Impact of non-contrast-enhanced imaging input sequences on the generation of virtual contrast-enhanced breast MRI scans using neural network.

Artificial intelligence Breast imaging Magnetic resonance imaging Neural network

Journal

European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774

Informations de publication

Date de publication:
25 Oct 2024
Historique:
received: 07 05 2024
accepted: 31 08 2024
revised: 25 06 2024
medline: 26 10 2024
pubmed: 26 10 2024
entrez: 25 10 2024
Statut: aheadofprint

Résumé

To investigate how different combinations of T1-weighted (T1w), T2-weighted (T2w), and diffusion-weighted imaging (DWI) impact the performance of virtual contrast-enhanced (vCE) breast MRI. The IRB-approved, retrospective study included 1064 multiparametric breast MRI scans (age: 52 ± 12 years) obtained from 2017 to 2020 (single site, two 3-T MRI). Eleven independent neural networks were trained to derive vCE images from varying input combinations of T1w, T2w, and multi-b-value DWI sequences (b-value = 50-1500 s/mm The independent test set consisted of 187 cases. The quantitative metrics significantly improved in target findings when multi-b-value DWI sequences were included during vCE training (p < 0.05). Non-significant effects (p > 0.05) were observed for the quantitative metrics on the full breast volume when comparing input combinations including T1w. Using T1w and DWI acquisitions during vCE training is necessary to achieve high satisfaction with contrast/SNR and good conspicuity of the enhancing findings. The input combination of T1w, T2w, and DWI sequences with three b-values showed the best qualitative performance. vCE breast MRI performance is significantly influenced by input sequences. Quantitative metrics and visual quality of vCE images significantly benefit when multi b-value DWI is added to morphologic T1w-/T2w sequences as input for model training. Question How do different MRI sequences impact the performance of virtual contrast-enhanced (vCE) breast MRI? Findings The input combination of T1-weighted, T2-weighted, and diffusion-weighted imaging sequences with three b-values showed the best qualitative performance. Clinical relevance While in the future neural networks providing virtual contrast-enhanced images might further improve accessibility to breast MRI, the significant influence of input data needs to be considered during translational research.

Identifiants

pubmed: 39455455
doi: 10.1007/s00330-024-11142-3
pii: 10.1007/s00330-024-11142-3
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Subventions

Organisme : Bayerisches Staatsministerium für Wissenschaft und Kunst
ID : bidt Graduate Center for Postdocs

Informations de copyright

© 2024. The Author(s).

Références

Mann RM, Cho N, Moy L (2019) Breast MRI: state of the art. Radiology 292:520–536
doi: 10.1148/radiol.2019182947 pubmed: 31361209
Mann RM, Kuhl CK, Moy L (2019) Contrast-enhanced MRI for breast cancer screening. J Magn Reson Imaging 50:377–390
doi: 10.1002/jmri.26654 pubmed: 30659696 pmcid: 6767440
Mann RM, Athanasiou A, Baltzer PAT et al (2022) Breast cancer screening in women with extremely dense breasts recommendations of the European Society of Breast Imaging (EUSOBI). Eur Radiol 32:4036–4045
doi: 10.1007/s00330-022-08617-6 pubmed: 35258677 pmcid: 9122856
Bakker MF, de Lange SV, Pijnappel RM et al (2019) Supplemental MRI screening for women with extremely dense breast tissue. N Engl J Med 381:2091–2102
doi: 10.1056/NEJMoa1903986 pubmed: 31774954
Kuhl CK, Schmutzler RK, Leutner CC et al (2000) Breast MR imaging screening in 192 women proved or suspected to be carriers of a breast cancer susceptibility gene: preliminary results. Radiology 215:267–279
doi: 10.1148/radiology.215.1.r00ap01267 pubmed: 10751498
Griebsch I, Brown J, Boggis C et al (2006) Cost-effectiveness of screening with contrast enhanced magnetic resonance imaging vs X-ray mammography of women at a high familial risk of breast cancer. Br J Cancer 95:801–810
doi: 10.1038/sj.bjc.6603356 pubmed: 17016484 pmcid: 2360541
Taneja C, Edelsberg J, Weycker D, Guo A, Oster G, Weinreb J (2009) Cost effectiveness of breast cancer screening with contrast-enhanced MRI in high-risk women. J Am Coll Radiol 6:171–179
doi: 10.1016/j.jacr.2008.10.003 pubmed: 19248993
Plaza M, Cole D, Sanchez-Gonzalez MA, Starr CJ (2021) Patient throughput times for supplemental breast cancer screening exams. Arch Breast Cancer 8:21–28
Borthakur A, Weinstein SP, Schnall MD, Conant EF (2019) Comparison of study activity times for “full” versus “fast MRI” for breast cancer screening. J Am Coll Radiol 16:1046–1051
doi: 10.1016/j.jacr.2019.01.004 pubmed: 30975607
Tollens F, Baltzer PA, Dietzel M et al (2022) Economic potential of abbreviated breast MRI for screening women with dense breast tissue for breast cancer. Eur Radiol 32:7409–7419
doi: 10.1007/s00330-022-08777-5 pubmed: 35482122 pmcid: 9668927
Tollens F, Baltzer PA, Dietzel M, Rübenthaler J, Froelich MF, Kaiser CG (2021) Cost-effectiveness of digital breast tomosynthesis vs. abbreviated breast MRI for screening women with intermediate risk of breast cancer—how low-cost must MRI be? Cancers (Basel) 13:1241
doi: 10.3390/cancers13061241 pubmed: 33808955
Mann RM, van Zelst JC, Vreemann S, Mus RD (2019) Is ultrafast or abbreviated breast MRI ready for prime time? Curr Breast Cancer Rep 11:9–16
doi: 10.1007/s12609-019-0300-8
McDonald RJ, Weinreb JC, Davenport MS (2022) Symptoms associated with gadolinium exposure (SAGE): a suggested term. Radiology 302:270–273
doi: 10.1148/radiol.2021211349 pubmed: 34783590
Wang P, Nie P, Dang Y et al (2021) Synthesizing the first phase of dynamic sequences of breast MRI for enhanced lesion identification. Front Oncol 11:792516
doi: 10.3389/fonc.2021.792516 pubmed: 34950593 pmcid: 8689139
Kim E, Cho H-H, Kwon J, Oh Y-T, Ko ES, Park H (2022) Tumor-attentive segmentation-guided GAN for synthesizing breast contrast-enhanced MRI without contrast agents. IEEE J Transl Eng Health Med 11:32–43
doi: 10.1109/JTEHM.2022.3221918 pubmed: 36478773
Muller-Franzes G, Huck L, Tayebi Arasteh S et al (2023) Using machine learning to reduce the need for contrast agents in breast MRI through synthetic images. Radiology. https://doi.org/10.1148/radiol.222211:222211
Chung M, Calabrese E, Mongan J et al (2022) Deep learning to simulate contrast-enhanced breast MRI of invasive breast cancer. Radiology. https://doi.org/10.1148/radiol.213199:213199
Zhang T, Han L, D’Angelo A et al (2023) Synthesis of contrast-enhanced breast MRI using T1- and multi-b-value DWI-based hierarchical fusion network with attention mechanism. Springer, Cham, pp 79–88 https://doi.org/10.1007/978-3-031-43990-2_8
Kapsner LA, Balbach EL, Folle L et al (2023) Image quality assessment using deep learning in high b-value diffusion-weighted breast MRI. Sci Rep 13:10549
doi: 10.1038/s41598-023-37342-3 pubmed: 37386021 pmcid: 10310703
Kapsner LA, Ohlmeyer S, Folle L et al (2022) Automated artifact detection in abbreviated dynamic contrast-enhanced (DCE) MRI-derived maximum intensity projections (MIPs) of the breast. Eur Radiol. https://doi.org/10.1007/s00330-022-08626-5
Ohlmeyer S, Laun FB, Bickelhaupt S et al (2021) Ultra-high b-value diffusion-weighted imaging-based abbreviated protocols for breast cancer detection. Invest Radiol 56:629–636
doi: 10.1097/RLI.0000000000000784 pubmed: 34494995
Baltzer P, Mann RM, Iima M et al (2020) Diffusion-weighted imaging of the breast—a consensus and mission statement from the EUSOBI International Breast Diffusion-Weighted Imaging working group. Eur Radiol 30:1436–1450
doi: 10.1007/s00330-019-06510-3 pubmed: 31786616
Bickelhaupt S, Tesdorff J, Laun FB et al (2017) Independent value of image fusion in unenhanced breast MRI using diffusion-weighted and morphological T2-weighted images for lesion characterization in patients with recently detected BI-RADS 4/5 x-ray mammography findings. Eur Radiol 27:562–569
doi: 10.1007/s00330-016-4400-9 pubmed: 27193776
Telegrafo M, Rella L, Stabile Ianora AA, Angelelli G, Moschetta M (2015) Unenhanced breast MRI (STIR, T2-weighted TSE, DWIBS): an accurate and alternative strategy for detecting and differentiating breast lesions. Magn Reson Imaging 33:951–955
doi: 10.1016/j.mri.2015.06.002 pubmed: 26117691
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600–612
doi: 10.1109/TIP.2003.819861 pubmed: 15376593
Morley SK, Brito TV, Welling DT (2018) Measures of model performance based on the log accuracy ratio. Space Weather 16:69–88
doi: 10.1002/2017SW001669
Scherpenzeel A (2002) Why use 11-point scales. Swiss Househ Panel 9:2008
Nečasová T, Burgos N, Svoboda D (2022) Validation and evaluation metrics for medical and biomedical image synthesis. In: Biomedical image synthesis and simulation. The MICCAI Society book Series. Elsevier, pp 573–600 https://doi.org/10.1016/B978-0-12-824349-7.00032-3
van Lohuizen Q, Roest C, Simonis FF et al (2024) Assessing deep learning reconstruction for faster prostate MRI: visual vs. diagnostic performance metrics. Eur Radiol. https://doi.org/10.1007/s00330-024-10771-y
McCullum L, Wood J, Gule-Monroe M et al (2023) The use of quantitative metrics and machine learning to predict radiologist interpretations of MRI image quality and artifacts. Preprint at https://doi.org/10.48550/arXiv.2311.05412
Huyskens DP, Maingon P, Vanuytsel L et al (2009) A qualitative and a quantitative analysis of an auto-segmentation module for prostate cancer. Radiother Oncol 90:337–345
doi: 10.1016/j.radonc.2008.08.007 pubmed: 18812252
Sherer MV, Lin D, Elguindi S et al (2021) Metrics to evaluate the performance of auto-segmentation for radiation treatment planning: a critical review. Radiother Oncol 160:185–191
doi: 10.1016/j.radonc.2021.05.003 pubmed: 33984348 pmcid: 9444281
Zimmermann F, Korzowski A, Breitling J et al (2020) A novel normalization for amide proton transfer CEST MRI to correct for fat signal-induced artifacts: application to human breast cancer imaging. Magn Reson Med 83:920–934
doi: 10.1002/mrm.27983 pubmed: 31532006
Zhang S, Seiler S, Wang X et al (2018) CEST-Dixon for human breast lesion characterization at 3 T: a preliminary study. Magn Reson Med 80:895–903
doi: 10.1002/mrm.27079 pubmed: 29322559 pmcid: 5980671
Zaric O, Farr A, Rodriguez EP et al (2019) 7T CEST MRI: a potential imaging tool for the assessment of tumor grade and cell proliferation in breast cancer. Magn Reson Imaging 59:77–87
doi: 10.1016/j.mri.2019.03.004 pubmed: 30880110

Auteurs

Andrzej Liebert (A)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany. andrzej.liebert@uk-erlangen.de.

Hannes Schreiter (H)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Lorenz A Kapsner (LA)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.
Lehrstuhl für Medizinische Informatik, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Jessica Eberle (J)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Chris M Ehring (CM)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Dominique Hadler (D)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Luise Brock (L)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Ramona Erber (R)

Institute of Pathology, Universitätsklinikum Erlangen, Erlangen, Comprehensive Cancer Center Erlangen-EMN, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Julius Emons (J)

Department of Gynecology and Obstetrics, Erlangen University Hospital, Comprehensive Cancer Center Erlangen-EMN, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Frederik B Laun (FB)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Michael Uder (M)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Evelyn Wenkel (E)

Medizinische Fakultät, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.
Radiologie München, München, Germany.

Sabine Ohlmeyer (S)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.

Sebastian Bickelhaupt (S)

Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.
German Cancer Research Center (DKFZ), Heidelberg, Germany.

Classifications MeSH