Citation Information :
Spahić L, Kurjak A, Stanojevic M, Badnjević A, Pokvić LG. Trustworthiness of Four-dimensional Ultrasound and Artificial Intelligence in Improving KANET Test for Detection of Fetuses at Neurorisk. Donald School J Ultrasound Obstet Gynecol 2024; 18 (1):6-16.
Background: Fetal neurological impairment disorders, encompassing conditions like cerebral palsy, epilepsy, and autism spectrum disorder, can result from various factors affecting fetal nervous system development. Timely diagnosis of these disorders is challenging but crucial for early intervention. Recent advancements in deep learning and ultrasound technology present an opportunity to develop a tool for early detection.
Objective: This study aims to leverage convolutional neural networks (CNNs) to analyze fetal neurobehavioral movements in ultrasound images, with the goal of aiding in the early detection of neurological impairment disorders.
Materials and methods: The study utilized a dataset of 3D ultrasound images extracted from 4D recordings of fetuses undergoing the Kurjak Antenatal Neurodevelopmental Test (KANET) during the third trimester. The methodology relies on the application of deep learning, more specifically convolutional neural networks (CNN) for the purpose of recognizing characteristic fetal movements.
Results: The custom CNN architecture achieved an overall accuracy of 93.83%. The system was visualized by means of designing a graphical user interface that includes the developed model that works in the background every time a frame of a recorded 4D ultrasound video is deemed to be parsed through the system. Notably, distinguishing between facial and hand-to-face movements proved challenging. This pilot study lays the foundation for AI-based fetal neurological risk assessment, providing a promising tool for the early detection of fetal neurological impairment disorders.
Conclusion: While acknowledging limitations such as class imbalance and the absence of differentiation between specific facial expressions, the study demonstrates the potential of AI in enhancing prenatal care. Future work will involve expanding the dataset, conducting real-time clinical validations, and further refining the model. The research holds implications for improving outcomes for affected children and making advanced diagnostic capabilities accessible in diverse healthcare settings.
Kurjak A, Stanojevic M, Andonotopo W, et al. Fetal neurobehavioral development: from the womb to the world. J Perinat Med 2007;35(5):377–390. DOI: 10.1515/JPM.2007.108
Kurjak A, Stanojevć M, Barišić LS, et al. Kurjak antenatal neurodevelopmental test (KANET): a useful tool for fetal neurodevelopmental assessment. Clinical Management of Infertility: Problems and Solutions. 2021. pp. 271–301.
Kurjak A, Stanojevic M, Azumendi G, et al. The potential of four-dimensional (4D) ultrasonography in the assessment of fetal awareness. J Perinat Med 2005;33(1):46–53. DOI: 10.1515/JPM.2005.008
Tinjić S. Experiences and Results of the KANET Test Application in Clinical Practice in Tuzla, Bosnia and Herzegovina. Donald School J Ultrasound Obstet Gynecol 2019;13(3):94–98. DOI: 10.5005/jp-journals-10009-1595
Kurjak A, Azumendi G, Vecek N, et al. Fetal hand movements and facial expression in normal pregnancy studied by four-dimensional sonography. J Perinat Med 2003;31(6):496–508.
Kurjak A, Azumendi G, Andonotopo W, et al. Three- and four-dimensional ultrasonography for the structural and functional evaluation of the fetal face. Am J Obstet Gynecol 2007;196(1):16–28. DOI: 10.1016/j.ajog.2006.06.090
Kurjak A, Badreldeen A, Azumendi G, et al. Can we improve the assessment of fetal behavior in early pregnancy? Int J Gynecol Obstet 2005;88(3):307–313.
Kurjak A, Pooh RK, Merce LT, et al. Structural and functional early human development assessed by three-dimensional and four-dimensional sonography. Fetal Diagnos Ther 2005;20(6):496–508. DOI: 10.1159/000088164
Kurjak A, Chervenak FA. Donald School Textbook of Ultrasound in Obstetrics and Gynecology, 4th edition. Jaypee Brothers Medical Publishers; 2017.
Kurjak A, Stanojevic M, Andonotopo W, et al. How useful is 4D sonography in perinatal medicine? J Perinat Med 2006;34(5):437–450. DOI: 10.1515/JPM.2006.087
Spahić L, Mašetić Z, Badnjević A, et al. Artificial intelligence-based ultrasound imaging classification for infant neurological impairment disorders: a review. Mediterranean Conference on Medical and Biological Engineering and Computing. Switzerland; Cham: Springer Nature. 2023. pp. 620–627.
Liu F, Zhou Z, Samsonov A, et al. Deep learning approach for evaluating knee MR images: achieving high diagnostic performance for cartilage lesion detection. Radiology 2018;289(1):160–169. DOI: 10.1148/radiol.2018172986
Yazdani A, Costa S, Kroon B. Artificial intelligence: friend or foe? Aust N Z J Obstet Gynaecol 2023;63(2):127–130. DOI: 10.1111/ajo.13661
Nu S, Bhokal R. Study of artificial neural network. Int J Math Trends Technol 2017;47:253–259. DOI: 10.14445/22315373/IJMTT-V47P535
Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2017;2(4):230–243. DOI: 10.1136/svn-2017-000101
Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med 2019;25(1):24–29. DOI: 10.1038/s41591-018-0316-z
Badnjević A, Pokvić LG, Spahić L. Inspection of medical devices. Clinical Engineering Handbook. Academic Press. 2020. pp. 491–497.
Badnjević A, Pokvić LG, Spahić L. Pediatric and neonate incubators. Clinical Engineering Handbook; Academic Press. 2020. pp. 514–519.
Badnjević A, Pokvić LG, Deumić A, et al. Post-market surveillance of medical devices: A review. Technol Health Care 2022;30(6):1315–1329. DOI: 10.3233/THC-220284
Badnjević A, Gurbeta L, Bošković D, et al. Measurement in medicine–Past, present, future. Folia Medica 2015;50(1):43–46.
Gurbeta L, Badnjević A, Žunić E, et al. (2015, October). Software package for tracking status of inspection dates and reports of medical devices in healthcare institutions of Bosnia and Herzegovina. In 2015 XXV International Conference on Information, Communication and Automation Technologies (ICAT) (pp. 1–5). IEEE.
Gurbeta L, Badnjevic A, Dzemic Z, et al. (2016, October). Testing of therapeutic ultrasound in healthcare institutions in Bosnia and Herzegovina. In 2nd EAI International Conference on Future Access Enablers of Ubiquitous and Intelligent Infrastructures (pp. 24–25).
Gurbeta L, Dzemic Z, Bego T, Sejdic E & Badnjevic A. Testing of anesthesia machines and defibrillators in healthcare institutions. Journal of Medical Systems, 2017;41:1–10. DOI: 10.1007/s10916-017-0783-7
Gurbeta L, Izetbegović S, Badnjević-Čengić A. Inspection and testing of pediatric and neonate incubators. Inspection of Medical Devices. 2018. pp. 221–249.
Gurbeta L, Badnjević A. Inspection process of medical devices in healthcare institutions: software solution. Health Technol 2017;7(1):109–117. DOI: 10.1007/s12553-016-0154-2
Badnjević A, Avdihodžić H, Gurbeta Pokvić L. Artificial intelligence in medical devices: past, present and future. Psychiatr Danub 2021;33(suppl 3):S336–S341.
Hadžić L, Fazlić A, Hasanić O, et al. Expert system for performance prediction of anesthesia machines. CMBEBIH 2019: Proceedings of the International Conference on Medical and Biological Engineering. 16–18 May 2019, Banja Luka, Bosnia and Herzegovina. Springer International Publishing. 2020. pp. 671–679.
Hrvat F, Spahić L, Aleta A. (2023) Heart disease prediction using logistic regression machine learning model. Joint conference of the Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON) and the International Conference on Medical and Biological Engineering in Bosnia and Herzegovina (CMBEBIH) (September 2023)
Kovačević Ž, Gurbeta Pokvić L, Spahić L, et al. Prediction of medical device performance using machine learning techniques: infant incubator case study. Health Technol 2020;10(1):151–155. DOI: 10.1007/s12553-019-00386-5
Spahić L, Kurta E, Ćordić S, et al. Machine learning techniques for performance prediction of medical devices: infant incubators. In CMBEBIH 2019: Proceedings of the International Conference on Medical and Biological Engineering, 16–18 May 2019, Banja Luka, Bosnia and Herzegovina. Springer International Publishing. 2020. pp. 483–490.
Šećkanović A, Šehovac M, Spahić L, et al. (2020, June). Review of artificial intelligence application in cardiology. In 2020 9th Mediterranean Conference on Embedded Computing (MECO) (pp. 1–5). IEEE.
Spahić L, Softić A, Durak-Nalbantić A, et al. (2023, September). Integrating Machine learning in clinical decision support for heart failure diagnosis: case study. Mediterranean Conference on Medical and Biological Engineering and Computing. Switzerland. Cham: Springer Nature. 2023. pp. 696–705.
Hrvat, F., Spahić, L., Aleta, A. (2023) Heart disease prediction using logistic regression machine learning model. Joint conference of the Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON) and the International Conference on Medical and Biological Engineering in Bosnia and Herzegovina (CMBEBIH) (September 2023)
Kawamoto K, Houlihan CA, Balas EA, et al. Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success. BMJ 2005;330(7494):765. DOI: 10.1136/bmj.38398.500764.8F
Osheroff JA, Teich JM, Middleton B, et al. A roadmap for national action on clinical decision support. J Am Med Inform Assoc 2007;14(2):141–145. DOI: 10.1197/jamia.M2334
Ammenwerth E, Rigby M, Talmon J. Evidence-Based Health Informatics: Promoting Safety and Efficiency Through Scientific Methods and Ethical Policy. IOS Press. 2018.
