TY - JOUR
T1 - Dose calculation in proton therapy using a discovery cross-domain generative adversarial network (DiscoGAN)
AU - Zhang, Xiaoke
AU - Hu, Zongsheng
AU - Zhang, Guoliang
AU - Zhuang, Yongdong
AU - Wang, Yuenan
AU - Peng, Hao
N1 - Publisher Copyright:
© 2021 American Association of Physicists in Medicine
PY - 2021/5
Y1 - 2021/5
N2 - Purpose: Accurate dose calculation is a critical step in proton therapy. A novel machine learning-based approach was proposed to achieve comparable accuracy to that of Monte Carlo simulation while reducing the computational time. Methods: Computed tomography-based patient phantoms were used and three treatment sites were selected (thorax, head, and abdomen), comprising different beam pathways and beam energies. The training data were generated using Monte Carlo simulations. A discovery cross-domain generative adversarial network (DiscoGAN) was developed to perform the mapping between two domains: stopping power and dose, with HU values from CT images incorporated as auxiliary features. The accuracy of dose calculation was quantitatively evaluated in terms of mean relative error (MRE) and mean absolute error (MAE). The relationship between the DiscoGAN performance and other factors such as absolute dose, beam energy and location within the beam cross-section (center and off-center lines) was examined. Results: The DiscoGAN model is found to be effective in dose calculation. For the abdominal case, the MRE is found to 1.47% (mean), 3.30% (maximum) and 0.67% (minimum). For the thoracic case, the MRE is found to ~2.43% (mean), 4.80% (maximum) and 0.71% (minimum). For the head case, the MRE is found to ~2.83% (mean), 4.84% (maximum) and 1.01% (minimum). Comparable accuracy is found in the independent validation dataset (different CT images), achieving a mean MRE of ~1.65% (thorax), 4.02% (head) and 1.64% (abdomen). For the energy span between 80 and 130 MeV, no strong dependency of accuracy on beam energy is found. The results imply that no systematic deviation, either over-dose or under-dose, occurs between the predicted dose and raw dose. Conclusion: The DiscoGAN framework demonstrates great potential as a tool for dose calculation in proton therapy, achieving comparable accuracy yet being more efficient relative to Monte Carlo simulation. Its comparison with the pencil beam algorithm (PBA) will be the next step of our research. If successful, our proposed approach is expected to find its use in more advanced applications such as inverse planning and adaptive proton therapy.
AB - Purpose: Accurate dose calculation is a critical step in proton therapy. A novel machine learning-based approach was proposed to achieve comparable accuracy to that of Monte Carlo simulation while reducing the computational time. Methods: Computed tomography-based patient phantoms were used and three treatment sites were selected (thorax, head, and abdomen), comprising different beam pathways and beam energies. The training data were generated using Monte Carlo simulations. A discovery cross-domain generative adversarial network (DiscoGAN) was developed to perform the mapping between two domains: stopping power and dose, with HU values from CT images incorporated as auxiliary features. The accuracy of dose calculation was quantitatively evaluated in terms of mean relative error (MRE) and mean absolute error (MAE). The relationship between the DiscoGAN performance and other factors such as absolute dose, beam energy and location within the beam cross-section (center and off-center lines) was examined. Results: The DiscoGAN model is found to be effective in dose calculation. For the abdominal case, the MRE is found to 1.47% (mean), 3.30% (maximum) and 0.67% (minimum). For the thoracic case, the MRE is found to ~2.43% (mean), 4.80% (maximum) and 0.71% (minimum). For the head case, the MRE is found to ~2.83% (mean), 4.84% (maximum) and 1.01% (minimum). Comparable accuracy is found in the independent validation dataset (different CT images), achieving a mean MRE of ~1.65% (thorax), 4.02% (head) and 1.64% (abdomen). For the energy span between 80 and 130 MeV, no strong dependency of accuracy on beam energy is found. The results imply that no systematic deviation, either over-dose or under-dose, occurs between the predicted dose and raw dose. Conclusion: The DiscoGAN framework demonstrates great potential as a tool for dose calculation in proton therapy, achieving comparable accuracy yet being more efficient relative to Monte Carlo simulation. Its comparison with the pencil beam algorithm (PBA) will be the next step of our research. If successful, our proposed approach is expected to find its use in more advanced applications such as inverse planning and adaptive proton therapy.
KW - Monte Carlo simulation
KW - dose calculation
KW - generative adversarial network (GAN)
KW - proton therapy
UR - http://www.scopus.com/inward/record.url?scp=85102488082&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102488082&partnerID=8YFLogxK
U2 - 10.1002/mp.14781
DO - 10.1002/mp.14781
M3 - Article
C2 - 33594673
AN - SCOPUS:85102488082
SN - 0094-2405
VL - 48
SP - 2646
EP - 2660
JO - Medical physics
JF - Medical physics
IS - 5
ER -