G Zhang, X Chen, J Dai, K Men*, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences, Beijing, 11CN,

• 
  K Men

PO-GePV-M-321 (Sunday, 7/10/2022)   [Eastern Time (GMT-4)]

ePoster Forums

Purpose: This study focused on developing a fast Monte Carlo (MC) plan verification platform via a deep learning-based denoising approach maintaining the MC dose calculation accuracy while significantly reducing the computation time and its potential applications for online adaptive proton therapy.

Methods: We modeled an MC platform for proton therapy using the beam data library (BDL) methods and then tested it with measured data. To accelerate the dose calculation, a DL-based denoising model with deep ResNet-deconvolution networks was developed. It was trained on the MC dose distribution of tumor sites obtained from 52 patients. The input MC dose distribution was with 1+E6 simulated protons and the reference was 1+E8. Five-fold cross-validation was performed.

Results: For developed in-house MC platform, the simulation results were quite comparable to the measured data. For the denoising approach, we found a significant improvement in the DVH for predicted images compared with input images. The root mean squared error (RMSE) for predicted versus reference images was 3.94 times lower than that of the input versus reference images. Moreover, for the gamma passing rate (3 mm/3%), the predicted versus reference images have an average of 99%, much higher than the 82% of the input versus reference images. The MC model successfully denoised the test dose map (high noise) to approach the reference (low noise). The elapsed time can be reduced to <60 s (simulation time + predicted time), much lower than the simulation time of a low noise dose map (e.g., >100 min of simulation of 1+E8 particles).

Conclusion: We propose an analogous end-to-end fast plan verification platform using the combination of MC and DL methods. The platform yields dose calculation accuracy similar to MC codes while significantly reducing the elapsed time and can be used for online APT as an alternative to online plan verification.

Funding Support, Disclosures, and Conflict of Interest: This work was supported by the National Natural Science Foundation of China (12175312), Beijing Nova Program (Z201100006820058), and the CAMS Innovation Fund for Medical Sciences (2020-I2M-C&T-B-073).

Keywords

Adaptive Sampling, Monte Carlo, Quality Assurance

Taxonomy

TH- External Beam- Particle/high LET therapy: Proton therapy – adaptive therapy

Contact Email