Artificial T1-Weighted Postcontrast Brain MRI: A Deep Learning Method for Contrast Signal Extraction

Robert Haase; Thomas Pinetz; Erich Kobler; Zeynep Bendella; Christian Gronemann; Daniel Paech; Alexander Radbruch; Alexander Effland; Katerina Deike

doi:10.1097/RLI.0000000000001107

Artificial T1-Weighted Postcontrast Brain MRI: A Deep Learning Method for Contrast Signal Extraction

Invest Radiol. 2024 Jul 30. doi: 10.1097/RLI.0000000000001107. Online ahead of print.

Authors

Robert Haase¹, Thomas Pinetz, Erich Kobler, Zeynep Bendella, Christian Gronemann, Daniel Paech, Alexander Radbruch, Alexander Effland, Katerina Deike

Affiliation

¹ From the Clinic of Neuroradiology, University Hospital Bonn, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany (R.H., E.K., Z.B., C.G., D.P., A.R., K.D.); Institute of Applied Mathematics, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany (T.P., A.E.); Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA (D.P.); and German Center for Neurodegenerative Diseases (DZNE), Helmholtz Association of German Research Centers, Bonn, Germany (A.R., K.D.).

PMID: 39074258
DOI: 10.1097/RLI.0000000000001107

Abstract

Objectives: 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.

Materials and methods: 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.

Results: 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).

Conclusions: 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.