AI as a New Frontier in Contrast Media Research: Bridging the Gap Between Contrast Media Reduction, the Contrast-Free Question and New Application Discoveries.
Journal
Investigative radiology
ISSN: 1536-0210
Titre abrégé: Invest Radiol
Pays: United States
ID NLM: 0045377
Informations de publication
Date de publication:
12 Oct 2023
12 Oct 2023
Historique:
pubmed:
12
10
2023
medline:
12
10
2023
entrez:
12
10
2023
Statut:
aheadofprint
Résumé
Artificial intelligence (AI) techniques are currently harnessed to revolutionize the domain of medical imaging. This review investigates 3 major AI-driven approaches for contrast agent management: new frontiers in contrast agent dose reduction, the contrast-free question, and new applications. By examining recent studies that use AI as a new frontier in contrast media research, we synthesize the current state of the field and provide a comprehensive understanding of the potential and limitations of AI in this context. In doing so, we show the dose limits of reducing the amount of contrast agents and demonstrate why it might not be possible to completely eliminate contrast agents in the future. In addition, we highlight potential new applications to further increase the radiologist's sensitivity at normal doses. At the same time, this review shows which network architectures provide promising approaches and reveals possible artifacts of a paired image-to-image conversion. Furthermore, current US Food and Drug Administration regulatory guidelines regarding AI/machine learning-enabled medical devices are highlighted.
Identifiants
pubmed: 37824140
doi: 10.1097/RLI.0000000000001028
pii: 00004424-990000000-00162
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: H.P., F.K., and G.J. are employees of Bayer AG. J.H. received financial support by the German Research Foundation (DFG)–funded Clinician Scientist Academy of the University Hospital Essen (UMEA) (FU 356/12-2). The authors declare no other conflict of interest.
Références
Ammari S, Bône A, Balleyguier C, et al. Can deep learning replace gadolinium in neuro-oncology?: a reader study. Invest Radiol . 2022;57:99–107.
Bône A, Ammari S, Menu Y, et al. From dose reduction to contrast maximization: can deep learning amplify the impact of contrast media on brain magnetic resonance image quality? A reader study. Invest Radiol . 2022;57:527–535.
Haubold J, Jost G, Theysohn JM, et al. Contrast agent dose reduction in MRI utilizing a generative adversarial network in an exploratory animal study. Invest Radiol . 2023;58:396–404.
Haase R, Pinetz T, Bendella Z, et al. Reduction of gadolinium-based contrast agents in MRI using convolutional neural networks and different input protocols: limited interchangeability of synthesized sequences with original full-dose images despite excellent quantitative performance. Invest Radiol . 2023;58:420–430.
Müller-Franzes G, Huck L, Tayebi Arasteh S, et al. Using machine learning to reduce the need for contrast agents in breast MRI through synthetic images. Radiology . 2023;307:e222211.
Luo H, Zhang T, Gong N-J, et al. Deep learning–based methods may minimize GBCA dosage in brain MRI. Eur Radiol . 2021;31:6419–6428.
Pasumarthi S, Tamir JI, Christensen S, et al. A generic deep learning model for reduced gadolinium dose in contrast-enhanced brain MRI. Magn Reson Med . 2021;86:1687–1700.
Gong E, Pauly JM, Wintermark M, et al. Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J Magn Reson Imaging . 2018;48:330–340.
Azarfar G, Ko SB, Adams SJ, et al. Applications of deep learning to reduce the need for iodinated contrast media for CT imaging: a systematic review. Int J Comput Assist Radiol Surg . 2023.
Haubold J, Hosch R, Umutlu L, et al. Contrast agent dose reduction in computed tomography with deep learning using a conditional generative adversarial network. Eur Radiol . 2021;31:6087–6095.
Chun J, Chang JS, Oh C, et al. Synthetic contrast-enhanced computed tomography generation using a deep convolutional neural network for cardiac substructure delineation in breast cancer radiation therapy: a feasibility study. Radiat Oncol . 2022;17:83.
Liu J, Tian Y, Ağıldere AM, et al. DyeFreeNet: deep virtual contrast CT synthesis. In: Burgos N, Svoboda D, Wolterink JM, et al, eds. Simulation and Synthesis in Medical Imaging. Lecture Notes in Computer Science . Cham, Switzerland: Springer International Publishing; 2020:80–89.
Seo M, Kim D, Lee K, et al. Neural contrast enhancement of CT image. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) . 2021:3972–3981.
Haubold J, Jost G, Theysohn JM, et al. Contrast media reduction in computed tomography with deep learning using a generative adversarial network in an experimental animal study. Invest Radiol . 2022;57:696–703.
Haubold J, Zensen S, Hosch R, et al. Individualized scan protocols for CT angiography: an animal study for contrast media or radiation dose optimization. Eur Radiol Exp . 2023;7:24.
Danieli L, Riccitelli GC, Distefano D, et al. Brain tumor-enhancement visualization and morphometric assessment: a comparison of MPRAGE, SPACE, and VIBE MRI techniques. Am J Neuroradiol . 2019;40:1140–1148.
Loevner LA, Kolumban B, Hutóczki G, et al. Efficacy and safety of gadopiclenol for contrast-enhanced MRI of the central nervous system: the PICTURE randomized clinical trial. Invest Radiol . 2023;58:307–313.
Lohrke J, Berger M, Frenzel T, et al. Preclinical profile of gadoquatrane: a novel tetrameric, macrocyclic high relaxivity gadolinium-based contrast agent. Invest Radiol . 2022;57:629–638.
Chubb H, Aziz S, Karim R, et al. Optimization of late gadolinium enhancement cardiovascular magnetic resonance imaging of post-ablation atrial scar: a cross-over study. J Cardiovasc Magn Reson . 2018;20:30.
Kribben A, Witzke O, Hillen U, et al. Nephrogenic systemic fibrosis: pathogenesis, diagnosis, and therapy. J Am Coll Cardiol . 2009;53:1621–1628.
Prince MR, Zhang HL, Roditi GH, et al. Risk factors for NSF: a literature review. J Magn Reson Imaging . 2009;30:1298–1308.
Radbruch A. Are some agents less likely to deposit gadolinium in the brain? Magn Reson Imaging . 2016;34:1351–1354.
Kanda T, Ishii K, Kawaguchi H, et al. High signal intensity in the dentate nucleus and globus pallidus on unenhanced T1-weighted MR images: relationship with increasing cumulative dose of a gadolinium-based contrast material. Radiology . 2014;270:834–841.
Chandrashekar A, Handa A, Lapolla P, et al. A deep learning approach to visualize aortic aneurysm morphology without the use of intravenous contrast agents. Ann Surg . 2023;277:e449–e459.
Choi JW, Cho YJ, Ha JY, et al. Generating synthetic contrast enhancement from non-contrast chest computed tomography using a generative adversarial network. Sci Rep . 2021;11:20403.
Ristea N-C, Miron A-I, Savencu O, et al. CyTran: a cycle-consistent transformer with multi-level consistency for non-contrast to contrast CT translation. Neurocomputing . 2023;538:126211.
Jayachandran Preetha C, Meredig H, Brugnara G, et al. Deep-learning–based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study. Lancet Digit Health . 2021;3:e784–e794.
Kleesiek J, Morshuis JN, Isensee F, et al. Can virtual contrast enhancement in brain MRI replace gadolinium?: a feasibility study. Invest Radiol . 2019;54:653–660.
Narayana PA, Coronado I, Sujit SJ, et al. Deep learning for predicting enhancing lesions in multiple sclerosis from noncontrast MRI. Radiology . 2020;294:398–404.
Li W, Xiao H, Li T, et al. Virtual contrast-enhanced magnetic resonance images synthesis for patients with nasopharyngeal carcinoma using multimodality-guided synergistic neural network. Int J Radiat Oncol Biol Phys . 2022;112:1033–1044.
ESUR Guidelines on Contrast Agents | esur.org . Available at: https://www.esur.org/esur-guidelines-on-contrast-agents/ . Accessed June 24, 2023.
Semelka RC, Ramalho M. Gadolinium deposition disease: current state of knowledge and expert opinion. Invest Radiol . 2023;58:523–529.
Kim ES, Chang JH, Choi HS, et al. Diagnostic yield of double-dose gadobutrol in the detection of brain metastasis: intraindividual comparison with double-dose gadopentetate dimeglumine. AJNR Am J Neuroradiol . 2010;31:1055–1058.
Subedi KS, Takahashi T, Yamano T, et al. Usefulness of double dose contrast-enhanced magnetic resonance imaging for clear delineation of gross tumor volume in stereotactic radiotherapy treatment planning of metastatic brain tumors: a dose comparison study. J Radiat Res . 2013;54:135–139.
Rovira A, Auger C, Huerga E, et al. Cumulative dose of macrocyclic gadolinium-based contrast agent improves detection of enhancing lesions in patients with multiple sclerosis. AJNR Am J Neuroradiol . 2017;38:1486–1493.
Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, They Are Data. Radiology . 2016;278:563–577.
Mallio CA, Radbruch A, Deike-Hofmann K, et al. Artificial intelligence to reduce or eliminate the need for gadolinium-based contrast agents in brain and cardiac MRI: a literature review. Invest Radiol . 2023. doi:10.1097/RLI.0000000000000983.
doi: 10.1097/RLI.0000000000000983
Zhou Z, Gao Y, Zhang W, et al. Artificial intelligence–based full aortic CT angiography imaging with ultra-low-dose contrast medium: a preliminary study. Eur Radiol . 2023;33:678–689.
Isola P, Zhu J, Zhou T, et al. Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 2017:5967–5976.
Zhu J, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) . 2017:2242–2251.
Yamashita R, Nishio M, Do RKG, et al. Convolutional neural networks: an overview and application in radiology. Insights Imaging . 2018;9:611–629.
Ajit A, Acharya K, Samanta A. A review of convolutional neural networks. In: 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE) . 2020:1–5.
Artificial intelligence and machine learning (AI/ML)–enabled medical devices. FDA . 2022. Available at: https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices . Accessed June 14, 2023.
Good machine learning practice for medical device development: guiding principles. FDA . 2022. Available at: https://www.fda.gov/medical-devices/software-medical-device-samd/good-machine-learning-practice-medical-device-development-guiding-principles . Accessed June 15, 2023.
Charilaou P, Battat R. Machine learning models and over-fitting considerations. World J Gastroenterol . 2022;28:605–607.
Cohen JP, Luck M, Honari S. How to cure cancer (in images) with unpaired image translation. 2018. Available at: https://openreview.net/forum?id=SJIA3pijM . Accessed February 9, 2020.
Parakh A, Lennartz S, An C, et al. Dual-energy CT images: pearls and pitfalls. Radiographics . 2021;41:98–119.
Obmann MM, Kelsch V, Cosentino A, et al. Interscanner and intrascanner comparison of virtual unenhanced attenuation values derived from twin beam dual-energy and dual-source, dual-energy computed tomography. Invest Radiol . 2019;54:1–6.
Martens B, Jost G, Mihl C, et al. Individualized scan protocols in abdominal computed tomography: radiation versus contrast media dose optimization. Invest Radiol . 2021;57:353–358.
Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging . 2013;26:1045–1057.
Liu BP, Rosenberg M, Saverio P, et al. Clinical efficacy of reduced-dose gadobutrol versus standard-dose gadoterate for contrast-enhanced MRI of the CNS: an international multicenter prospective crossover trial (LEADER-75). AJR Am J Roentgenol . 2021;217:1195–1205.
Dhariwal P, Nichol A. Diffusion models beat GANs on image synthesis. 2021. Available at: http://arxiv.org/abs/2105.05233 . Accessed June 29, 2023.