Zusammenfassung
Die pränatale Detektionsrate von fetalen Herzfehlern ist trotz Auflage nationaler und internationaler Screeningprogramme niedrig geblieben. Die Entdeckungsraten im Niedrigrisikokollektiv reichen von 22,5–52,8 %. Erfolgversprechende Ansätze hin zu verbesserten Detektionsraten könnten automatisierte Anwendungen der künstlichen Intelligenz (KI) darstellen. Bezug nehmend auf neuartige und bereits etablierte KI-Lösungen aus der Erwachsenenkardiologie sollen in dieser Übersicht die Möglichkeiten und Limitierungen von KI-Algorithmen für die fetale Echokardiographie diskutiert werden.
Abstract
The prenatal detection rates of fetal heart defects have remained low despite the implementation of national and international screening programs. The detection rates in the low-risk population range from 22.5% to 52.8%. Promising approaches for improved detection rates could include automated applications of artificial intelligence (AI). With reference to novel and already established AI solutions from adult cardiology, this review discusses the possibilities and limitations of AI algorithms for fetal echocardiography.
Literatur
Kuhn S, Heusel-Weiss M, Kadioglu D, Michl S (2019) Digitale Transformation der Medizin – Die Zukunft aktiv gestalten. Dtsch Arztebl 116(17):A830–834
Thomford NE, Bope CD, Agamah FE et al (2020) Implementing artificial intelligence and digital health in resource-limited settings? Top 10 lessons we learned in congenital heart defects and cardiology. OMICS 24(5):264–277
Obermeyer Z, Emanuel EJ (2016) Predicting the future – big data, machine learning, and clinical medicine. N Engl J Med 375(13):1216–1219
McKinney SM, Sieniek M, Godbole V et al (2020) International evaluation of an AI system for breast cancer screening. Nature 577(7788):89–94
Ou WC, Polat D, Dogan BE (2021) Deep learning in breast radiology: current progress and future directions. Eur Radiol 31(7):4872–4885
Day TG, Kainz B, Hajnal J, Razavi R, Simpson JM (2021) Artificial intelligence, fetal echocardiography, and congenital heart disease. Prenat Diagn 41:733–742
Zhou J, Du M, Chang S, Chen Z (2021) Artificial intelligence in echocardiography: detection, functional evaluation, and disease diagnosis. Cardiovasc Ultrasound 19(1):29
Knackstedt C, Bekkers SC, Schummers G et al (2015) Fully automated versus standard tracking of left ventricular ejection fraction and longitudinal strain: the FAST-EFs multicenter study. J Am Coll Cardiol 66(13):1456–1466
Tsang W, Salgo IS, Medvedofsky D et al (2016) Transthoracic 3D echocardiographic left heart chamber quantification using an automated adaptive analytics algorithm. JACC Cardiovasc Imaging 9(7):769–782
Yeo L, Romero R (2020) New and advanced features of fetal intelligent navigation echocardiography (FINE) or 5D heart. J Matern Fetal Neonatal Med. https://doi.org/10.1080/14767058.2020.1759538
Garcia-Canadilla P, Sanchez-Martinez S, Crispi F, Bijnens B (2020) Machine learning in fetal cardiology: what to expect. Fetal Diagn Ther 47(5):363–372
Johnson KW, Torres Soto J, Glicksberg BS et al (2018) Artificial intelligence in cardiology. J Am Coll Cardiol 71(23):2668–2679
Hinton GE (2007) To recognize shapes, first learn to generate images. Prog Brain Res 165:535–547
Kusunose K (2021) Steps to use artificial intelligence in echocardiography. J Echocardiogr 19(1):21–27
Yoon YE, Kim S, Chang HJ (2021) Artificial intelligence and echocardiography. J Cardiovasc Imaging 29(3):193–204
Yu L, Guo Y, Wang Y, Yu J, Chen P (2017) Segmentation of fetal left ventricle in echocardiographic sequences based on dynamic convolutional neural networks. IEEE Trans Biomed Eng 64(8):1886–1895
Xu L, Liu M, Shen Z et al (2020) DW-Net: a cascaded convolutional neural network for apical four-chamber view segmentation in fetal echocardiography. Comput Med Imaging Graph 80:101690
Zhang J, Gajjala S, Agrawal P et al (2018) Fully automated echocardiogram interpretation in clinical practice. Circulation 138(16):1623–1635
Arnaout R, Curran L, Zhao Y, Levine JC, Chinn E, Moon-Grady AJ (2020) Expert-level prenatal detection of complex congenital heart disease from screening ultrasound using deep learning (medRxiv)
Le TK, Truong V, Nguyen-Vo TH (2020) Application of machine learning in screening of congenital heart diseases using fetal echo-cardiography. J Am Coll Cardiol 75(11):648
Dozen A, Komatsu M, Sakai A et al (2020) Image segmentation of the ventricular septum in fetal cardiac ultrasound videos based on deep learning using time-series information. Biomolecules 10(11):1526. https://doi.org/10.3390/biom10111526
Dong J, Liu S, Liao Y et al (2020) A generic quality control framework for fetal ultrasound cardiac four-chamber planes. IEEE J Biomed Health Inform 24(4):931–942
Nagendran M, Chen Y, Lovejoy CA et al (2020) Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ 368:m689
Lee CS, Lee AY (2020) How artificial intelligence can transform randomized controlled trials. Transl Vis Sci Technol 9(2):9
Kim YH (2021) Artificial intelligence in medical ultrasonography: driving on an unpaved road. Ultrasonography 40(3):313–317
Patra A, Noble JA (2020) Hierarchical class incremental learning of anatomical structures in fetal echocardiography videos. IEEE J Biomed Health Inform 24(4):1046–1058
Huang W, Bridge CP, Noble JA, Zisserman A (2017) Temporal heartnet: towards human-level automatic analysis of fetal cardiac screening video
Sharma H, Drukker L, Chatelain P, Droste R, Papageorghiou AT, Noble JA (2021) Knowledge representation and learning of operator clinical workflow from full-length routine fetal ultrasound scan videos. Med Image Anal 69:101973
Droste R, Drukker L, Papageorghiou AT, Noble JA (2020) Automatic probe movement guidance for freehand obstetric ultrasound. Med Image Comput Comput Assist Interv 12263:583–592
Alsharid M, Sharma H, Drukker L, Chatelain P, Papageorghiou AT, Noble JA (2019) Captioning ultrasound images automatically (Paper presented at: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019)
Cai Y, Droste R, Sharma H et al (2020) Spatio-temporal visual attention modelling of standard biometry plane-finding navigation. Med Image Anal 65:101762
Baumgartner CF, Kamnitsas K, Matthew J et al (2017) SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans Med Imaging 36(11):2204–2215
Yaqub M, Kelly B, Noble JA, Papageorghiou AT (2018) An AI system to support sonologists during fetal ultrasound anomaly screening. Ultrasound Obstet Gynecol 52(S1):9–10
Yaqub M, Sleep N, Syme S et al (2021) ScanNav® audit: an AI-powered screening assistant for fetal anatomical ultrasound. Am J Obstet Gynecol 224(Suppl):312
Yeo L, Romero R (2013) Fetal intelligent navigation echocardiography (FINE): a novel method for rapid, simple, and automatic examination of the fetal heart. Ultrasound Obstet Gynecol 42(3):268–284
Yeo L, Luewan S, Romero R (2018) Fetal intelligent navigation echocardiography (FINE) detects 98 % of congenital heart disease. J Ultrasound Med 37(11):2577–2593
Garcia M, Yeo L, Romero R et al (2016) Prospective evaluation of the fetal heart using fetal intelligent navigation echocardiography (FINE). Ultrasound Obstet Gynecol 47(4):450–459
Huang C, Zhao BW, Chen R et al (2020) Is fetal intelligent navigation echocardiography helpful in screening for d‑transposition of the great arteries? J Ultrasound Med 39(4):775–784
DeVore GR, Haxel C, Satou G et al (2021) Improved detection of coarctation of the aorta using speckle-tracking analysis of fetal heart on last examination prior to delivery. Ultrasound Obstet Gynecol 57(2):282–291
DeVore GR, Klas B, Satou G, Sklansky M (2018) 24-segment sphericity index: a new technique to evaluate fetal cardiac diastolic shape. Ultrasound Obstet Gynecol 51(5):650–658
DeVore GR, Klas B, Satou G, Sklansky M (2018) Twenty-four segment transverse ventricular fractional shortening: a new technique to evaluate fetal cardiac function. J Ultrasound Med 37(5):1129–1141
DeVore GR, Polanco B, Satou G, Sklansky M (2016) Two-Dimensional Speckle Tracking of the Fetal Heart: A Practical Step-by-Step Approach for the Fetal Sonologist. J Ultrasound Med. 2016 Aug;35(8):1765–1781
Lee M, Won H (2019) Novel technique for measurement of fetal right myocardial performance index using synchronised images of right ventricular inflow and outflow. Ultrasound Obstet Gynecol 54:178–179
Kang OJ, Kim SY, Lee MY et al (2021) Novel technique for the measurement of fetal right modified myocardial performance index using synchronized images of right ventricular inflow and outflow and clinical application to twin-to-twin transfusion syndrome. J Ultrasound Med 40(11):2467–2475. https://doi.org/10.1002/jum.15634
Box G (1976) Science and statistics. J Am Stat Assoc 71:791–799
Wasserstein R (2010) George Box: a model statistician. Significance 7:134–135
Chen Z, Liu Z, Du M, Wang Z (2021) Artificial intelligence in obstetric ultrasound: an update and future applications. Front Med (Lausanne) 8:733468
Bates DW, Auerbach A, Schulam P, Wright A, Saria S (2020) Reporting and implementing interventions involving machine learning and artificial intelligence. Ann Intern Med 172(11):S137–s144
Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D (2019) Key challenges for delivering clinical impact with artificial intelligence. BMC Med 17(1):195
Sengupta PP, Shrestha S, Berthon B et al (2020) Proposed requirements for cardiovascular imaging-related machine learning evaluation (PRIME): a checklist: reviewed by the American college of cardiology Healthcare innovation council. JACC Cardiovasc Imaging 13(9):2017–2035
Antoniades C, Oikonomou EK (2021) Artificial intelligence in cardiovascular imaging-principles, expectations, and limitations. Eur Heart J. https://doi.org/10.1093/eurheartj/ehab678
Quer G, Arnaout R, Henne M, Arnaout R (2021) Machine learning and the future of cardiovascular care: JACC state-of-the-art review. J Am Coll Cardiol 77(3):300–313
Allen B Jr., Seltzer SE, Langlotz CP et al (2019) A road map for translational research on artificial intelligence in medical imaging: from the 2018 national institutes of health/RSNA/ACR/the academy workshop. J Am Coll Radiol 16(9 Pt A):1179–1189
Langlotz CP, Allen B, Erickson BJ et al (2019) A roadmap for foundational research on artificial intelligence in medical imaging: from the 2018 NIH/RSNA/ACR/the academy workshop. Radiology 291(3):781–791
Gaffar S, Gearhart AS, Chang AC (2020) The next frontier in pediatric cardiology: artificial intelligence. Pediatr Clin North Am 67(5):995–1009
Krittanawong C, Rogers AJ, Johnson KW et al (2021) Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management. Nat Rev Cardiol 18(2):75–91
Benjamins JW, Hendriks T, Knuuti J, Juarez-Orozco LE, van der Harst P (2019) A primer in artificial intelligence in cardiovascular medicine. Neth Heart J 27(9):392–402
Schuuring MJ, Išgum I, Cosyns B, Chamuleau SAJ, Bouma BJ (2021) Routine echocardiography and artificial intelligence solutions. Front Cardiovasc Med 8:648877
Sonntag D (2021) Künstliche Intelligenz in der Medizin und Gynäkologie – Holzweg oder Heilversprechen? Gynäkologe 54:476–482
Banerjee M, Chiew D, Patel KT et al (2021) The impact of artificial intelligence on clinical education: perceptions of postgraduate trainee doctors in London (UK) and recommendations for trainers. BMC Med Educ 21(1):429
Kleesiek J, Murray J, Kaissis G, Braren R (2020) Künstliche Intelligenz und maschinelles Lernen in der onkologischen Bildgebung. Onkologe 26:60–65
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Interessenkonflikt
J. Weichert und M. Gembicki haben Vortragshonorare von Samsung HME erhalten. A. Welp, J.L. Scharf, C. Dracopoulos und A. Rody geben an, dass kein Interessenkonflikt besteht.
Für diesen Beitrag wurden von den Autoren keine Studien an Menschen oder Tieren durchgeführt. Für die aufgeführten Studien gelten die jeweils dort angegebenen ethischen Richtlinien.
Additional information
Redaktion
Jan Weichert, Lübeck
Ulrich Gembruch, Bonn
Klaus Diedrich, Lübeck
QR-Code scannen & Beitrag online lesen
Rights and permissions
About this article
Cite this article
Weichert, J., Welp, A., Scharf, J.L. et al. Künstliche Intelligenz in der pränatalen kardialen Diagnostik. Gynäkologe 55, 22–31 (2022). https://doi.org/10.1007/s00129-021-04890-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00129-021-04890-6
Schlüsselwörter
- Echokardiographie
- Ultraschall
- Risikoschwangerschaft
- Kardiovaskuläre Erkrankungen
- Interobservervariabilität