Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO)
Abstract Background It is not unusual to see some parts of tissues are excluded in the field of view of CT simulation images. A typical mitigation is to avoid beams entering the missing body parts at the cost of sub-optimal planning. Methods This study is to solve the problem by developing 3 methods...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-01-01
|
| Series: | Radiation Oncology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13014-023-02384-4 |
| _version_ | 1797276407086186496 |
|---|---|
| author | Sunmi Kim Lulin Yuan Siyong Kim Tae Suk Suh |
| author_facet | Sunmi Kim Lulin Yuan Siyong Kim Tae Suk Suh |
| author_sort | Sunmi Kim |
| collection | DOAJ |
| description | Abstract Background It is not unusual to see some parts of tissues are excluded in the field of view of CT simulation images. A typical mitigation is to avoid beams entering the missing body parts at the cost of sub-optimal planning. Methods This study is to solve the problem by developing 3 methods, (1) deep learning (DL) mechanism for missing tissue generation, (2) using patient body outline (PBO) based on surface imaging, and (3) hybrid method combining DL and PBO. The DL model was built upon a Globally and Locally Consistent Image Completion to learn features by Convolutional Neural Networks-based inpainting, based on Generative Adversarial Network. The database used comprised 10,005 CT training slices of 322 lung cancer patients and 166 CT evaluation test slices of 15 patients. CT images were from the publicly available database of the Cancer Imaging Archive. Since existing data were used PBOs were acquired from the CT images. For evaluation, Structural Similarity Index Metric (SSIM), Root Mean Square Error (RMSE) and Peak signal-to-noise ratio (PSNR) were evaluated. For dosimetric validation, dynamic conformal arc plans were made with the ground truth images and images generated by the proposed method. Gamma analysis was conducted at relatively strict criteria of 1%/1 mm (dose difference/distance to agreement) and 2%/2 mm under three dose thresholds of 1%, 10% and 50% of the maximum dose in the plans made on the ground truth image sets. Results The average SSIM in generation part only was 0.06 at epoch 100 but reached 0.86 at epoch 1500. Accordingly, the average SSIM in the whole image also improved from 0.86 to 0.97. At epoch 1500, the average values of RMSE and PSNR in the whole image were 7.4 and 30.9, respectively. Gamma analysis showed excellent agreement with the hybrid method (equal to or higher than 96.6% of the mean of pass rates for all scenarios). Conclusions It was first demonstrated that missing tissues in simulation imaging could be generated with high similarity, and dosimetric limitation could be overcome. The benefit of this study can be significantly enlarged when MR-only simulation is considered. |
| first_indexed | 2024-03-07T15:27:52Z |
| format | Article |
| id | doaj.art-812e05bbbaae4401b4d417798811dd82 |
| institution | Directory Open Access Journal |
| issn | 1748-717X |
| language | English |
| last_indexed | 2024-03-07T15:27:52Z |
| publishDate | 2024-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Radiation Oncology |
| spelling | doaj.art-812e05bbbaae4401b4d417798811dd822024-03-05T16:37:18ZengBMCRadiation Oncology1748-717X2024-01-0119111210.1186/s13014-023-02384-4Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO)Sunmi Kim0Lulin Yuan1Siyong Kim2Tae Suk Suh3Department of Biomedical Engineering and Research Institute of Biomedical Engineering, College of Medicine, The Catholic University of KoreaDepartment of Radiation Oncology, School of Medicine, Virginia Commonwealth UniversityDepartment of Radiation Oncology, School of Medicine, Virginia Commonwealth UniversityDepartment of Biomedical Engineering and Research Institute of Biomedical Engineering, College of Medicine, The Catholic University of KoreaAbstract Background It is not unusual to see some parts of tissues are excluded in the field of view of CT simulation images. A typical mitigation is to avoid beams entering the missing body parts at the cost of sub-optimal planning. Methods This study is to solve the problem by developing 3 methods, (1) deep learning (DL) mechanism for missing tissue generation, (2) using patient body outline (PBO) based on surface imaging, and (3) hybrid method combining DL and PBO. The DL model was built upon a Globally and Locally Consistent Image Completion to learn features by Convolutional Neural Networks-based inpainting, based on Generative Adversarial Network. The database used comprised 10,005 CT training slices of 322 lung cancer patients and 166 CT evaluation test slices of 15 patients. CT images were from the publicly available database of the Cancer Imaging Archive. Since existing data were used PBOs were acquired from the CT images. For evaluation, Structural Similarity Index Metric (SSIM), Root Mean Square Error (RMSE) and Peak signal-to-noise ratio (PSNR) were evaluated. For dosimetric validation, dynamic conformal arc plans were made with the ground truth images and images generated by the proposed method. Gamma analysis was conducted at relatively strict criteria of 1%/1 mm (dose difference/distance to agreement) and 2%/2 mm under three dose thresholds of 1%, 10% and 50% of the maximum dose in the plans made on the ground truth image sets. Results The average SSIM in generation part only was 0.06 at epoch 100 but reached 0.86 at epoch 1500. Accordingly, the average SSIM in the whole image also improved from 0.86 to 0.97. At epoch 1500, the average values of RMSE and PSNR in the whole image were 7.4 and 30.9, respectively. Gamma analysis showed excellent agreement with the hybrid method (equal to or higher than 96.6% of the mean of pass rates for all scenarios). Conclusions It was first demonstrated that missing tissues in simulation imaging could be generated with high similarity, and dosimetric limitation could be overcome. The benefit of this study can be significantly enlarged when MR-only simulation is considered.https://doi.org/10.1186/s13014-023-02384-4Machine learningMissing tissue generationRadiation therapy simulationField of view (FOV)MR-only simulation |
| spellingShingle | Sunmi Kim Lulin Yuan Siyong Kim Tae Suk Suh Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO) Radiation Oncology Machine learning Missing tissue generation Radiation therapy simulation Field of view (FOV) MR-only simulation |
| title | Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO) |
| title_full | Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO) |
| title_fullStr | Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO) |
| title_full_unstemmed | Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO) |
| title_short | Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO) |
| title_sort | generation of tissues outside the field of view fov of radiation therapy simulation imaging based on machine learning and patient body outline pbo |
| topic | Machine learning Missing tissue generation Radiation therapy simulation Field of view (FOV) MR-only simulation |
| url | https://doi.org/10.1186/s13014-023-02384-4 |
| work_keys_str_mv | AT sunmikim generationoftissuesoutsidethefieldofviewfovofradiationtherapysimulationimagingbasedonmachinelearningandpatientbodyoutlinepbo AT lulinyuan generationoftissuesoutsidethefieldofviewfovofradiationtherapysimulationimagingbasedonmachinelearningandpatientbodyoutlinepbo AT siyongkim generationoftissuesoutsidethefieldofviewfovofradiationtherapysimulationimagingbasedonmachinelearningandpatientbodyoutlinepbo AT taesuksuh generationoftissuesoutsidethefieldofviewfovofradiationtherapysimulationimagingbasedonmachinelearningandpatientbodyoutlinepbo |