Estimation of the radiation dose in pregnancy: an automated patient-specific model using convolutional neural networks
- 106 Downloads
The conceptus dose during diagnostic imaging procedures for pregnant patients raises health concerns owing to the high radiosensitivity of the developing embryo/fetus. The aim of this work is to develop a methodology for automated construction of patient-specific computational phantoms based on actual patient CT images to enable accurate estimation of conceptus dose.
We developed a 3D deep convolutional network algorithm for automated segmentation of CT images to build realistic computational phantoms. The neural network architecture consists of analysis and synthesis paths with four resolution levels each, trained on manually labeled CT scans of six identified anatomical structures. Thirty-two CT exams were augmented to 128 datasets and randomly split into 80%/20% for training/testing. The absorbed doses for six segmented organs/tissues from abdominal CT scans were estimated using Monte Carlo calculations. The resulting radiation doses were then compared between the computational models generated using automated segmentation and manual segmentation, serving as reference.
The Dice similarity coefficient for identified internal organs between manual segmentation and automated segmentation results varies from 0.92 to 0.98 while the mean Hausdorff distance for the uterus is 16.1 mm. The mean absorbed dose for the uterus is 2.9 mGy whereas the mean organ dose differences between manual and automated segmentation techniques are 0.07%, − 0.45%, − 1.55%, − 0.48%, − 0.12%, and 0.28% for the kidney, liver, lung, skeleton, uterus, and total body, respectively.
The proposed methodology allows automated construction of realistic computational models that can be exploited to estimate patient-specific organ radiation doses from radiological imaging procedures.
• The conceptus dose during diagnostic radiology and nuclear medicine imaging procedures for pregnant patients raises health concerns owing to the high radiosensitivity of the developing embryo/fetus.
• The proposed methodology allows automated construction of realistic computational models that can be exploited to estimate patient-specific organ radiation doses from radiological imaging procedures.
• The dosimetric results can be used for the risk-benefit analysis of radiation hazards to conceptus from diagnostic imaging procedures, thus guiding the decision-making process.
KeywordsMultidetector-row computed tomography Radiologic phantoms Patient-specific computational modeling Radiation dosimetry
Adaptive moment estimation
Convolutional neural networks
Dice similarity coefficient
Geneva University Hospital
Positron emission tomography
Positron emission tomography/computed tomography
Positive predictive value
Rectified linear unit
This work was supported by the Swiss National Science Foundation under grant SNSF 320030_176052 and Qatar National Research Fund under grant NPRP10-0126-170263. No other potential conflicts of interest relevant to this article exist.
This study has received funding by the Swiss National Science Foundation.
Compliance with ethical standards
The scientific guarantor of this publication is Habib Zaidi.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Written informed consent was waived in this study.
Institutional Review Board approval was obtained.
• Performed at one institution
- 5.American College of Radiology (2013) ACR-SPR practice parameter for imaging pregnant or potentially pregnant adolescents and women with ionizing radiation. Revised 2013 (Resolution 48)Google Scholar
- 7.ICRP (2003) ICRP publication 90: biological effects after prenatal irradiation (embryo and fetus). Ann ICRP 33:5–206Google Scholar
- 8.Altman KI, Lett JT (2013) Relative radiation sensitivities of human organ systems. ElsevierGoogle Scholar
- 11.(2007) ICRP publication 105. Radiological protection in medicine. Ann ICRP 37:1–63Google Scholar
- 12.Vañó E, Miller DL, Martin CJ et al(2017) ICRP publication 135: diagnostic reference levels in medical imaging. Ann ICRP 46:1–144Google Scholar
- 33.Mikolov T, Karafiát M, Burget L, Černocký J, Khudanpur S (2010) Recurrent neural network based language model. 11th annual conference of the International Speech Communication Association (INTERSPEECH-2010), Makuhari, Chiba, Japan, September 26–30. 2010, pp 1045–1048Google Scholar
- 34.Chung J, Gulcehre C, Cho K, Bengio Y (2015) Gated feedback recurrent neural networks. Proceedings of the 32nd International Conference on International Conference on Machine Learning. J PMLR 37:2067–2075Google Scholar
- 38.Sum J, Leung CS (2019) Learning algorithm for Boltzmann machines with additive weight and bias noise. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2018.2889072
- 40.Zhou X, Takayama R, Wang S, Zhou X, Hara T, Fujita H (2017) Automated segmentation of 3D anatomical structures on CT images by using a deep convolutional network based on end-to-end learning approach. Medical imaging: image processingGoogle Scholar
- 43.Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9351. Springer, Cham Springer, pp 234–241Google Scholar
- 44.Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin S, Joskowicz L, Sabuncu M, Unal G, Wells W (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016. MICCAI 2016. Lecture Notes in Computer Science, vol 9901. Springer, Cham, pp 424–432Google Scholar
- 45.Chollet F (2018) Keras: the Python deep learning library. Astrophysics Source Code Library. Available at https://keras.io/
- 46.(2002) Basic anatomical and physiological data for use in radiological protection: reference values. A report of age- and gender-related differences in the anatomical and physiological characteristics of reference individuals. ICRP Publication 89. Ann ICRP 32:5–265Google Scholar
- 48.Pelowitz DB (2005) MCNPX user’s manual Version 2.5.0. Los Alamos National Laboratory, Los AlamosGoogle Scholar