Click here to


Are you sure ?

Yes, do it No, cancel

Verification of the Machine Delivery Parameters of Treatment Plan Via Deep Learning

j fan*, L Xing, Y Yang, Stanford Univ School of Medicine, Stanford, CA


(Tuesday, 7/14/2020) 3:30 PM - 5:30 PM [Eastern Time (GMT-4)]

Room: Track 3

To develop a deep learning approach to estimate the multileaf collimator (MLC) aperture and corresponding monitor units (MUs) from a given three dimensional (3D) dose distribution.

We developed a treatment plan verification framework by implementing a deep learning network to learn a mapping between CT, segment 3D dose and MUs/MLC shapes. The proposed design of neural network, jointly trains a “U-Net”-like architecture as generator and a convolutional neural network classifier as discriminator. 199 patients treated with intensity modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT) techniques 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 obtained 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.

A novel deep learning network was developed to predict MUs/MLC shapes for treatment plan verification. 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.


Not Applicable / None Entered.


Not Applicable / None Entered.

Contact Email