Patient‐specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy
Abstract Objective Despite its prevalence, cone beam computed tomography (CBCT) has poor soft‐tissue contrast, making it challenging to localize liver tumors. We propose a patient‐specific deep learning model to generate synthetic magnetic resonance imaging (MRI) from CBCT to improve tumor localizat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-06-01
|
| Series: | Precision Radiation Oncology |
| Online Access: | https://doi.org/10.1002/pro6.1163 |
| _version_ | 1818236045000441856 |
|---|---|
| author | Zeyu Zhang Zhuoran Jiang Hualiang Zhong Ke Lu Fang‐Fang Yin Lei Ren |
| author_facet | Zeyu Zhang Zhuoran Jiang Hualiang Zhong Ke Lu Fang‐Fang Yin Lei Ren |
| author_sort | Zeyu Zhang |
| collection | DOAJ |
| description | Abstract Objective Despite its prevalence, cone beam computed tomography (CBCT) has poor soft‐tissue contrast, making it challenging to localize liver tumors. We propose a patient‐specific deep learning model to generate synthetic magnetic resonance imaging (MRI) from CBCT to improve tumor localization. Methods A key innovation is using patient‐specific CBCT‐MRI image pairs to train a deep learning model to generate synthetic MRI from CBCT. Specifically, patient planning CT was deformably registered to prior MRI, and then used to simulate CBCT with simulated projections and Feldkamp, Davis, and Kress reconstruction. These CBCT‐MRI images were augmented using translations and rotations to generate enough patient‐specific training data. A U‐Net‐based deep learning model was developed and trained to generate synthetic MRI from CBCT in the liver, and then tested on a different CBCT dataset. Synthetic MRIs were quantitatively evaluated against ground‐truth MRI. Results The synthetic MRI demonstrated superb soft‐tissue contrast with clear tumor visualization. On average, the synthetic MRI achieved 28.01, 0.025, and 0.929 for peak signal‐to‐noise ratio, mean square error, and structural similarity index, respectively, outperforming CBCT images. The model performance was consistent across all three patients tested. Conclusion Our study demonstrated the feasibility of a patient‐specific model to generate synthetic MRI from CBCT for liver tumor localization, opening up a potential to democratize MRI guidance in clinics with conventional LINACs. |
| first_indexed | 2024-12-12T12:03:37Z |
| format | Article |
| id | doaj.art-360aeac0472b45ac9a29c15f2265e197 |
| institution | Directory Open Access Journal |
| issn | 2398-7324 |
| language | English |
| last_indexed | 2024-12-12T12:03:37Z |
| publishDate | 2022-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Precision Radiation Oncology |
| spelling | doaj.art-360aeac0472b45ac9a29c15f2265e1972022-12-22T00:25:03ZengWileyPrecision Radiation Oncology2398-73242022-06-016211011810.1002/pro6.1163Patient‐specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapyZeyu Zhang0Zhuoran Jiang1Hualiang Zhong2Ke Lu3Fang‐Fang Yin4Lei Ren5Duke University Medical Center Durham North Carolina USADuke University Medical Center Durham North Carolina USAMedical College of Wisconsin Milwaukee Wisconsin USADuke University Medical Center Durham North Carolina USADuke University Medical Center Durham North Carolina USAUniversity of Maryland School of Medicine Baltimore Maryland USAAbstract Objective Despite its prevalence, cone beam computed tomography (CBCT) has poor soft‐tissue contrast, making it challenging to localize liver tumors. We propose a patient‐specific deep learning model to generate synthetic magnetic resonance imaging (MRI) from CBCT to improve tumor localization. Methods A key innovation is using patient‐specific CBCT‐MRI image pairs to train a deep learning model to generate synthetic MRI from CBCT. Specifically, patient planning CT was deformably registered to prior MRI, and then used to simulate CBCT with simulated projections and Feldkamp, Davis, and Kress reconstruction. These CBCT‐MRI images were augmented using translations and rotations to generate enough patient‐specific training data. A U‐Net‐based deep learning model was developed and trained to generate synthetic MRI from CBCT in the liver, and then tested on a different CBCT dataset. Synthetic MRIs were quantitatively evaluated against ground‐truth MRI. Results The synthetic MRI demonstrated superb soft‐tissue contrast with clear tumor visualization. On average, the synthetic MRI achieved 28.01, 0.025, and 0.929 for peak signal‐to‐noise ratio, mean square error, and structural similarity index, respectively, outperforming CBCT images. The model performance was consistent across all three patients tested. Conclusion Our study demonstrated the feasibility of a patient‐specific model to generate synthetic MRI from CBCT for liver tumor localization, opening up a potential to democratize MRI guidance in clinics with conventional LINACs.https://doi.org/10.1002/pro6.1163 |
| spellingShingle | Zeyu Zhang Zhuoran Jiang Hualiang Zhong Ke Lu Fang‐Fang Yin Lei Ren Patient‐specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy Precision Radiation Oncology |
| title | Patient‐specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy |
| title_full | Patient‐specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy |
| title_fullStr | Patient‐specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy |
| title_full_unstemmed | Patient‐specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy |
| title_short | Patient‐specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy |
| title_sort | patient specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy |
| url | https://doi.org/10.1002/pro6.1163 |
| work_keys_str_mv | AT zeyuzhang patientspecificsyntheticmagneticresonanceimaginggenerationfromconebeamcomputedtomographyforimageguidanceinliverstereotacticbodyradiationtherapy AT zhuoranjiang patientspecificsyntheticmagneticresonanceimaginggenerationfromconebeamcomputedtomographyforimageguidanceinliverstereotacticbodyradiationtherapy AT hualiangzhong patientspecificsyntheticmagneticresonanceimaginggenerationfromconebeamcomputedtomographyforimageguidanceinliverstereotacticbodyradiationtherapy AT kelu patientspecificsyntheticmagneticresonanceimaginggenerationfromconebeamcomputedtomographyforimageguidanceinliverstereotacticbodyradiationtherapy AT fangfangyin patientspecificsyntheticmagneticresonanceimaginggenerationfromconebeamcomputedtomographyforimageguidanceinliverstereotacticbodyradiationtherapy AT leiren patientspecificsyntheticmagneticresonanceimaginggenerationfromconebeamcomputedtomographyforimageguidanceinliverstereotacticbodyradiationtherapy |