrics and gynecology. Obstet Gynecol Clin North Am. 2019; 46: 367. doi: 10.1016/j.ogc.2019.01.011
Ondeck CL, Pretorius D, McCaulley J, Kinori M, Maloney T, Hull A, Robbins SL. Ultrasonographic prenatal imaging of fetal ocular and orbital abnormalities. Surv Ophthalmol. 2018; 63: 745–53. doi: 10.1016/j.survophthal.2018.04.006
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: 633-641. doi: 10.1016/j.ajog.2017.07.025
Pramanik M, Gupta M, Krishnan KB Enhancing reproducibility of ultrasonic measurements by new users, Proc. SPIE 8673, Medical Imaging 2013: Image Perception, Observer Performance, and Technology Assessment, 86730Q (28 March 2013). doi: 10.1117/12.2008032
Carneiro G, Georgescu B, Good S. Knowledge-Based Automated Fetal Biometrics Using Syngo Auto OB. Erlangen: Siemens Medical Solutions (2008)
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: 847-850. doi: 10.7863/ultra.32.5.847
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. doi: 10.2196/14286
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: 770-776. doi: 10.1002/pd.3900
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: 180-193. doi: 10.1109/TMI.2018.2858779
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. doi: 10.1088/1361-6560/ab3ad1
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: B412-416. doi: 10.1002/uog.7737
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. doi: 10.1016/j.ultrasmedbio.2016.08.034
Sobhaninia Z, Rafiei S, Emami A, Karimi N, Najarian K, Samavi S, Soroushmehr SMR. Fetal ultrasound image segmentation for measuring biometric parameters using multi-task deep learning. Annu Int Conf IEEE Eng Med Biol Soc. 2019; 2019: 6545-6548. doi: 10.1109/EMBC.2019.8856981
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: 773-785. doi: 10.1016/j.ultrasmedbio.2018.09.015
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. doi: 10.1371/journal.pone.0200412
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. doi: 10.1016/j.cmpb.2020.105519
Yang X, Li HM, Liu L, Ni D. Scale-aware auto-context-guided Fetal US segmentation with structured random forests. BIO Integr. 2020; 1: 118-129. doi: 10.15212/bioi-2020-0016
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
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. doi: 10.1002/uog.22171
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: 874-885. doi: 10.1109/JBHI.2017.2705031
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: 642-647. doi: 10.1002/uog.10104
Caetano AC, Zamarian AC, Araujo JE, 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: 1397-1405. doi: 10.7863/ultra.34.8.1397
Namburete AIL, Stebbing RV, Kemp B, Yaqub M, Papageorghiou AT, Noble AJ. Learning-based prediction of gestational age from ultrasound images of the fetal brain. Med Image Anal. 2015; 21: 72-86. doi: 10.1016/j.media.2014.12.006
Grandjean GA, 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: 709-716. doi: 10.1016/j.diii.2018.08.001
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: 1303-1312. doi: 10.1007/s11548-020-02182-3
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: 1512-1520. doi: 10.1109/JBHI.2017.2776116
Chen H, Ni D, Qin J, Li S, Yang X, Wang T, Heng PA. Standard plane localization in fetal ultrasound via domain transferred deep neural networks. IEEE J Biomed Health Inform. 2015; 19: 1627-1636. doi: 10.1109/JBHI.2015.2425041
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: 230-236. doi: 10.1159/000335349
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: 1437-443. doi: 10.7863/ultra.16.06069
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: 1459-1476. doi: 10.1002/jum.14824
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: 882-8891. doi: 10.1038/s41591-021-01342-5
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: 1763-1782. doi: 10.1007/s11517-019-01991-2
Chaoui R, Abuhamad A, Martins J, Heling KS. Recent development in three and four dimension fetal echocardiography. Fetal Diagn Ther. 2020; 47: 345-353. doi: 10.1159/000500454
Bridge CP, Ioannou C, Noble JA. Automated annotation and quantitative description of ultrasound videos of the fetal heart. Med Image Anal. 2017; 36: 147-161. doi: 10.1016/j.media.2016.11.006
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. doi: 10.1016/j.compmedimag.2019.101690
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: 931-942. doi: 10.1109/JBHI.2019.2948316
Barreto EQ, Araujo JE, 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: 1087-1093. doi: 10.3109/14767058.2014.943176
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; 28:1388-1393. doi: 10.3109/14767058.2014.955005
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: 3699-3702. doi: 10.1080/14767058.2018.1484088
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: 579-587. doi: 10.1002/uog.21967
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. doi: 10.3390/biom10121691
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. doi: 10.3390/biom10111526
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: 173-188. doi: 10.1016/j.acra.2019.11.006
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. doi: 10.1186/s12884-020-03532-4
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. doi: 10.1186/s12884-021-03720-w
Ebert J, Tutschek B. Virtual reality objects improve learning efficiency and retention of diagnostic ability in fetal ultrasound. Ultrasound Obstet Gynecol. 2019; 53: 525-528. doi: 10.1002/uog.19177
Popovici R, Pristavu A, Sava A. Three dimensional ultrasound and hdlive technology as possible tools in teaching embryology. Clin Anat. 2017; 30: 953-957. doi: 10.1002/ca.22963