Possibilities of using neural network analysis in ultrasound diagnostics of congenital malformations of the fetus in the second trimester of pregnancy

Aim. The aim of the study is to evaluate the diagnostic possibilities of using artificial intelligence in ultrasound diagnostics for detecting congenital malformations of the central nervous system, cardiovascular system and abdominal organs of the fetus in the second trimester of pregnancy.

Materials and Methods. In the course of work to evaluate the possibilities of using artificial intelligence in prenatal ultrasound diagnostics in the detection of congenital malformations of various systems and organs, an ultrasound examination of 371 patients was performed in the second trimester of pregnancy. The materials were collected, images were processed, the main anatomical structures were graphically highlighted, the neural network model was «trained» to «recognize» anatomical landmarks and form an instrumental diagnosis of the type «norm» and «not norm».

Results. 1484 echograms were obtained and graphically isolated with visualization of fetal brain structures in axial section, heart in a four-chamber section and vessels in a three-vessel section, as well as abdominal organs in a transversely abdominal section. The neural network model was «trained» using ultrasound images with a normal anatomical structure of these areas of structures, as well as with pathologically altered ultrasound images.

Conclusion. The use of artificial intelligence in modern prenatal ultrasound diagnostics in the detection of congenital malformations of the fetus in the second trimester of pregnancy can make it possible to form an instrumental diagnosis of the type «normal» and «not normal» with sufficiently high accuracy.

1. Burlutskaya A. V., Statova A. V., Mamyan E. V. Structure and organisation of palliative care for children in Krasnodar Krai. Kuban Scientific Medical Bulletin. 2020;27(2):29-37. (In Russ.). https://doi.org/10.25207/1608-6228-2020-27-2-2937

2. Gumenyuk E. G., Ivshin A. A., Boldina Yu. S. Search for predictors of fetal growth retardation: from centimeter tape to artificial intelligence. Obstetrics and gynecology. 2022;12:18-24. (In Russ.). https://dx.doi.org/10.18565/aig.2022.185

3. Zhdanova E. V., Rubtsova E. V. Implementing an Artificial Intelligence System in the Work of General Practitioner in the Yamalo-Nenets Autonomous Okrug: Pilot Cross-sectional Screening Observational Study. Kuban Scientific Medical Bulletin. 2022;29(4):14-31. (In Russ.). https://doi.org/10.25207/1608-6228-2022-29-4-14-31

4. Pomortsev A. V., Redko A. N., Barsukova E. A., Matosyan M. A., Dyachenko Yu. Yu., Dyachenko R. A., Beloglyadova I. A., Yanaeva M. V., Babayan V. T. Use of Artificial Intelligence in Ultrasound Diagnosis of Fetal Central Nervous System Anomalies Between 19 and 22 Weeks’ Gestation. Innovative Medicine of Kuban. 2024;(2):42-47. (In Russ.). https://doi.org/10.35401/2541-9897-2024-9-2-42-47

5. Pomortsev A. V., Karakhalis M. N., Matulevich S. A., Daschyan G. A., Khalafyan A. A., Sencha A. N. Congenital Heart Diseases: Risk Factors and Ultrasound Diagnostic Potential at the First Screening. Innovative Medicine of Kuban. 2023; (4):51-59. (In Russ.). https://doi.org/10.35401/2541-9897-2023-8-4-51-59

6. Carvalho J., Axt-Fliedner R., Chaoui R., Copel J., Cuneo B., Goff D., Gordin Kopylov L., Hecher K., Lee W., MoonGrady A., Mousa H., Munoz H., Paladini D., Prefumo F., Quarello E., Rychik J., Tutschek B., Wiechec M., Yagel S. ISUOG Practice Guidelines (updated): fetal cardiac screening. Ultrasound & Functional Diagnostics. 2024;(1):44-70. (In Russ.). https://doi.org/10.24835/16 07-0771-270

7. Drukker L., Noble J. A., Papageorghiou A. T. Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol. 2020;56(4):498-505. https://doi.org/10.1002/uog.22122

8. Iftikhar P., Kuijpers M. V., Khayyat A., Iftikhar A., DeGouvia De Sa M. Artificial Intelligence: A New Paradigm in Obstetrics and Gynecology Research and Clinical Practice. Cureus. 2020;12(2):e7124. https://doi.org/10.7759/cureus.7124

9. Yi J., Kang H. K., Kwon J. H., Kim K. S., Park M. H., Seong Y. K., Kim D. W., Ahn B., Ha K., Lee J., Hah Z., Bang W. C. Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency. Ultrasonography. 2021;40(1):7-22. https://doi.org/10.14366/usg.2010.