Abstract
Zusammenfassung. Künstliche Intelligenz (KI) ist in aller Munde. Aus unserem Alltagsleben ist sie schon längst nicht mehr wegzudenken und hat sich dort an vielen Stellen bereits nahtlos integriert, ohne dass wir uns dessen immer vollständig bewusst sind. Auch im Gesundheitswesen befinden wir uns schon längt inmitten einer Revolution, die unser aller Alltag in der Zukunft verändern wird. Die Radiologie im Speziellen ist aufgrund ihrer fortgeschrittenen Digitalisierung und historisch bedingten Technik-Affinität besonders von diesen Entwicklungen betroffen. Doch was ist KI eigentlich genau und was macht KI so potent, dass etablierte Fachdisziplinen wie die Radiologie sich mit ihrer Zukunftsfähigkeit auseinandersetzen? Was kann KI in der Radiologie heute schon – und was kann sie nicht? Mit diesen Fragen beschäftigt sich der vorliegende Artikel.
Abstract. Artificial Intelligence (AI) is omnipresent. It has neatly permeated our daily life, even if we are not always fully aware of its ubiquitous presence. The healthcare sector in particular is experiencing a revolution which will change our daily routine considerably in the near future. Due to its advanced digitization and its historical technical affinity radiology is especially prone to these developments. But what exactly is AI and what makes AI so potent that established medical disciplines such as radiology worry about their future job perspectives? What are the assets of AI in radiology today – and what are the major challenges? This review article tries to give some answers to these questions.
Résumé. L’intelligence artificielle (IA) est sur toutes les lèvres. Elle fait depuis longtemps partie intégrante de notre vie quotidienne et s’est déjà intégrée sans heurts en de nombreux endroits, sans que nous en ayons toujours pleinement conscience. Ainsi, dans le secteur de la santé, nous sommes déjà au milieu d’une révolution qui changera notre vie quotidienne à l’avenir. La radiologie en particulier est touchée par ces développements en raison de sa numérisation avancée et son affinité historique pour la technologie. Mais qu’est-ce que l’IA exactement et qu’est-ce qui la rend si puissante que des disciplines établies comme la radiologie doivent se préoccuper de sa viabilité future? Qu’est-ce que l’IA peut déjà faire ou ne pas faire en radiologie aujourd’hui? Cet article traite de ces questions.
Bibliografie
Continuous Learning AI in radiology: implementation principles and early applications. Radiology. 2020;200038.
,On radiology. Machine learning and the market for intelligence conference. 2016; Toronto [Internet]. https://www.youtube.com/watch?v=2HMPRXstSvQ&feature=youtu.be; letzter Zugriff: 15.09.2020.
.Artificial Intelligence. In: English Oxford Living Dictionary [Internet]. https://www.lexico.com/definition/artificial_intelligence; letzter Zugriff: 15.09.2020.
, schwache KI – was kann Künstliche Intelligenz? [Internet]. JAAI. 27. September 2018. https://jaai.de/starke-ki-schwache-ki-was-kann-kuenstliche-intelligenz-261/; letzter Zugriff: 15.09.2020.
Maschinelles Lernen [Internet]. https://de.wikipedia.org/wiki/Maschinelles_Lernen; letzter Zugriff: 15.09.2020.
Artificial neural networks in medicine. Health Technol. 2019;9(1):1–6.
.Rise of deep learning for genomic, proteomic, and metabolomic data integration in precision medicine. OMICS. 2018;22 (10):630–636.
.European Society of Radiology (ESR) . What the radiologist should know about artificial intelligence – an ESR white paper. Insights Imaging. 2019;10(1):44.The RSNA pediatric bone age machine learning challenge. Radiology. 2019;290(2):498–503.
,Fully automated deep learning system for bone age assessment. J Digit Imaging. 2017;30(4):427–441.
,TW3-based fully automated bone age assessment system using deep neural networks. IEEE Access. 2019;7:33346–33358.
,Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 2018;15 (11):e1002686.
,Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: A retrospective study. PLoS Med. 2018;15(11):e1002697.
.Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med. 2018;15(11):e1002683.
.Deep learning with convolutional neural network for differentiation of kliver masses at dynamic contrast-enhanced CT: a preliminary study. Radiology. 2018;286(3):887–896.
.Liver fibrosis: Deep convolutional neural network for staging by using gadoxetic acid-enhanced hepatobiliary phase MR images. Radiology. 2018;287(1):146–155.
.A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. Medical Image Analysis. 2016;30:108–119.
.A population-based phenome-wide association study of cardiac and aortic structure and function. Nat Med [Internet]. 24. August 2020; http://www.nature.com/articles/s41591-020-1009-y; letzter Zugriff: 27.08.2020.
,Automatic multi-organ segmentation on abdominal CT with dense V-networks. IEEE Trans Med Imaging. 2018;37(8):1822–1834.
,Automated abdominal segmentation of CT scans for body composition analysis using deep learning. Radiology. 2019;290(3):669–679.
,Spatial aggregation of holistically-nested convolutional neural networks for automated pancreas localization and segmentation. Med Image Anal. 2018; 45:94–107.
,Automatic magnetic resonance prostate segmentation by deep learning with holistically nested networks. J Med Imag. 2017;4(04):1.
,Automated detection of white matter and cortical lesions in early stages of multiple sclerosis: Automated MS Lesion Segmentation. J Magn Reson Imaging. 2016;43(6):1445–1454.
,Artificial intelligence-based classification of breast lesions imaged with a multiparametric breast MRI protocol with ultrafast DCE-MRI, T2, and DWI: Investigative Radiology. Invest Radiol. 2019;54(6):325–32.
,Artificial neural networks in mammography interpretation and diagnostic decision making. Comput Math Method M. 2013;2013:1–10.
.Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making. Eur Radiol. 2019;29(10):5458–5468.
.Determination of mammographic breast density using a deep convolutional neural network. BJR. 2018;20180691.
,Deep learning with domain adaptation for accelerated projection-reconstruction MR. Magn Reson Med. 2018;80(3):1189–1205.
.Generative adversarial networks for noise reduction in low-dose CT. IEEE Trans Med Imaging. 2017;36(12):2536–2545.
.A aparse-view CT reconstruction method based on combination of DenseNet and deconvolution. IEEE Trans Med Imaging. 2018;37(6):1407–1417.
.A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE Trans Med Imaging. 2018; 37(2):491–503.
.Collaboration, campaigns and champions for appropriate imaging: feedback from the Zagreb workshop. Insights Imaging. 2018;9(2):211–214.
.Structured report data can be used to develop deep learning algorithms: a proof of concept in ankle radiographs. Insights Imaging. 2019;10(1):283.
,Big data, artificial intelligence, and structured reporting. Eur RAdiol Exp. 2018;2(1):42.
.Chihuahua or a muffin? The most bizarre internet craze ever [Internet]. Mail Online. 2016. https://www.dailymail.co.uk/news/article-3487538/Is-Chihuahua-muffin-Hilarious-photos-dogs-look-like-food-sweeping-internet.html; letzter Zugriff: 15.09.2020.
.Deep learning approach for very similar objects recognition application on Chihuahua and muffin problem. CoRR [Internet]. 2018 Jan 29. http://arxiv.org/abs/1801.09573; letzter Zugriff: 15.09.2020.
.One pixel attack for fooling deep neural networks. IEEE Trans Evol Computat. 2019;23(5):828–841.
.Adversarial patch. CoRR [Internet]. 2017 Dec 27. https://arxiv.org/abs/1712.09 665; letzter Zugriff: 15.09.2020.
.Can your AI differentiate cats from Covid-19? Sample efficient uncertainty estimation for deep learning safety [Internet]. https://api.deepai.org/publication-download-pdf/can-your-ai-differentiate-cats-from-covid-19-sample-efficient-uncertainty-estimation-for-deep-learning-safety; letzter Zugriff: 15.09.2020.
.Ethics of artificial intelligence in radiology: summary of the joint European and North American Multisociety Statement. Radiology. 2019;293(2):436–440.
,