Abstract：
OBJECTIVE: To develop a machine learning-based pipeline for multi-organ/tissue personalized radiation dosimetry in CT.
METHODS: For the study, 95 chest CT scans and 85 abdominal CT scans were collected retrospectively. For each CT scan, a personalized Monte Carlo (MC) simulation was carried out. The produced 3D dose distributions and the respective CT examinations were utilized for the development of organ/tissue-specific dose prediction deep neural networks (DNNs). A pipeline that integrates a robust open-source organ segmentation tool with the dose prediction DNNs was developed for the automatic estimation of radiation doses for 30 organs/tissues including sub-volumes of the heart and lungs. The accuracy and time efficiency of the presented methodology was assessed. Statistical analysis (t-tests) was conducted to determine if the differences between the ground truth organ/tissue radiation dose estimates and the respective dose predictions were significant.
RESULTS: The lowest median percentage differences between MC-derived organ/tissue doses and DNN dose predictions were observed for the lung vessels (4.3%), small bowel (4.7%), pulmonary artery (4.7%), and colon (5.2%), while the highest differences were observed for the right lung\'s upper lobe (13.3%), spleen (13.1%), pancreas (12.1%), and stomach (11.6%). Statistical analysis showed that the differences were not significant (p-value > 0.18). Furthermore, the mean inference time, regarding the validation cohort, of the developed methodology was 77.0 ± 11.0 s.
CONCLUSIONS: The proposed workflow enables fast and accurate organ/tissue radiation dose estimations. The developed algorithms and dose prediction DNNs are publicly available ( https://github.com/eltzanis/multi-structure-CT-dosimetry ).
CONCLUSIONS: The accuracy and time efficiency of the developed pipeline compose a useful tool for personalized dosimetry in CT. By adopting the proposed workflow, institutions can utilize an automated pipeline for patient-specific dosimetry in CT.
CONCLUSIONS: Personalized dosimetry is ideal, but is time-consuming. The proposed pipeline composes a tool for facilitating patient-specific CT dosimetry in routine clinical practice. The developed workflow integrates a robust open-source segmentation tool with organ/tissue-specific dose prediction neural networks.
METHODS: For the study, 95 chest CT scans and 85 abdominal CT scans were collected retrospectively. For each CT scan, a personalized Monte Carlo (MC) simulation was carried out. The produced 3D dose distributions and the respective CT examinations were utilized for the development of organ/tissue-specific dose prediction deep neural networks (DNNs). A pipeline that integrates a robust open-source organ segmentation tool with the dose prediction DNNs was developed for the automatic estimation of radiation doses for 30 organs/tissues including sub-volumes of the heart and lungs. The accuracy and time efficiency of the presented methodology was assessed. Statistical analysis (t-tests) was conducted to determine if the differences between the ground truth organ/tissue radiation dose estimates and the respective dose predictions were significant.
RESULTS: The lowest median percentage differences between MC-derived organ/tissue doses and DNN dose predictions were observed for the lung vessels (4.3%), small bowel (4.7%), pulmonary artery (4.7%), and colon (5.2%), while the highest differences were observed for the right lung\'s upper lobe (13.3%), spleen (13.1%), pancreas (12.1%), and stomach (11.6%). Statistical analysis showed that the differences were not significant (p-value > 0.18). Furthermore, the mean inference time, regarding the validation cohort, of the developed methodology was 77.0 ± 11.0 s.
CONCLUSIONS: The proposed workflow enables fast and accurate organ/tissue radiation dose estimations. The developed algorithms and dose prediction DNNs are publicly available ( https://github.com/eltzanis/multi-structure-CT-dosimetry ).
CONCLUSIONS: The accuracy and time efficiency of the developed pipeline compose a useful tool for personalized dosimetry in CT. By adopting the proposed workflow, institutions can utilize an automated pipeline for patient-specific dosimetry in CT.
CONCLUSIONS: Personalized dosimetry is ideal, but is time-consuming. The proposed pipeline composes a tool for facilitating patient-specific CT dosimetry in routine clinical practice. The developed workflow integrates a robust open-source segmentation tool with organ/tissue-specific dose prediction neural networks.
摘要：
目的：开发基于机器学习的管道，用于CT中的多器官/组织个性化辐射剂量测定。
方法：对于研究，回顾性收集95例胸部CT扫描和85例腹部CT扫描。对于每次CT扫描，进行了个性化蒙特卡罗(MC)模拟。所产生的3D剂量分布和各自的CT检查被用于开发器官/组织特异性剂量预测深度神经网络(DNN)。开发了一种将强大的开源器官分割工具与剂量预测DNN集成的管道，用于自动估计30个器官/组织的辐射剂量，包括心脏和肺部的子体积。评估了所提出方法的准确性和时间效率。进行统计分析(t检验)以确定真实器官/组织辐射剂量估计和各自剂量预测之间的差异是否显著。
结果：对于肺血管，观察到MC来源的器官/组织剂量与DNN剂量预测之间的最低中位数百分比差异（4.3％），小肠(4.7%),肺动脉(4.7%),和结肠(5.2%)，而右肺上叶差异最大（13.3%），脾脏(13.1%),胰腺（12.1%），和胃（11.6％）。统计学分析表明差异不显著(p值>0.18)。此外，平均推理时间，关于验证队列，所开发的方法为77.0±11.0s。
结论：所提出的工作流程可实现快速准确的器官/组织辐射剂量估算。所开发的算法和剂量预测DNN是公开可用的(https://github.com/eltzanis/multi-structure-CT-剂量测定)。
结论：开发的管道的准确性和时间效率构成了CT个性化剂量测定的有用工具。通过采用建议的工作流程，机构可以利用自动管道在CT中进行患者特异性剂量测定。
结论：个性化剂量测定是理想的，但是很耗时。拟议的管道构成了一种在常规临床实践中促进患者特异性CT剂量测定的工具。开发的工作流程将强大的开源分割工具与器官/组织特定剂量预测神经网络集成在一起。
方法：对于研究，回顾性收集95例胸部CT扫描和85例腹部CT扫描。对于每次CT扫描，进行了个性化蒙特卡罗(MC)模拟。所产生的3D剂量分布和各自的CT检查被用于开发器官/组织特异性剂量预测深度神经网络(DNN)。开发了一种将强大的开源器官分割工具与剂量预测DNN集成的管道，用于自动估计30个器官/组织的辐射剂量，包括心脏和肺部的子体积。评估了所提出方法的准确性和时间效率。进行统计分析(t检验)以确定真实器官/组织辐射剂量估计和各自剂量预测之间的差异是否显著。
结果：对于肺血管，观察到MC来源的器官/组织剂量与DNN剂量预测之间的最低中位数百分比差异（4.3％），小肠(4.7%),肺动脉(4.7%),和结肠(5.2%)，而右肺上叶差异最大（13.3%），脾脏(13.1%),胰腺（12.1%），和胃（11.6％）。统计学分析表明差异不显著(p值>0.18)。此外，平均推理时间，关于验证队列，所开发的方法为77.0±11.0s。
结论：所提出的工作流程可实现快速准确的器官/组织辐射剂量估算。所开发的算法和剂量预测DNN是公开可用的(https://github.com/eltzanis/multi-structure-CT-剂量测定)。
结论：开发的管道的准确性和时间效率构成了CT个性化剂量测定的有用工具。通过采用建议的工作流程，机构可以利用自动管道在CT中进行患者特异性剂量测定。
结论：个性化剂量测定是理想的，但是很耗时。拟议的管道构成了一种在常规临床实践中促进患者特异性CT剂量测定的工具。开发的工作流程将强大的开源分割工具与器官/组织特定剂量预测神经网络集成在一起。
