Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRI
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. Rega...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/5/816 |
| _version_ | 1827693604043227136 |
|---|---|
| author | Kuei-Yuan Hou Hao-Yuan Lu Ching-Ching Yang |
| author_facet | Kuei-Yuan Hou Hao-Yuan Lu Ching-Ching Yang |
| author_sort | Kuei-Yuan Hou |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T11:46:50Z |
| format | Article |
| id | doaj.art-021c2756a894478daeca06017ca0c30e |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T11:46:50Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-021c2756a894478daeca06017ca0c30e2023-11-21T17:58:58ZengMDPI AGDiagnostics2075-44182021-04-0111581610.3390/diagnostics11050816Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRIKuei-Yuan Hou0Hao-Yuan Lu1Ching-Ching Yang2Department of Radiology, Cathay General Hospital, Taipei 106, TaiwanInstitute of Radiological Sciences, Tzu-Chi University of Science and Technology, Hualien 970, TaiwanDepartment of Medical Imaging and Radiological Sciences, Kaohsiung Medical University, Kaohsiung 807, TaiwanThis 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.https://www.mdpi.com/2075-4418/11/5/816MRI intensity normalizationpseudo-CT synthesisconvolutional neural network |
| spellingShingle | Kuei-Yuan Hou Hao-Yuan Lu Ching-Ching Yang Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRI Diagnostics MRI intensity normalization pseudo-CT synthesis convolutional neural network |
| title | Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRI |
| title_full | Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRI |
| title_fullStr | Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRI |
| title_full_unstemmed | Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRI |
| title_short | Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRI |
| title_sort | applying mri intensity normalization on non bone tissues to facilitate pseudo ct synthesis from mri |
| topic | MRI intensity normalization pseudo-CT synthesis convolutional neural network |
| url | https://www.mdpi.com/2075-4418/11/5/816 |
| work_keys_str_mv | AT kueiyuanhou applyingmriintensitynormalizationonnonbonetissuestofacilitatepseudoctsynthesisfrommri AT haoyuanlu applyingmriintensitynormalizationonnonbonetissuestofacilitatepseudoctsynthesisfrommri AT chingchingyang applyingmriintensitynormalizationonnonbonetissuestofacilitatepseudoctsynthesisfrommri |