A Comparative Study of Deep Learning Dose Prediction Models for Cervical Cancer Volumetric Modulated Arc Therapy
Purpose: Deep learning (DL) is widely used in dose prediction for radiation oncology, multiple DL techniques comparison is often lacking in the literature. To compare the performance of 4 state-of-the-art DL models in predicting the voxel-level dose distribution for cervical cancer volumetric modula...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2024-04-01
|
| Series: | Technology in Cancer Research & Treatment |
| Online Access: | https://doi.org/10.1177/15330338241242654 |
| _version_ | 1797215537955078144 |
|---|---|
| author | Zhe Wu PhD Mujun Liu PhD Ya Pang BS Lihua Deng PhD Yi Yang MS Yi Wu PhD |
| author_facet | Zhe Wu PhD Mujun Liu PhD Ya Pang BS Lihua Deng PhD Yi Yang MS Yi Wu PhD |
| author_sort | Zhe Wu PhD |
| collection | DOAJ |
| description | Purpose: Deep learning (DL) is widely used in dose prediction for radiation oncology, multiple DL techniques comparison is often lacking in the literature. To compare the performance of 4 state-of-the-art DL models in predicting the voxel-level dose distribution for cervical cancer volumetric modulated arc therapy (VMAT). Methods and Materials: A total of 261 patients’ plans for cervical cancer were retrieved in this retrospective study. A three-channel feature map, consisting of a planning target volume (PTV) mask, organs at risk (OARs) mask, and CT image was fed into the three-dimensional (3D) U-Net and its 3 variants models. The data set was randomly divided into 80% as training-validation and 20% as testing set, respectively. The model performance was evaluated on the 52 testing patients by comparing the generated dose distributions against the clinical approved ground truth (GT) using mean absolute error (MAE), dose map difference (GT-predicted), clinical dosimetric indices, and dice similarity coefficients (DSC). Results: The 3D U-Net and its 3 variants DL models exhibited promising performance with a maximum MAE within the PTV 0.83% ± 0.67% in the UNETR model. The maximum MAE among the OARs is the left femoral head, which reached 6.95% ± 6.55%. For the body, the maximum MAE was observed in UNETR, which is 1.19 ± 0.86%, and the minimum MAE was 0.94 ± 0.85% for 3D U-Net. The average error of the Dmean difference for different OARs is within 2.5 Gy. The average error of V40 difference for the bladder and rectum is about 5%. The mean DSC under different isodose volumes was above 90%. Conclusions: DL models can predict the voxel-level dose distribution accurately for cervical cancer VMAT treatment plans. All models demonstrated almost analogous performance for voxel-wise dose prediction maps. Considering all voxels within the body, 3D U-Net showed the best performance. The state-of-the-art DL models are of great significance for further clinical applications of cervical cancer VMAT. |
| first_indexed | 2024-04-24T11:31:39Z |
| format | Article |
| id | doaj.art-0e99510d4f8745cb9f763b2033f748fd |
| institution | Directory Open Access Journal |
| issn | 1533-0338 |
| language | English |
| last_indexed | 2024-04-24T11:31:39Z |
| publishDate | 2024-04-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Technology in Cancer Research & Treatment |
| spelling | doaj.art-0e99510d4f8745cb9f763b2033f748fd2024-04-10T09:05:05ZengSAGE PublishingTechnology in Cancer Research & Treatment1533-03382024-04-012310.1177/15330338241242654A Comparative Study of Deep Learning Dose Prediction Models for Cervical Cancer Volumetric Modulated Arc TherapyZhe Wu PhD0Mujun Liu PhD1Ya Pang BS2Lihua Deng PhD3Yi Yang MS4Yi Wu PhD5 Department of Radiation Oncology, , Zigong First People's Hospital, Zigong, Sichuan, China Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, , Chongqing, China Department of Radiation Oncology, , Zigong First People's Hospital, Zigong, Sichuan, China Department of Radiology, The First Affiliated Hospital of the , Chongqing, China Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, , Chongqing, China Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, , Chongqing, ChinaPurpose: Deep learning (DL) is widely used in dose prediction for radiation oncology, multiple DL techniques comparison is often lacking in the literature. To compare the performance of 4 state-of-the-art DL models in predicting the voxel-level dose distribution for cervical cancer volumetric modulated arc therapy (VMAT). Methods and Materials: A total of 261 patients’ plans for cervical cancer were retrieved in this retrospective study. A three-channel feature map, consisting of a planning target volume (PTV) mask, organs at risk (OARs) mask, and CT image was fed into the three-dimensional (3D) U-Net and its 3 variants models. The data set was randomly divided into 80% as training-validation and 20% as testing set, respectively. The model performance was evaluated on the 52 testing patients by comparing the generated dose distributions against the clinical approved ground truth (GT) using mean absolute error (MAE), dose map difference (GT-predicted), clinical dosimetric indices, and dice similarity coefficients (DSC). Results: The 3D U-Net and its 3 variants DL models exhibited promising performance with a maximum MAE within the PTV 0.83% ± 0.67% in the UNETR model. The maximum MAE among the OARs is the left femoral head, which reached 6.95% ± 6.55%. For the body, the maximum MAE was observed in UNETR, which is 1.19 ± 0.86%, and the minimum MAE was 0.94 ± 0.85% for 3D U-Net. The average error of the Dmean difference for different OARs is within 2.5 Gy. The average error of V40 difference for the bladder and rectum is about 5%. The mean DSC under different isodose volumes was above 90%. Conclusions: DL models can predict the voxel-level dose distribution accurately for cervical cancer VMAT treatment plans. All models demonstrated almost analogous performance for voxel-wise dose prediction maps. Considering all voxels within the body, 3D U-Net showed the best performance. The state-of-the-art DL models are of great significance for further clinical applications of cervical cancer VMAT.https://doi.org/10.1177/15330338241242654 |
| spellingShingle | Zhe Wu PhD Mujun Liu PhD Ya Pang BS Lihua Deng PhD Yi Yang MS Yi Wu PhD A Comparative Study of Deep Learning Dose Prediction Models for Cervical Cancer Volumetric Modulated Arc Therapy Technology in Cancer Research & Treatment |
| title | A Comparative Study of Deep Learning Dose Prediction Models for Cervical Cancer Volumetric Modulated Arc Therapy |
| title_full | A Comparative Study of Deep Learning Dose Prediction Models for Cervical Cancer Volumetric Modulated Arc Therapy |
| title_fullStr | A Comparative Study of Deep Learning Dose Prediction Models for Cervical Cancer Volumetric Modulated Arc Therapy |
| title_full_unstemmed | A Comparative Study of Deep Learning Dose Prediction Models for Cervical Cancer Volumetric Modulated Arc Therapy |
| title_short | A Comparative Study of Deep Learning Dose Prediction Models for Cervical Cancer Volumetric Modulated Arc Therapy |
| title_sort | comparative study of deep learning dose prediction models for cervical cancer volumetric modulated arc therapy |
| url | https://doi.org/10.1177/15330338241242654 |
| work_keys_str_mv | AT zhewuphd acomparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT mujunliuphd acomparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT yapangbs acomparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT lihuadengphd acomparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT yiyangms acomparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT yiwuphd acomparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT zhewuphd comparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT mujunliuphd comparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT yapangbs comparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT lihuadengphd comparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT yiyangms comparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy AT yiwuphd comparativestudyofdeeplearningdosepredictionmodelsforcervicalcancervolumetricmodulatedarctherapy |