Skip to main content

2025 | OriginalPaper | Buchkapitel

40. Künstliche (Artifizielle) Intelligenz (KI oder AI) im Ultraschall

verfasst von : Prof. Dr. med. Jan Weichert, Prof. Dr. techn. Christian Kollmann

Erschienen in: Ultraschalldiagnostik in Geburtshilfe und Gynäkologie

Verlag: Springer Berlin Heidelberg

Zusammenfassung

Von einigen Experten wird der künstlichen Intelligenz (KI) ein ähnlich enormes Potential wie der Elektrizität vor mehr als 100 Jahren im Hinblick auf die nachhaltige Veränderung bestehender Prozessabläufe in allen Bereichen des täglichen Lebens zugesprochen, so auch im Gesundheitswesen. Im medizinischen Kontext ist einer der wesentlichen Vorteile der KI in der computergestützten Analyse von Bilddaten zu sehen. Deutlich wurde dieses spätestens im Jahr 2015, wo erstmals die Fehlerraten eines KI-Algorithmus (ResNet) bei der Klassifikation, Detektion und Lokalisation von Bildinformationen im Rahmen der ImageNet Large-Scale Visual Recognition Challenge (ILSVCR) deutlich unterhalb der von Menschen lagen. Insbesondere dort, wo arbeits- und zeitintensive, potenziell fehleranfällige und repetitive Arbeitsschritte in der Diagnostik und Befundung anfallen, sind Anwendungen der KI in der Lage, die Untersucherabhängigkeit mit konsekutiver Varianz in der diagnostischen Qualität maßgeblich zu verringern.
Literatur
Zurück zum Zitat Alzubaidi Alzubaidi M, Agus M, Alyafei K, Althelaya KA, Shah U, Abd-Alrazaq A, Anbar M, Makhlouf M, Househ M (2022) Toward deep observation: a systematic survey on artificial intelligence techniques to monitor fetus via ultrasound images. iScience 25:104713CrossRefPubMed Alzubaidi Alzubaidi M, Agus M, Alyafei K, Althelaya KA, Shah U, Abd-Alrazaq A, Anbar M, Makhlouf M, Househ M (2022) Toward deep observation: a systematic survey on artificial intelligence techniques to monitor fetus via ultrasound images. iScience 25:104713CrossRefPubMed
Zurück zum Zitat Arnaout R, Curran L, Zhao Y, Levine JC, Chinn E, Moon-Grady AJ (2021) An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart disease. Nat Med 27:882–891CrossRefPubMedPubMedCentral Arnaout R, Curran L, Zhao Y, Levine JC, Chinn E, Moon-Grady AJ (2021) An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart disease. Nat Med 27:882–891CrossRefPubMedPubMedCentral
Zurück zum Zitat Bastiaansen WAP, Klein S, Koning AHJ, Niessen WJ, Steegers-Theunissen RPM, Rousian M (2023) Computational methods for the analysis of early-pregnancy brain ultrasonography: a systematic review. EBioMedicine 89:104466CrossRefPubMedPubMedCentral Bastiaansen WAP, Klein S, Koning AHJ, Niessen WJ, Steegers-Theunissen RPM, Rousian M (2023) Computational methods for the analysis of early-pregnancy brain ultrasonography: a systematic review. EBioMedicine 89:104466CrossRefPubMedPubMedCentral
Zurück zum Zitat Baumgartner CF, Kamnitsas K, Matthew J, Fletcher TP, Smith S, Koch LM, Kainz B, Sononet RD (2017) Real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans Med Imaging 36:2204–2215CrossRefPubMed Baumgartner CF, Kamnitsas K, Matthew J, Fletcher TP, Smith S, Koch LM, Kainz B, Sononet RD (2017) Real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans Med Imaging 36:2204–2215CrossRefPubMed
Zurück zum Zitat Chen Z et al (2021) Artificial intelligence in obstetric ultrasound: an update and future applications. Front Med 8:733468CrossRef Chen Z et al (2021) Artificial intelligence in obstetric ultrasound: an update and future applications. Front Med 8:733468CrossRef
Zurück zum Zitat Colak E, Moreland R, Ghassemi M (2021) Five principles for the intelligent use of AI in medical imaging. Intensive Care Med 47:154–156CrossRefPubMed Colak E, Moreland R, Ghassemi M (2021) Five principles for the intelligent use of AI in medical imaging. Intensive Care Med 47:154–156CrossRefPubMed
Zurück zum Zitat Davidson L, Boland MR (2021) Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes. Brief Bioinform 22:bbaa369CrossRefPubMedPubMedCentral Davidson L, Boland MR (2021) Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes. Brief Bioinform 22:bbaa369CrossRefPubMedPubMedCentral
Zurück zum Zitat Day TG, Kainz B, Hajnal J, Razavi R, Simpson JM (2021) Artificial intelligence, fetal echocardiography, and congenital heart disease. Prenat Diagn 41:733–742CrossRefPubMedCentral Day TG, Kainz B, Hajnal J, Razavi R, Simpson JM (2021) Artificial intelligence, fetal echocardiography, and congenital heart disease. Prenat Diagn 41:733–742CrossRefPubMedCentral
Zurück zum Zitat Drukker L, Noble JA, Papageorghiou AT (2020) Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol 56:498–505CrossRefPubMedPubMedCentral Drukker L, Noble JA, Papageorghiou AT (2020) Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol 56:498–505CrossRefPubMedPubMedCentral
Zurück zum Zitat Du Y, McNestry C, Wei L, Antoniadi AM, McAuliffe FM, Mooney C (2023) Machine learning-based clinical decision support systems for pregnancy care: A systematic review. Int J Med Inform 173:105040CrossRefPubMed Du Y, McNestry C, Wei L, Antoniadi AM, McAuliffe FM, Mooney C (2023) Machine learning-based clinical decision support systems for pregnancy care: A systematic review. Int J Med Inform 173:105040CrossRefPubMed
Zurück zum Zitat Garcia-Canadilla P, Sanchez-Martinez S, Crispi F, Bijnens B (2020) Machine learning in fetal cardiology: what to expect. Fetal Diagn Ther 47:363–372CrossRefPubMed Garcia-Canadilla P, Sanchez-Martinez S, Crispi F, Bijnens B (2020) Machine learning in fetal cardiology: what to expect. Fetal Diagn Ther 47:363–372CrossRefPubMed
Zurück zum Zitat He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv
Zurück zum Zitat Jone PN, Gearhart A, Lei H, Xing F, Nahar J, Lopez-Jimenez F, Diller GP, Marelli A, Wilson L, Saidi A, Cho D, Chang AC (2022) Artificial intelligence in congenital heart disease. Curr State Prospect 1:100153CrossRef Jone PN, Gearhart A, Lei H, Xing F, Nahar J, Lopez-Jimenez F, Diller GP, Marelli A, Wilson L, Saidi A, Cho D, Chang AC (2022) Artificial intelligence in congenital heart disease. Curr State Prospect 1:100153CrossRef
Zurück zum Zitat Komatsu M, Sakai A, Komatsu R, Matsuoka R, Yasutomi S, Shozu K, Dozen A, Machino H, Hidaka H, Arakaki T et al (2021) Detection of Cardiac Structural Abnormalities in Fetal Ultrasound Videos Using Deep Learning. Appl Sci 11:371CrossRef Komatsu M, Sakai A, Komatsu R, Matsuoka R, Yasutomi S, Shozu K, Dozen A, Machino H, Hidaka H, Arakaki T et al (2021) Detection of Cardiac Structural Abnormalities in Fetal Ultrasound Videos Using Deep Learning. Appl Sci 11:371CrossRef
Zurück zum Zitat Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: Conference and workshop on neural information processing systems Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: Conference and workshop on neural information processing systems
Zurück zum Zitat Lin M, He X, Guo H, He M, Zhang L, Xian J, Lei T, Xu Q, Zheng J, Feng J, Hao C, Yang Y, Wang N, Xie H (2022) Use of real-time artificial intelligence in detection of abnormal image patterns in standard sonographic reference planes in screening for fetal intracranial malformations. Ultrasound Obstet Gynecol 59:304-316CrossRefPubMed Lin M, He X, Guo H, He M, Zhang L, Xian J, Lei T, Xu Q, Zheng J, Feng J, Hao C, Yang Y, Wang N, Xie H (2022) Use of real-time artificial intelligence in detection of abnormal image patterns in standard sonographic reference planes in screening for fetal intracranial malformations. Ultrasound Obstet Gynecol 59:304-316CrossRefPubMed
Zurück zum Zitat Matthew J, Skelton E, Day TG, Zimmer VA, Gomez A, Wheeler G, Toussaint N, Liu T, Budd S, Lloyd K, Wright R, Deng S, Ghavami N, Sinclair M, Meng Q, Kainz B, Schnabel JA, Rueckert D, Razavi R, Simpson J, Hajnal J (2022) Exploring a new paradigm for the fetal anomaly ultrasound scan: Artificial intelligence in real time. Prenat Diagn 42:49–59CrossRefPubMed Matthew J, Skelton E, Day TG, Zimmer VA, Gomez A, Wheeler G, Toussaint N, Liu T, Budd S, Lloyd K, Wright R, Deng S, Ghavami N, Sinclair M, Meng Q, Kainz B, Schnabel JA, Rueckert D, Razavi R, Simpson J, Hajnal J (2022) Exploring a new paradigm for the fetal anomaly ultrasound scan: Artificial intelligence in real time. Prenat Diagn 42:49–59CrossRefPubMed
Zurück zum Zitat Ronneberger O (2015) U-Net: convolutional networks for biomedical image segmentation. MICCAI. Bd. 9351. Springer Ronneberger O (2015) U-Net: convolutional networks for biomedical image segmentation. MICCAI. Bd. 9351. Springer
Zurück zum Zitat Sarno L, Neola D, Carbone L, Saccone G, Carlea A, Miceli M, Iorio GG, Mappa I, Rizzo G, Girolamo RD, D’Antonio F, Guida M, Maruotti GM (2023) Use of artificial intelligence in obstetrics: not quite ready for prime time. Am J Obstet Gynecol MFM 5:100792CrossRefPubMed Sarno L, Neola D, Carbone L, Saccone G, Carlea A, Miceli M, Iorio GG, Mappa I, Rizzo G, Girolamo RD, D’Antonio F, Guida M, Maruotti GM (2023) Use of artificial intelligence in obstetrics: not quite ready for prime time. Am J Obstet Gynecol MFM 5:100792CrossRefPubMed
Zurück zum Zitat Samuel AL (1959) Some studies in machine learning using the game of checkers. IBM J Res Dev 3:207-226. Samuel AL (1959) Some studies in machine learning using the game of checkers. IBM J Res Dev 3:207-226.
Zurück zum Zitat Schmidt LJ, Rieger O, Neznansky M, Hackelöer M, Dröge LA, Henrich W, Higgins D, Verlohren S (2022) A machine-learning-based algorithm improves prediction of preeclampsia-associated adverse outcomes. Am J Obstet Gynecol 227:77.e1–77.e30CrossRefPubMed Schmidt LJ, Rieger O, Neznansky M, Hackelöer M, Dröge LA, Henrich W, Higgins D, Verlohren S (2022) A machine-learning-based algorithm improves prediction of preeclampsia-associated adverse outcomes. Am J Obstet Gynecol 227:77.e1–77.e30CrossRefPubMed
Zurück zum Zitat Seah J, Boeken T, Sapoval M, Goh GS (2022) Prime time for artificial intelligence in Interventional radiology. Cardiovasc Intervent Radiol 45:283–289CrossRefPubMedPubMedCentral Seah J, Boeken T, Sapoval M, Goh GS (2022) Prime time for artificial intelligence in Interventional radiology. Cardiovasc Intervent Radiol 45:283–289CrossRefPubMedPubMedCentral
Zurück zum Zitat Wu E et al (2021) How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals. Nat Med 27:582–584CrossRefPubMed Wu E et al (2021) How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals. Nat Med 27:582–584CrossRefPubMed
Zurück zum Zitat Xiao S, Zhang J, Zhu Y, Zhang Z, Cao H, Xie M, Zhang L (2023) Application and progress of artificial intelligence in fetal ultrasound. J Clin Med 12:3298CrossRefPubMedPubMedCentral Xiao S, Zhang J, Zhu Y, Zhang Z, Cao H, Xie M, Zhang L (2023) Application and progress of artificial intelligence in fetal ultrasound. J Clin Med 12:3298CrossRefPubMedPubMedCentral
Zurück zum Zitat Yeo L, Romero R (2022) New and advanced features of fetal intelligent navigation echocardiography (FINE) or 5D heart. J Matern Fetal Neonatal Med 35:1498–1516CrossRefPubMed Yeo L, Romero R (2022) New and advanced features of fetal intelligent navigation echocardiography (FINE) or 5D heart. J Matern Fetal Neonatal Med 35:1498–1516CrossRefPubMed
Metadaten
Titel
Künstliche (Artifizielle) Intelligenz (KI oder AI) im Ultraschall
verfasst von
Prof. Dr. med. Jan Weichert
Prof. Dr. techn. Christian Kollmann
Copyright-Jahr
2025
Verlag
Springer Berlin Heidelberg
DOI
https://doi.org/10.1007/978-3-662-67373-7_40