Abstract
This study aimed to facilitate pseudo-CT synthesis from MRI by normalizing MRI intensity of the same tissue type to a similar intensity level. MRI intensity normalization was conducted through dividing MRI by a shading map, which is a smoothed ratio image between MRI and a three-intensity mask. Regarding pseudo-CT synthesis from MRI, a conversion model based on a three-layer convolutional neural network was trained and validated. Before MRI intensity normalization, the mean value ± standard deviation of fat tissue in 0.35 T chest MRI was 297 ± 73 (coefficient of variation (CV) = 24.58%), which was 533 ± 91 (CV = 17.07%) in 1.5 T abdominal MRI. The corresponding results were 149 ± 32 (CV = 21.48%) and 148 ± 28 (CV = 18.92%) after intensity normalization. With regards to pseudo-CT synthesis from MRI, the differences in mean values between pseudo-CT and real CT were 3, 15, and 12 HU for soft tissue, fat, and lung/air in 0.35 T chest imaging, respectively, while the corresponding results were 3, 14, and 15 HU in 1.5 T abdominal imaging. Overall, the proposed workflow is reliable in pseudo-CT synthesis from MRI and is more practicable in clinical routine practice compared with deep learning methods, which demand a high level of resources for building a conversion model.
Highlights
The integration of MRI into radiotherapy is an important technological development to improve tumor targeting [1,2]
If these pseudo-CT synthesis methods are generalized across different scanners, they could be more embedded within routine practice for either MR-LINAC adaptive plans or PET/MR attenuation correction
As for abdominal imaging for lesion diagnosis, the difference between mean values in pseudo- and real CT was 3, 14, and 15 HU for soft tissue, fat, and air, respectively. These results indicate that the proposed method has substantial reliability in pseudo-CT synthesis for both MRI systems
Summary
The integration of MRI into radiotherapy is an important technological development to improve tumor targeting [1,2]. Several voxel-based methods have been proposed for pseudo-CT synthesis from MRI, such as the bulk-density method, which assigns homogeneous CT numbers to volumes of interest (VOIs) defined on MRI, and learning-based methods, which employ model fitting or statistical learning techniques [8,9,10,11]. Before applying these voxel-based methods, intensity inhomogeneity in MRI, which arises from the imperfections in the image acquisition process, has to be compensated to provide accurate electron density estimation [12,13,14].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
