274031 20250411100000.0 10.1097/RLI.0000000000001107 doi pmid:39074258 pmid 0020-9996 ISSN 1536-0210 ISSN DZNE-2025-00012 English 610 Haase, Robert P:(DE-2719)9001860 0 Artificial T1-Weighted Postcontrast Brain MRI: A Deep Learning Method for Contrast Signal Extraction. [Erscheinungsort nicht ermittelbar] 2025 Ovid article DRIVER Output Types/Journal article DataCite Journal Article journal journal PUB:(DE-HGF)16 1744358340_16420 PUB:(DE-HGF) ARTICLE BibTeX JOURNAL_ARTICLE ORCID Journal Article 0 EndNote Reducing gadolinium-based contrast agents to lower costs, the environmental impact of gadolinium-containing wastewater, and patient exposure is still an unresolved issue. Published methods have never been compared. The purpose of this study was to compare the performance of 2 reimplemented state-of-the-art deep learning methods (settings A and B) and a proposed method for contrast signal extraction (setting C) to synthesize artificial T1-weighted full-dose images from corresponding noncontrast and low-dose images.In this prospective study, 213 participants received magnetic resonance imaging of the brain between August and October 2021 including low-dose (0.02 mmol/kg) and full-dose images (0.1 mmol/kg). Fifty participants were randomly set aside as test set before training (mean age ± SD, 52.6 ± 15.3 years; 30 men). Artificial and true full-dose images were compared using a reader-based study. Two readers noted all false-positive lesions and scored the overall interchangeability in regard to the clinical conclusion. Using a 5-point Likert scale (0 being the worst), they scored the contrast enhancement of each lesion and its conformity to the respective reference in the true image.The average counts of false-positives per participant were 0.33 ± 0.93, 0.07 ± 0.33, and 0.05 ± 0.22 for settings A-C, respectively. Setting C showed a significantly higher proportion of scans scored as fully or mostly interchangeable (70/100) than settings A (40/100, P < 0.001) and B (57/100, P < 0.001), and generated the smallest mean enhancement reduction of scored lesions (-0.50 ± 0.55) compared with the true images (setting A: -1.10 ± 0.98; setting B: -0.91 ± 0.67, both P < 0.001). The average scores of conformity of the lesion were 1.75 ± 1.07, 2.19 ± 1.04, and 2.48 ± 0.91 for settings A-C, respectively, with significant differences among all settings (all P < 0.001).The proposed method for contrast signal extraction showed significant improvements in synthesizing postcontrast images. A relevant proportion of images showing inadequate interchangeability with the reference remains at this dosage. 353 - Clinical and Health Care Research (POF4-353) G:(DE-HGF)POF4-353 POF4-353 POF IV 0 Dataset connected to CrossRef, PubMed, , Journals: pub.dzne.de Contrast Media NLM Chemicals Humans MeSH Deep Learning MeSH Male MeSH Contrast Media MeSH Female MeSH Prospective Studies MeSH Magnetic Resonance Imaging: methods MeSH Middle Aged MeSH Brain: diagnostic imaging MeSH Adult MeSH Pinetz, Thomas 1 Kobler, Erich 2 Bendella, Zeynep P:(DE-2719)9003165 3 dzne Gronemann, Christian 4 Paech, Daniel P:(DE-2719)9001705 5 dzne Radbruch, Alexander P:(DE-2719)9001861 6 dzne Effland, Alexander P:(DE-2719)9002732 7 dzne Deike-Hofmann, Katerina P:(DE-2719)9001745 8 Last author 10.1097/RLI.0000000000001107 Vol. 60, no. 2 PERI:(DE-600)2041543-6 2 105 - 113 Investigative radiology 60 2025 0020-9996 http://pub.dzne.de/record/274031/files/DZNE-2025-00012%20SUP.doc http://pub.dzne.de/record/274031/files/DZNE-2025-00012%20SUP.docx http://pub.dzne.de/record/274031/files/DZNE-2025-00012%20SUP.odt http://pub.dzne.de/record/274031/files/DZNE-2025-00012%20SUP.pdf http://pub.dzne.de/record/274031/files/DZNE-2025-00012_Restricted.pdf http://pub.dzne.de/record/274031/files/DZNE-2025-00012_Restricted.pdf?subformat=pdfa pdfa VDB oai:pub.dzne.de:274031 External Institute I:(DE-HGF)0 Extern 3 P:(DE-2719)9003165 External Institute I:(DE-HGF)0 Extern 5 P:(DE-2719)9001705 Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 6 P:(DE-2719)9001861 External Institute I:(DE-HGF)0 Extern 7 P:(DE-2719)9002732 Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 8 P:(DE-2719)9001745 DE-HGF Gesundheit Neurodegenerative Diseases G:(DE-HGF)POF4-350 G:(DE-HGF)POF4-353 G:(DE-HGF)POF4 G:(DE-HGF)POF4-300 G:(DE-HGF)POF Clinical and Health Care Research 0 2025 Allianz-Lizenz StatID:(DE-HGF)0410 StatID 2023-10-24 ger DBCoverage StatID:(DE-HGF)0300 StatID Medline 2023-10-24 DBCoverage StatID:(DE-HGF)0199 StatID Clarivate Analytics Master Journal List 2023-10-24 DBCoverage StatID:(DE-HGF)1050 StatID BIOSIS Previews 2023-10-24 WoS StatID:(DE-HGF)0113 StatID Science Citation Index Expanded 2023-10-24 DBCoverage StatID:(DE-HGF)0150 StatID Web of Science Core Collection 2023-10-24 DBCoverage StatID:(DE-HGF)1030 StatID Current Contents - Life Sciences 2023-10-24 DBCoverage StatID:(DE-HGF)1190 StatID Biological Abstracts 2023-10-24 DBCoverage StatID:(DE-HGF)0160 StatID Essential Science Indicators 2023-10-24 DBCoverage StatID:(DE-HGF)1110 StatID Current Contents - Clinical Medicine 2023-10-24 JCR StatID:(DE-HGF)0100 StatID INVEST RADIOL : 2022 2023-10-24 DBCoverage StatID:(DE-HGF)0200 StatID SCOPUS 2023-10-24 IF >= 5 StatID:(DE-HGF)9905 StatID INVEST RADIOL : 2022 2023-10-24 I:(DE-2719)5000075 AG Radbruch Clinical Neuroimaging 0 journal VDB I:(DE-2719)5000075 UNRESTRICTED