TY  - CONF
AU  - Pinetz, Thomas
AU  - Kobler, Erich
AU  - Haase, Robert
AU  - Deike-Hofmann, Katerina
AU  - Radbruch, Alexander
AU  - Effland, Alexander
A3  - Greenspan, Hayit
A3  - Madabhushi, Anant
A3  - Mousavi, Parvin
A3  - Salcudean, Septimiu
A3  - Duncan, James
A3  - Syeda-Mahmood, Tanveer
A3  - Taylor, Russell
TI  - Faithful Synthesis of Low-Dose Contrast-Enhanced Brain MRI Scans Using Noise-Preserving Conditional GANs
VL  - 14221
CY  - Cham
PB  - Springer Nature Switzerland
M1  - DZNE-2023-01039
SN  - 978-3-031-43894-3 (print)
T2  - Lecture Notes in Computer Science
SP  - 607 - 617
PY  - 2023
AB  - Today Gadolinium-based contrast agents (GBCA) are indispensable in Magnetic Resonance Imaging (MRI) for diagnosing various diseases. However, GBCAs are expensive and may accumulate in patients with potential side effects, thus dose-reduction is recommended. Still, it is unclear to which extent the GBCA dose can be reduced while preserving the diagnostic value – especially in pathological regions. To address this issue, we collected brain MRI scans at numerous non-standard GBCA dosages and developed a conditional GAN model for synthesizing corresponding images at fractional dose levels. Along with the adversarial loss, we advocate a novel content loss function based on the Wasserstein distance of locally paired patch statistics for the faithful preservation of noise. Our numerical experiments show that conditional GANs are suitable for generating images at different GBCA dose levels and can be used to augment datasets for virtual contrast models. Moreover, our model can be transferred to openly available datasets such as BraTS, where non-standard GBCA dosage images do not exist. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
T2  - 26th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2023
CY  - 8 Oct 2023 - 12 Oct 2023, Vancouver (Canada)
Y2  - 8 Oct 2023 - 12 Oct 2023
M2  - Vancouver, Canada
LB  - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
DO  - DOI:10.1007/978-3-031-43895-0_57
UR  - https://pub.dzne.de/record/265790
ER  -