Predicting real-time 3D deformation field maps (DFM) based on volumetric cine MRI (VC-MRI) and artificial neural networks for on-board 4D target tracking: a feasibility study.

Published online

Conference Paper

PURPOSE: To predict real-time 3D deformation field maps (DFMs) using Volumetric Cine MRI (VC-MRI) and adaptive boosting and multi-layer perceptron neural network (ADMLP-NN) for 4D target tracking.
 Methods: One phase of a prior 4D-MRI is set as the prior phase, MRI<sub>prior</sub>. Principal component analysis (PCA) is used to extract three major respiratory deformation modes from the DFMs generated between the prior and remaining phases. VC-MRI at each time-step is considered a deformation of MRI<sub>prior</sub>, where the DFM is represented as a weighted linear combination of the PCA components. The PCA weightings are solved by minimizing the differences between on-board 2D cine MRI and its corresponding VC-MRI slice. The PCA weightings solved during the initial training period are used to train an ADMLP-NN to predict PCA weightings ahead of time during the prediction period. The predicted PCA weightings are used to build predicted 3D DFM and ultimately, predicted VC-MRIs for 4D target tracking. The method was evaluated using a 4D computerized phantom (XCAT) with patient breathing curves and MRI data from a real liver cancer patient. Effects of breathing amplitude change and ADMLP-NN parameter variations were assessed. The accuracy of the PCA curve prediction was evaluated. The predicted real-time 3D tumor was evaluated against the ground-truth using Volume Dice Coefficient (VDC), Center-of-Mass-Shift (COMS), and target tracking errors. 
 Results: For the XCAT study, the average VDC and COMS for the predicted tumor were 0.92 ± 0.02 and 1.06 ± 0.40 mm, respectively, across all predicted time-steps. The correlation coefficients between predicted and actual PCA curves generated through VC-MRI estimation for the 1st/2nd principal components were 0.98/0.89 and 0.99/0.57 in the SI and AP directions, respectively. The optimal number of input neurons, hidden neurons, and MLP-NN for ADMLP-NN PCA weighting coefficient prediction was determined to be 7, 4, and 10, respectively. The optimal cost function threshold was determined to be 0.05. PCA weighting coefficient and VC-MRI accuracy worsened with increasing prediction-step size. Accurate PCA weighting coefficient prediction correlated with accurate VC-MRI prediction. For the patient study, the predicted 4D tumor tracking errors in superior-inferior, anterior-posterior and lateral directions were 0.50 ± 0.47 mm, 0.40 ± 0.55 mm, and 0.28 ± 0.12 mm, respectively.
 Conclusion: Preliminary studies demonstrated the feasibility and robustness to use VC-MRI and artificial neural networks to predict real-time 3D DFMs of the tumor for 4D target tracking.&#13.

Full Text

Duke Authors

Cited Authors

  • Pham, J; Harris, W; Sun, W; Yang, Z; Yin, F-F; Ren, L

Published Date

  • July 25, 2019

Published In

PubMed ID

  • 31344693

Pubmed Central ID

  • 31344693

Electronic International Standard Serial Number (EISSN)

  • 1361-6560

Digital Object Identifier (DOI)

  • 10.1088/1361-6560/ab359a

Conference Location

  • England