TY  - CONF
AU  - Yawson, Ama Katseena
AU  - Paul, Katharina Maria
AU  - Beyer, Cedric
AU  - Dorsch, Stefan
AU  - Klüter, Sebastian
AU  - Welzel, Thomas
AU  - Seidensaal, Katharina
AU  - Debus, Jürgen
AU  - Jäkel, Oliver
AU  - Giske, Kristina
A3  - Waiter, Gordon
A3  - Lambrou, Tryphon
A3  - Leontidis, Georgios
A3  - Oren, Nir
A3  - Morris, Teresa
A3  - Gordon, Sharon
TI  - Pseudo-SPR Map Generation from MRI Using U-Net Architecture for Ion Beam Therapy Application
VL  - 14122
CY  - Cham
PB  - Springer Nature Switzerland
M1  - DKFZ-2023-02516
SN  - 978-3-031-48592-3
T2  - Lecture Notes in Computer Science
PY  - 2024
N1  -   Medical Image Understanding and Analysis: 257–267
AB  - Stopping power ratio (SPR) maps are needed for dose deposition calculations and are typically estimated from single energy CT (SECT) in clinical routine. SECT-based SPR conversion leads to large variability due to the one-to-one relationship assumed by the conversion method. Dual-energy CT (DECT) involving the acquisition of two energy spectra captures both material-specific information and tissue characterization which is essential for an accurate SPR map conversion. The goal of this study is to train a U-Net architecture to generate pseudo-SPR map from MRI (Dixon) using a DECT-converted SPR map. The model performance was validated using Head </td><td width="150">
AB  -  Neck cohort of 16 patients with paired MRI and SPR maps. The proposed solution achieved a mean absolute error (MAE) and peak-signal-to-noise-ratio (PSNR) of 19.41 ± 8.67 HU and 58.76 ± 2.17 dB respectively for all test cases. From observation, the sequential incorporation of different Dixon MRI images such as fat-suppressed and water-suppressed yielded an accurate pseudo-SPR map which is comparable to its corresponding target SPR map. Furthermore, bone delineation integrated as additional channel to Dixon MRI sequence demonstrated an enhanced bone identification on predicted pseudo-SPR map. As future direction, we would like to extend this approach to a clinical SPR map which will enable dosimetric analysis of clinical target volume (CTV) to be possible in treatment planning application for ion beam therapy.
T2  - 27th Conference on Medical Image Understanding and Analysis 2023
CY  - 19 Jul 2023 - 21 Jul 2023, Aberdeeen (UK)
Y2  - 19 Jul 2023 - 21 Jul 2023
M2  - Aberdeeen, UK
LB  - PUB:(DE-HGF)3 ; PUB:(DE-HGF)26
DO  - DOI:10.1007/978-3-031-48593-0_19
UR  - https://inrepo02.dkfz.de/record/285708
ER  -