Bio

Professional Education


  • Doctor of Philosophy, High Energy Physics Institute (2015)
  • Bachelor (Undeclared), Nanjing Normal University (2009)

Stanford Advisors


Publications

All Publications


  • Verification of the machine delivery parameters of treatment plan via deep learning. Physics in medicine and biology Fan, J., Xing, L., Ma, M., Hu, W., Yang, Y. 2020

    Abstract

    We developed a generative adversarial network (GAN)-based deep learning approach to estimate the multileaf collimator (MLC) aperture and corresponding monitor units (MUs) from a given three dimensional (3D) dose distribution. The proposed design of adversari-al network, which integrates a residual block into pix2pix framework, jointly trains a "U-Net"-like architecture as generator and a convolutional "PatchGAN" classifier as dis-criminator. 199 patients, including nasopharyngeal, lung and rectum, treated with intensi-ty modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT) tech-niques were utilized to train the network. Additional 47 patients were used to test the prediction accuracy of the proposed deep learning model. The Dice similarity coefficient (DSC) was calculated to evaluate the similarity between the MLC aperture shapes ob-tained from the treatment planning system (TPS) and the deep learning prediction. The average and standard deviation of the bias between the TPS generated MUs and predicted MUs were calculated to evaluate the MU prediction accuracy. Additionally, the differences between TPS and deep learning-predicted MLC leaf positions were compared. The average and standard deviation of DSC was 0.94 0.043 for 47 testing patients. The average deviation of predicted MUs from the planned MUs normalized to each beam or arc was within 2% for all the testing patients. The average deviation of the predicted MLC leaf positions was around one pixel for all the testing patients. Our results demonstrated the feasibility and reliability of the proposed approach. The proposed technique has strong potential to improve the efficiency and accuracy of patient plan quality assurance (QA) process.

    View details for DOI 10.1088/1361-6560/aba165

    View details for PubMedID 32604082

Footer Links:

Stanford Medicine Resources: