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
Typ-2-Diabetes und Adipositas Klimawandel und Gesundheit Neues aus dem Markt 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 Patientenratgeber
Erweiterte Suche
Anmelden
nach oben
European Radiology
Erschienen in:

18.03.2021 | Neuro

Deep learning–based methods may minimize GBCA dosage in brain MRI

verfasst von: Huanyu Luo, Tao Zhang, Nan-Jie Gong, Jonthan Tamir, Srivathsa Pasumarthi Venkata, Cheng Xu, Yunyun Duan, Tao Zhou, Fuqing Zhou, Greg Zaharchuk, Jing Xue, Yaou Liu

Erschienen in: European Radiology | Ausgabe 9/2021

Einloggen, um Zugang zu erhalten

Abstract

Objectives

To evaluate the clinical performance of a deep learning (DL)–based method for brain MRI exams with reduced gadolinium-based contrast agent (GBCA) dose to provide better understanding of the readiness and limitations of this method.

Methods

Eighty-three consecutive patients (from March 2019 to August 2019) who underwent brain contrast-enhanced (CE) MRI were included. Three 3D T1-weighted images with zero-dose, low-dose (10%), and full-dose (100%) GBCA were collected. The first 30 cases were used to train a DL model to synthesize the full-dose GBCA images from the zero-dose and low-dose image pairs. The remaining 53 cases were used for testing. The enhancement pattern, number, and location of enhancing lesions were recorded. Overall image quality, image signal noise ratio (SNR), lesion conspicuity, and lesion enhancement were assessed.

Results

Lesion detection from the DL-synthesized CE-MRI image accurately matched those from the true full-dose CE-MRI images in 48 of 53 cases (90.6%). The DL method identified the lesions in 34 of 36 cases (94.4%) with a single enhanced lesion and all lesions in 3 of 6 cases (50.0%) in cases with multiple enhancing lesions. The agreement between synthesized and true full-dose CE-MRI images were 0.73, 0.63, 0.89, and 0.87 for image quality, image SNR, lesion conspicuity, and lesion enhancement, respectively.

Conclusions

The proposed DL method is a feasible way to minimize the dosage of GBCAs in brain MRI without sacrificing the diagnostic information. Missing enhancement of small lesions in patients with multiple lesions was observed, requiring improvements in algorithms or dosage design.

Key Points

• This study evaluated the clinical performance of a DL-based reconstruction method for significant dose reduction in GBCA contrast-enhanced MRI exams.
• The proposed DL method has the potential to satisfy the routine radiological diagnosis needs in certain clinical applications.
Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Runge VM (2016) Safety of the gadolinium-based contrast agents for magnetic resonance imaging, focusing in part on their accumulation in the brain and especially the dentate nucleus. Invest Radiol 51:273–279CrossRefPubMed
2.
Runge VM (2017) Critical questions regarding gadolinium deposition in the brain and body after injections of the gadolinium-based contrast agents, safety, and clinical recommendations in consideration of the EMA’s Pharmacovigilance and Risk Assessment Committee recommendation for suspension of the marketing authorizations for 4 linear agents. Invest Radiol 52:317–323CrossRefPubMed
3.
Runge VM (2000) Safety of approved MR contrast media for intravenous injection. J Magn Reson Imaging 12:205–213CrossRefPubMed
4.
Morgan DE, Spann JS, Lockhart ME, Winningham B, Bolus DN (2011) Assessment of adverse reaction rates during gadoteridol-enhanced MR imaging in 28,078 patients. Radiology 259:109–116CrossRefPubMed
5.
McDonald JS, Hunt CH, Kolbe AB et al (2019) Acute adverse events following gadolinium-based contrast agent administration: a single-center retrospective study of 281 945 injections. Radiology 292:620–627CrossRefPubMed
6.
Grobner T (2006) Gadolinium--a specific trigger for the development of nephrogenic fibrosing dermopathy and nephrogenic systemic fibrosis? Nephrol Dial Transplant 21:1104–1108CrossRefPubMed
7.
Sadowski EA, Bennett LK, Chan MR et al (2007) Nephrogenic systemic fibrosis: risk factors and incidence estimation. Radiology 243:148–157CrossRefPubMed
8.
Rydahl C, Thomsen HS, Marckmann P (2008) High prevalence of nephrogenic systemic fibrosis in chronic renal failure patients exposed to gadodiamide, a gadolinium-containing magnetic resonance contrast agent. Invest Radiol 43:141–144CrossRefPubMed
9.
Thomsen HS, Morcos SK, Almen T et al (2013) Nephrogenic systemic fibrosis and gadolinium-based contrast media: updated ESUR Contrast Medium Safety Committee guidelines. Eur Radiol 23:307–318CrossRefPubMed
10.
Kanda T, Ishii K, Kawaguchi H, Kitajima K, Takenaka D (2014) 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 270:834–841CrossRefPubMed
11.
Radbruch A, Weberling LD, Kieslich PJ et al (2015) Gadolinium retention in the dentate nucleus and globus pallidus is dependent on the class of contrast agent. Radiology 275:783–791CrossRefPubMed
12.
McDonald RJ, McDonald JS, Kallmes DF et al (2017) Gadolinium deposition in human brain tissues after contrast-enhanced MR imaging in adult patients without intracranial abnormalities. Radiology 285:546–554CrossRefPubMed
13.
Kanda T, Fukusato T, Matsuda M et al (2015) Gadolinium-based contrast agent accumulates in the brain even in subjects without severe renal dysfunction: evaluation of autopsy brain specimens with inductively coupled plasma mass spectroscopy. Radiology 276:228–232CrossRefPubMed
14.
Ramalho J, Castillo M, AlObaidy M et al (2015) High signal intensity in globus pallidus and dentate nucleus on unenhanced T1-weighted MR images: evaluation of two linear gadolinium-based contrast agents. Radiology 276:836–844CrossRefPubMed
15.
Weberling LD, Kieslich PJ, Kickingereder P et al (2015) Increased signal intensity in the dentate nucleus on unenhanced T1-weighted images after gadobenate dimeglumine administration. Invest Radiol 50:743–748CrossRefPubMed
16.
Radbruch A, Weberling LD, Kieslich PJ et al (2015) High-signal intensity in the dentate nucleus and globus pallidus on unenhanced T1-weighted images: evaluation of the macrocyclic gadolinium-based contrast agent gadobutrol. Invest Radiol 50:805–810CrossRefPubMed
17.
Radbruch A, Weberling LD, Kieslich PJ et al (2016) Intraindividual analysis of signal intensity changes in the dentate nucleus after consecutive serial applications of linear and macrocyclic gadolinium-based contrast agents. J Investig Radiol 51:683–690CrossRef
18.
Bjørnerud A, Vatnehol SAS, Larsson C, Due-Tønnessen P, Hol PK, Groote IR (2017) Signal enhancement of the dentate nucleus at unenhanced MR imaging after very high cumulative doses of the macrocyclic gadolinium-based contrast agent gadobutrol: an observational study. Radiology 285:434–444CrossRefPubMed
19.
McDonald RJ, McDonald JS, Kallmes DF et al (2015) Intracranial gadolinium deposition after contrast-enhanced MR imaging. Radiology 275:772–782CrossRefPubMed
20.
Ryu YJ, Choi YH, Cheon JE et al (2018) Pediatric brain: gadolinium deposition in dentate nucleus and globus pallidus on unenhanced T1-weighted images is dependent on the type of contrast agent. Invest Radiol 53:246–255CrossRefPubMed
21.
Dekkers IA, Roos R, van der Molen AJ (2018) Gadolinium retention after administration of contrast agents based on linear chelators and the recommendations of the European Medicines Agency. Eur Radiol 28:1579–1584CrossRefPubMed
22.
Litjens G, Kooi T, Bejnordi BE et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88CrossRefPubMed
23.
24.
Choy G, Khalilzadeh O, Michalski M et al (2018) Current applications and future impact of machine learning in radiology. Radiology 288:318–328CrossRefPubMed
25.
Greffier J, Hamard A, Pereira F et al (2020) Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study. Eur Radiol 30:3951–3959CrossRefPubMed
26.
Weston AD, Korfiatis P, Kline TL et al (2019) Automated abdominal segmentation of CT scans for body composition analysis using deep learning. Radiology 290:669–679CrossRefPubMed
27.
Xia KJ, Yin HS, Zhang YD (2018) Deep semantic segmentation of kidney and space-occupying lesion area based on SCNN and ResNet models combined with SIFT-flow algorithm. J Med Syst 43:2CrossRefPubMed
28.
Deniz CM, Xiang S, Hallyburton RS et al (2018) Segmentation of the proximal femur from MR images using deep convolutional neural networks. Sci Rep 8:16485CrossRefPubMedPubMedCentral
29.
Kooi T, Litjens G, van Ginneken B et al (2017) Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal 35:303–312CrossRefPubMed
30.
Becker AS, Marcon M, Ghafoor S, Wurnig MC, Frauenfelder T, Boss A (2017) Deep learning in mammography: diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer. Invest Radiol 52:434–440CrossRefPubMed
31.
Lakhani P, Sundaram B (2017) Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284:574–582CrossRefPubMed
32.
Yasaka K, Akai H, Abe O, Kiryu S (2018) Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: a preliminary study. Radiology 286:887–896CrossRefPubMed
33.
Gong E, Pauly JM, Wintermark M, Zaharchuk G (2018) Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J Magn Reson Imaging 48:330–340CrossRefPubMed
34.
Venkata SP, Tamir J, Gong E, Zaharchuk G, Zhang T (2020) Toward a site and scanner-generic deep learning model for reduced gadolinium dose in contrast-enhanced brain MRI. In: Proceedings of International Society for Magnetic Resonance in Medicine, Virtual Annual Meeting, August. 2020
35.
Essig M, Dinkel J, Gutierrez JE (2012) Use of contrast media in neuroimaging. Magn Reson Imaging Clin N Am 20:633–648CrossRefPubMed
36.
Yuh WT, Fisher DJ, Engelken JD et al (1991) MR evaluation of CNS tumors: dose comparison study with gadopentetate dimeglumine and gadoteridol. Radiology 180:485–491CrossRefPubMed
37.
Yuh WT, Engelken JD, Muhonen MG, Mayr NA, Fisher DJ, Ehrhardt JC (1992) Experience with high-dose gadolinium MR imaging in the evaluation of brain metastases. AJNR Am J Neuroradiol 13:335–345PubMedPubMedCentral
38.
Vaneckova M, Herman M, Smith MP et al (2015) The benefits of high relaxivity for brain tumor imaging: results of a multicenter intraindividual crossover comparison of gadobenate dimeglumine with gadoterate meglumine (The BENEFIT Study). AJNR Am J Neuroradiol 36:1589–1598
39.
Kleesiek J, Morshuis JN, Isensee F et al (2019) Can virtual contrast enhancement in brain MRI replace gadolinium?: a feasibility study. Invest Radiol 54:653–660CrossRefPubMed
Metadaten
Titel
Deep learning–based methods may minimize GBCA dosage in brain MRI
verfasst von
Huanyu Luo
Tao Zhang
Nan-Jie Gong
Jonthan Tamir
Srivathsa Pasumarthi Venkata
Cheng Xu
Yunyun Duan
Tao Zhou
Fuqing Zhou
Greg Zaharchuk
Jing Xue
Yaou Liu
Publikationsdatum
18.03.2021
Verlag
Springer Berlin Heidelberg
Erschienen in
European Radiology / Ausgabe 9/2021
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI
https://doi.org/10.1007/s00330-021-07848-3

Weitere Artikel der Ausgabe 9/2021

T2 relaxation time shortening in the cochlea of patients with sudden sensory neuronal hearing loss: a retrospective study using quantitative synthetic magnetic resonance imaging

  • Head and Neck

Targetoid appearance on T2-weighted imaging and signs of tumor vascular involvement: diagnostic value for differentiating HCC from other primary liver carcinomas

  • Hepatobiliary-Pancreas

How to improve image quality of DWI of the prostate—enema or catheter preparation?

  • Open Access
  • Magnetic Resonance

Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT

  • Musculoskeletal

AI-based detection and classification of distal radius fractures using low-effort data labeling: evaluation of applicability and effect of training set size

  • Open Access
  • Musculoskeletal

A novel personalized dosimetry method for endovascular aneurysm repair (EVAR) procedures

  • Interventional

Neu im Fachgebiet Radiologie

KI-gestütztes Mammografiescreening überzeugt im Praxistest

Mit dem Einsatz künstlicher Intelligenz lässt sich die Detektionsrate im Mammografiescreening offenbar deutlich steigern. Mehr unnötige Zusatzuntersuchungen sind laut der Studie aus Deutschland nicht zu befürchten.

Stumme Schlaganfälle − ein häufiger Nebenbefund im Kopf-CT?

In 4% der in der Notfallambulanz initiierten zerebralen Bildgebung sind „alte“ Schlaganfälle zu erkennen. Gar nicht so selten handelt es sich laut einer aktuellen Studie dabei um unbemerkte Insulte. Bietet sich hier womöglich die Chance auf ein effektives opportunistisches Screening?

Die elektronische Patientenakte kommt: Das sollten Sie jetzt wissen

Am 15. Januar geht die „ePA für alle“ zunächst in den Modellregionen an den Start. Doch schon bald soll sie in allen Praxen zum Einsatz kommen. Was ist jetzt zu tun? Was müssen Sie wissen? Wir geben in einem FAQ Antworten auf 21 Fragen.

Stören weiße Wände und viel Licht die Bildqualitätskontrolle?

Wenn es darum geht, die technische Qualität eines Mammogramms zu beurteilen, könnten graue Wandfarbe und reduzierte Beleuchtung im Bildgebungsraum von Vorteil sein. Darauf deuten zumindest Ergebnisse einer kleinen Studie hin. 

Update Radiologie

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

Newsletter bestellen
Bildnachweise