Journal article
A. Santhanam, M. Lauria, B. Stiehl, Daniel Elliott, Saty Seshan, S. Hsieh, M. Cao, D. Low
Medical Imaging: Image Processing, 2020
Medical Imaging: Image Processing, 2020
Semantic Scholar
DBLP
DOI
Cite
Cite
APA
Click to copy
Santhanam, A., Lauria, M., Stiehl, B., Elliott, D., Seshan, S., Hsieh, S., … Low, D. (2020). An adversarial machine-learning-based approach and biomechanically guided validation for improving deformable image registration accuracy between a planning CT and cone-beam CT for adaptive prostate radiotherapy applications. Medical Imaging: Image Processing.
Chicago/Turabian
Click to copy
Santhanam, A., M. Lauria, B. Stiehl, Daniel Elliott, Saty Seshan, S. Hsieh, M. Cao, and D. Low. “An Adversarial Machine-Learning-Based Approach and Biomechanically Guided Validation for Improving Deformable Image Registration Accuracy between a Planning CT and Cone-Beam CT for Adaptive Prostate Radiotherapy Applications.” Medical Imaging: Image Processing (2020).
MLA
Click to copy
Santhanam, A., et al. “An Adversarial Machine-Learning-Based Approach and Biomechanically Guided Validation for Improving Deformable Image Registration Accuracy between a Planning CT and Cone-Beam CT for Adaptive Prostate Radiotherapy Applications.” Medical Imaging: Image Processing, 2020.
BibTeX Click to copy
@article{a2020a,
title = {An adversarial machine-learning-based approach and biomechanically guided validation for improving deformable image registration accuracy between a planning CT and cone-beam CT for adaptive prostate radiotherapy applications},
year = {2020},
journal = {Medical Imaging: Image Processing},
author = {Santhanam, A. and Lauria, M. and Stiehl, B. and Elliott, Daniel and Seshan, Saty and Hsieh, S. and Cao, M. and Low, D.}
}
Abstract
Adaptive radiotherapy is an effective procedure for the treatment of cancer, where the daily anatomical changes in the patient are quantified, and the dose delivered to the tumor is adapted accordingly. Deformable Image Registration (DIR) inaccuracies and delays in retrieving and registering on-board cone beam CT (CBCT) image datasets from the treatment system with the planning kilo Voltage CT (kVCT) have limited the adaptive workflow to a limited number of patients. In this paper, we present an approach for improving the DIR accuracy using a machine learning approach coupled with biomechanically guided validation. For a given set of 11 planning prostate kVCT datasets and their segmented contours, we first assembled a biomechanical model to generate synthetic abdominal motions, bladder volume changes, and physiological regression. For each of the synthetic CT datasets, we then injected noise and artifacts in the images using a novel procedure in order to mimic closely CBCT datasets. We then considered the simulated CBCT images for training neural networks that predicted the noise and artifact-removed CT images. For this purpose, we employed a constrained generative adversarial neural network, which consisted of two deep neural networks, a generator and a discriminator. The generator produced the artifact-removed CT images while the discriminator computed the accuracy. The deformable image registration (DIR) results were finally validated using the model-generated landmarks. Results showed that the artifact-removed CT matched closely to the planning CT. Comparisons were performed using the image similarity metrics, and a normalized cross correlation of >0.95 was obtained from the cGAN based image enhancement. In addition, when DIR was performed, the landmarks matched within 1.1 +/- 0.5 mm. This demonstrates that using an adversarial DNN-based CBCT enhancement, improved DIR accuracy bolsters adaptive radiotherapy workflow.
