Skip to main content
Hauptrubriken
CME Facharzt-Training Webinare Zeitschriften Bücher e.Medpedia Podcast
Service
Jobbörse Info & Hilfe
Fachgebiete
Anästhesiologie Allgemeinmedizin Arbeitsmedizin Augenheilkunde Chirurgie Dermatologie Gynäkologie und Geburtshilfe HNO Innere Medizin Kardiologie Neurologie Onkologie und Hämatologie Orthopädie und Unfallchirurgie Pädiatrie Pathologie Psychiatrie Radiologie Rechtsmedizin Urologie Zahnmedizin
Themen
Klimawandel und Gesundheit Neues aus dem Markt COVID-19 Praxis und Beruf Seltene Erkrankungen GOÄ & EBM Panorama
Sammlungen
Kasuistiken Algorithmen & Infografiken Blickdiagnosen Arthropedia FlapFinder (für Dermatochirurgen) Videos Kongressberichterstattung Medizin für Apothekerinnen und Apotheker Für Ärztinnen und Ärzte in Weiterbildung Für Medizinstudierende
Erweiterte Suche
Anmelden
nach oben
Clinical Neuroradiology

29.01.2024 | Review Article

Challenges and Potential of Artificial Intelligence in Neuroradiology

verfasst von: Anthony J. Winder, Emma AM Stanley, Jens Fiehler, Nils D. Forkert

Erschienen in: Clinical Neuroradiology

Einloggen, um Zugang zu erhalten

Abstract

Purpose

Artificial intelligence (AI) has emerged as a transformative force in medical research and is garnering increased attention in the public consciousness. This represents a critical time period in which medical researchers, healthcare providers, insurers, regulatory agencies, and patients are all developing and shaping their beliefs and policies regarding the use of AI in the healthcare sector. The successful deployment of AI will require support from all these groups. This commentary proposes that widespread support for medical AI must be driven by clear and transparent scientific reporting, beginning at the earliest stages of scientific research.

Methods

A review of relevant guidelines and literature describing how scientific reporting plays a central role at key stages in the life cycle of an AI software product was conducted. To contextualize this principle within a specific medical domain, we discuss the current state of predictive tissue outcome modeling in acute ischemic stroke and the unique challenges presented therein.

Results and Conclusion

Translating AI methods from the research to the clinical domain is complicated by challenges related to model design and validation studies, medical product regulations, and healthcare providers’ reservations regarding AI’s efficacy and affordability. However, each of these limitations is also an opportunity for high-impact research that will help to accelerate the clinical adoption of state-of-the-art medical AI. In all cases, establishing and adhering to appropriate reporting standards is an important responsibility that is shared by all of the parties involved in the life cycle of a prospective AI software product.
Literatur
1.
2.
GBD 2019 Collaborators. Global, regional, and national burden of diseases and injuries for adults 70 years and older: systematic analysis for the Global Burden of Disease 2019 Study. BMJ. 2022;376:e068208.
3.
4.
Boniol M, Kunjumen T, Nair TS, Siyam A, Campbell J, Diallo K. The global health workforce stock and distribution in 2020 and 2030: a threat to equity and ‘universal’ health coverage? Bmj Glob Health. 2022;7(6):e9316.PubMedPubMedCentralCrossRef
5.
Hartman M, Martin AB, Washington B, Catlin A, National Health Expenditure Accounts Team T. National Health Care Spending In 2020: Growth Driven By Federal Spending In Response To The COVID-19 Pandemic: National Health Expenditures study examines US health care spending in 2020. Health Aff. 2022;41(1):13–25.CrossRef
6.
Wolff J, Pauling J, Keck A, Baumbach J. Systematic Review of Economic Impact Studies of Artificial Intelligence in Health Care. J Med Internet Res. 2020;22(2):e16866.PubMedPubMedCentralCrossRef
7.
Bohr A, Memarzadeh K. The rise of artificial intelligence in healthcare applications. In: Artif Intell Heal Elsevier. 2020;pp:25–60.
8.
Ebrahimian S, et al. FDA-regulated AI Algorithms: Trends, Strengths, and Gaps of Validation Studies. Academic Radiology. 2022;29(4):559–566.
9.
Van Der Heijden AA, Abramoff MD, Verbraak F, Van Hecke MV, Liem A, Nijpels G. Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System. Acta Ophthalmol. 2018;96(1):63–8.CrossRef
10.
Huang X‑M, et al. Cost-effectiveness of artificial intelligence screening for diabetic retinopathy in rural China. BMC Health Serv Res. 2022;22(1):260.PubMedPubMedCentralCrossRef
11.
Bellemo V, et al. Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study. Lancet Digit Health. 2019;1(1):e35–e44.PubMedCrossRef
12.
Straka M, Albers GW, Bammer R. Real-time diffusion-perfusion mismatch analysis in acute stroke. J Magn Reson Imaging. 2010;32(5):1024–37.PubMedPubMedCentralCrossRef
13.
FDA approves stroke-detecting AI software. Nat Biotechnol. 2018;36(4):290.
14.
Van Leeuwen KG, et al. Cost-effectiveness of artificial intelligence aided vessel occlusion detection in acute stroke: an early health technology assessment. Insights Imaging. 2021;12(1):133.PubMedPubMedCentralCrossRef
15.
Fuller SD, et al. Five-Year Cost-Effectiveness Modeling of Primary Care-Based, Nonmydriatic Automated Retinal Image Analysis Screening Among Low-Income Patients With Diabetes. J Diabetes Sci Technol. 2022;16(2):415–27.PubMedCrossRef
16.
Schwendicke F, et al. Cost-effectiveness of Artificial Intelligence for Proximal Caries Detection. J Dent Res. 2021;100(4):369–76.PubMedCrossRef
17.
18.
Souza R, et al. Image-encoded biological and non-biological variables may be used as shortcuts in deep learning models trained on multisite neuroimaging data. J Am Med Inform Assoc. 2023;30(12):1925–33.PubMedPubMedCentralCrossRef
19.
Stanley EAM, Wilms M, Forkert ND. Disproportionate Subgroup Impacts and Other Challenges of Fairness in Artificial Intelligence for Medical Image Analysis. In: Baxter JSH et al. editors. Lecture Notes in Computer Science, vol 13755. Springer:Cham; 2022. Pp. 14–25.
20.
Stanley EAM, et al. Towards objective and systematic evaluation of bias in medical imaging AI. Arxiv. 2023;2311:2115.
21.
Mongan J, Moy L, Kahn CE. Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers. Radiol Artif Intell. 2020;2(2):e200029.PubMedPubMedCentralCrossRef
22.
Norgeot B, et al. Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist. Nat Med. 2020;26(9):1320–4.PubMedPubMedCentralCrossRef
23.
Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): The TRIPOD Statement. Ann Intern Med. 2015;162(1):55–63.PubMedCrossRef
24.
Wolff RF, et al. PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies. Ann Intern Med. 2019;170(1):51.PubMedCrossRef
25.
Collins GS, et al. Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. Bmj Open. 2021;11(7):e48008.PubMedPubMedCentralCrossRef
26.
Naverro CLA, et al. Risk of bias in studies on prediction models developed using supervised machine learning techniques. Syst Rev.
27.
Roberts M, et al. Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans. Nat Mach Intell. 2021;3(3):199–217.CrossRef
28.
Wen J, Zhang Z, Lan Y, Cui Z, Cai J, Zhang W. A survey on federated learning: challenges and applications. Int J Mach Learn Cybern. 2023;14:513–35.PubMedCrossRef
29.
30.
31.
32.
Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447–53.PubMedCrossRef
33.
Straw I, Wu H. Investigating for bias in healthcare algorithms: a sex-stratified analysis of supervised machine learning models in liver disease prediction. Bmj Health Care Inform. 2022;29(1):e100457.PubMedPubMedCentralCrossRef
34.
Beede E, et al. A Human-Centered Evaluation of a Deep Learning System Deployed in Clinics for the Detection of Diabetic Retinopathy. In: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. ACM;. 2020;pp:1–12.
35.
36.
Canon CL, Chick JFB, DeQuesada I, Gunderman RB, Hoven N, Prosper AE. Physician Burnout in Radiology: Perspectives From the Field. Am J Roentgenol. 2022;218(2):370–4.CrossRef
37.
38.
39.
Li C, Parpia C, Sriharan A, Keefe DT. Electronic medical record-related burnout in healthcare providers: a scoping review of outcomes and interventions. Bmj Open. 2022;12(8):e60865.PubMedPubMedCentralCrossRef
40.
Stern AD, Goldfarb A, Minssen T, Price WNII. AI Insurance: How Liability Insurance Can Drive the Responsible Adoption of Artificial Intelligence in Health Care. Nejm Catal. 2022;3(4).
41.
Chen Y, Stavropoulou C, Narasinkan R, Baker A, Scarbrough H. Professionals’ responses to the introduction of AI innovations in radiology and their implications for future adoption: a qualitative study. BMC Health Serv Res. 2021;21(1):813.PubMedPubMedCentralCrossRef
42.
Kurowecki D, Lee SY, Monteiro S, Finlay K. Resident Physicians’ Perceptions of Diagnostic Radiology and the Declining Interest in the Specialty. Acad Radiol. 2021;28(2):261–70.PubMedCrossRef
43.
Chen MM, Golding LP, Nicola GN. Who Will Pay for AI?. Radiology: Artificial Intelligence. 2021;3(3):e210030.
44.
Varoquaux G, Cheplygina V. Machine learning for medical imaging: methodological failures and recommendations for the future. Npj Digit Med. 2022;5(1):48.PubMedPubMedCentralCrossRef
45.
Fernández-Delgado M, Cernadas E, Barro S, Amorim D. Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res. 2014;15(1):3133–81.
46.
47.
48.
Yu W, Jiang W‑J. A Simple Imaging Guide for Endovascular Thrombectomy in Acute Ischemic Stroke: From Time Window to Perfusion Mismatch and Beyond. Front Neurol. 2019;10:502.PubMedPubMedCentralCrossRef
49.
50.
Goyal M, et al. Challenging the Ischemic Core Concept in Acute Ischemic Stroke Imaging. Stroke. 2020;51(10):3147–55.PubMedCrossRef
51.
Winder AJ, Siemonsen S, Flottmann F, Thomalla G, Fiehler J, Forkert ND. Technical considerations of multi-parametric tissue outcome prediction methods in acute ischemic stroke patients. Sci Rep. 2019;9(1):13208.PubMedPubMedCentralCrossRef
52.
Winder AJ, Wilms M, Amador K, Flottmann F, Fiehler J, Forkert ND. Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning. Front Neurosci. 2022;16:1009654.PubMedPubMedCentralCrossRef
53.
Amador K, Wilms M, Winder A, Fiehler J, Forkert ND. Predicting treatment-specific lesion outcomes in acute ischemic stroke from 4D CT perfusion imaging using spatio-temporal convolutional neural networks. Med Image Anal. 2022;82:102610.PubMedCrossRef
54.
Winzeck S, et al. ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI. Front Neurol. 2018;9:679.PubMedPubMedCentralCrossRef
55.
Wang X, Fan Y, Zhang N, Li J, Duan Y, Yang B. Performance of Machine Learning for Tissue Outcome Prediction in Acute Ischemic Stroke: A Systematic Review and Meta-Analysis. Front Neurol. 2022;13:910259.PubMedPubMedCentralCrossRef
56.
Fiehler J, et al. ERASER: A Thrombectomy Study With Predictive Analytics End Point. Stroke. 2019;50(5):1275–8.CrossRef
57.
Nielsen A, Hansen MB, Tietze A, Mouridsen K. Prediction of Tissue Outcome and Assessment of Treatment Effect in Acute Ischemic Stroke Using Deep Learning. Stroke. 2018;49:1394–401.PubMedCrossRef
58.
Winder A, Wilms M, Fiehler J, Forkert ND. Treatment Efficacy Analysis in Acute Ischemic Stroke Patients Using In Silico Modeling Based on Machine Learning: A Proof-of-Principle. Biomedicines. 2021;9(10):1357.PubMedPubMedCentralCrossRef
59.
Bücke P, et al. What You Always Wanted to Know about Endovascular Therapy in Acute Ischemic Stroke but Never Dared to Ask: A Comprehensive Review. Rev Cardiovasc Med. 2022;23(10):340.CrossRef
60.
Ovbiagele B, Kidwell CS, Starkman S, Saver JL. Neuroprotective agents for the treatment of acute ischemic stroke. Curr Neurol Neurosci Rep. 2003;3(1):9–20.PubMedCrossRef
61.
Litvinenko IV, et al. The algorithm of reperfusion treatment of the ischemic stroke: focus on DAWN and DEFUSE-3 trials. Arter Gipertenz. 2021;27(1):29–40.CrossRef
62.
63.
Konduri PR, Marquering HA, Van Bavel EE, Hoekstra A, Majoie CBLM, The INSIST Investigators. In-Silico Trials for Treatment of Acute Ischemic Stroke. Front Neurol.. 11:558125. 2020.
64.
Miller C, et al. In silico trials for treatment of acute ischemic stroke: Design and implementation. Comput Biol Med. 2021;137:104802.PubMedCrossRef
65.
Benzakoun J, et al. Tissue outcome prediction in hyperacute ischemic stroke: Comparison of machine learning models. J Cereb Blood Flow Metab. 2021;41(11):3085–96.PubMedPubMedCentralCrossRef
66.
Stier N, Vincent N, Liebeskind D, Scalzo F. Deep learning of tissue fate features in acute ischemic stroke. In, Vol. 2015. International Conference on Bioinformatics and Biomedicine (BIBM). IEEE: IEEE; 2015. pp. 1316–21.
67.
Rajput D, Wang W‑J, Chen C‑C. Evaluation of a decided sample size in machine learning applications. Bmc Bioinformatics. 2023;24:48.PubMedPubMedCentralCrossRef
68.
Forkert ND, Fiehler J. Effect of sample size on multi-parametric prediction of tissue outcome in acute ischemic stroke using a random forest classifier.
69.
Carter RE, Attia ZI, Lopez-Jimenez F, Friedman PA. Pragmatic considerations for fostering reproducible research in artificial intelligence. Npj Digit Med. 2019;2(1):42.CrossRef
70.
Ni H, et al. Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-contrast CT Scans. In: Wang L, Dou Q, Fletcher PT, Speidel S, Li S, editors. Image Computing and Computer Assisted Intervention—MICCAI. Switzerland, Vol. 2022. Cham: Springer Nature: Medical; 2022. pp. 416–26.
71.
Kao P‑Y, Chen JW, Manjunath BS. Predicting Clinical Outcome of Stroke Patients with Tractographic Feature. In: Crimi A, Bakas S, editors. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. Cham: Springer; 2020. pp. 32–43.CrossRef
72.
Kemmling A, et al. Multivariate Dynamic Prediction of Ischemic Infarction and Tissue Salvage as a Function of Time and Degree of Recanalization. J Cereb Blood Flow Metab. 2015;35(9):1397–405.PubMedPubMedCentralCrossRef
73.
Yu Y, et al. Use of Deep Learning to Predict Final Ischemic Stroke Lesions From Initial Magnetic Resonance Imaging. Jama Netw Open. 2020;3(3):e200772.PubMedPubMedCentralCrossRef
74.
Debs N, et al. Impact of the reperfusion status for predicting the final stroke infarct using deep learning. Neuroimage: Clin. 2021;29:102548.PubMedCrossRef
75.
Livne M, Boldsen JK, Mikkelsen IK, Fiebach JB, Sobesky J, Mouridsen K. Boosted Tree Model Reforms Multimodal Magnetic Resonance Imaging Infarct Prediction in Acute Stroke. Stroke. 2018;49(4):912–8.CrossRef
76.
Dubin JR, Simon SD, Norrell K, Perera J, Gowen J, Cil A. Risk of Recall Among Medical Devices Undergoing US Food and Drug Administration 510(k) Clearance and Premarket Approval, 2008-2017. JAMA Netw Open. 2021;4(5):e217274.
77.
Ardaugh BM, Graves SE, Redberg RF. The 510(k) Ancestry of a Metal-on-Metal Hip Implant. N Engl J Med. 2013;368(2):97–100.PubMedCrossRef
78.
79.
80.
Furlan NE, et al. The Impact of Age on Mortality and Disability in Patients With Ischemic Stroke Who Underwent Cerebral Reperfusion Therapy: A Brazilian Cohort Study. Front Aging Neurosci. 2021;13:649902.PubMedPubMedCentralCrossRef
81.
Zhang Y, Liu S, Li C, Wang J. Application of Deep Learning Method on Ischemic Stroke Lesion. Segmentation J Shanghai Jiaotong Univ (sci). 2022;27(1):99–111.CrossRef
82.
Nielsen C, Tuladhar A, Forkert ND. Investigating the Vulnerability of Federated Learning-Based Diabetic Retinopathy Grade Classification to Gradient Inversion Attacks. In: Antony B, Fu H, Lee CS, MacGillivray T, Xu Y, Zheng Y, editors. Ophthalmic Medical Image Analysis. Cham: Springer; 2022. pp. 183–92.CrossRef
83.
Stanley EAM, Wilms M, Mouches P, Forkert ND. Fairness-related performance and explainability effects in deep learning models for brain image analysis. J Med Imag. 2022;9:6.CrossRef
84.
Benjamens S, Dhunnoo P, Meskó B. The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database. Npj Digit Med. 2020;3(1):118.PubMedPubMedCentralCrossRef
85.
86.
87.
Wu E, Wu K, Daneshjou R, Ouyang D, Ho DE, Zou J. How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals. Nat Med. 2021;27(4):582–4.PubMedCrossRef
88.
Lehman CD, Wellman RD, Buist DSM, Kerlikowske K, Tosteson ANA, Miglioretti DL. Diagnostic Accuracy of Digital Screening Mammography With and Without Computer-Aided Detection. JAMA Intern Med. 2015;175(11):1828.PubMedPubMedCentralCrossRef
89.
Salim M, et al. External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms. JAMA Oncol. 2020;6(10):1581.PubMedPubMedCentralCrossRef
90.
Lee JH, et al. Improving the Performance of Radiologists Using Artificial Intelligence-Based Detection Support Software for Mammography: A Multi-Reader Study. Korean J Radiol. 2022;23(5):505.PubMedPubMedCentralCrossRef
Metadaten
Titel
Challenges and Potential of Artificial Intelligence in Neuroradiology
verfasst von
Anthony J. Winder
Emma AM Stanley
Jens Fiehler
Nils D. Forkert
Publikationsdatum
29.01.2024
Verlag
Springer Berlin Heidelberg
Erschienen in
Clinical Neuroradiology
Print ISSN: 1869-1439
Elektronische ISSN: 1869-1447
DOI
https://doi.org/10.1007/s00062-024-01382-7

Neu im Fachgebiet Radiologie

Akuter Schwindel: Wann lohnt sich eine MRT?

28.04.2024 Schwindel Nachrichten

Akuter Schwindel stellt oft eine diagnostische Herausforderung dar. Wie nützlich dabei eine MRT ist, hat eine Studie aus Finnland untersucht. Immerhin einer von sechs Patienten wurde mit akutem ischämischem Schlaganfall diagnostiziert.

Screening-Mammografie offenbart erhöhtes Herz-Kreislauf-Risiko

26.04.2024 Mammografie Nachrichten

Routinemäßige Mammografien helfen, Brustkrebs frühzeitig zu erkennen. Anhand der Röntgenuntersuchung lassen sich aber auch kardiovaskuläre Risikopatientinnen identifizieren. Als zuverlässiger Anhaltspunkt gilt die Verkalkung der Brustarterien.

S3-Leitlinie zu Pankreaskrebs aktualisiert

23.04.2024 Pankreaskarzinom Nachrichten

Die Empfehlungen zur Therapie des Pankreaskarzinoms wurden um zwei Off-Label-Anwendungen erweitert. Und auch im Bereich der Früherkennung gibt es Aktualisierungen.

Fünf Dinge, die im Kindernotfall besser zu unterlassen sind

18.04.2024 Pädiatrische Notfallmedizin Nachrichten

Im Choosing-Wisely-Programm, das für die deutsche Initiative „Klug entscheiden“ Pate gestanden hat, sind erstmals Empfehlungen zum Umgang mit Notfällen von Kindern erschienen. Fünf Dinge gilt es demnach zu vermeiden.

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen
Bildnachweise