Florian Friedrich1,2, C. Katharina Spindeldreier3, Juliane Hörner-Rieber3, Sebastian Klüter3, Peter Bachert1,2, Mark E. Ladd1, and Benjamin R. Knowles1
1Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany, 2Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany, 3Department of Radiation Oncology,, University Hospital of Heidelberg, Heidelberg, Germany
Synopsis
MR-linac
hybrid systems can dynamically image a tumor during radiotherapy to aid in a
more precise delivery of the radiation dose. Motion tracking of the target is
required and is currently performed by a deformable image registration on
Cartesian bSSFP images. This study compares three different tracking methods (convolutional neuronal network, multi-template matching, and
deformable image registration) to track a lung tumor in Cartesian
images, where the performance of the three methods did not differ significantly.
The convolutional neuronal network provided minimal decrease in tracking
accuracy in a healthy volunteer
when undersampled
radial images were used to accelerate image acquisition.
Introduction
New hybrid MRI-linear
accelerator (MR-linac) systems allow imaging of tumors with high soft-tissue
contrast in real-time during tumor irradiation for the first time. This can
increase the treatment accuracy[1]. Healthy tissue is spared from radiation by either irradiating only when
the tumor is in a predefined target volume or by updating the multileaf-collimator
shape as the tumor moves. Both methods require fast imaging to avoid delays
between target detection and beam delivery. The ViewRay
system used here employs a Cartesian
sampling scheme for imaging and a deformable image registration for tumor
tracking in clinical
application. Here we compare three different tumor tracking methods on clinical
Cartesian images as well as on undersampled, high temporal resolution radial
images.Methods
Imaging was performed
on a 0.35T MRIdian Linac system (ViewRay Inc., Cleveland, Ohio, USA) using two 6-channel surface receive coils. A bSSFP sequence
was used to maximize signal-to-noise ratio, resulting in a T2/T1-weighted
contrast[2]. Patient data (Fig.1) were acquired with
Cartesian sampling with 4 frames per second (fps). Imaging parameters: (Δx)³=3.5x3.5x7mm³; FOV=350x350mm²;
TR/TE=2.10ms/0.91ms. Images were resampled for analysis from 100 to 128 pixels,
leading to an in-plane pixel size of 2.7x2.7mm². Manual contouring was
performed twice for an inter-observer comparison.
Images
of a healthy volunteer (Fig.2) were taken using radial tiny
golden angle (Ψ10=16.95...°) sampling[3]. Imaging parameters: (Δx)³=2.3x2.3x5mm³;
FOV=300x300mm²; TR/TE=3.34ms/1.67ms.
Videos
with seven different reconstruction windows between 75 spokes (4 fps) down to 10
spokes (30 fps) were analyzed. Radial images were reconstructed using a non-uniform
fast Fourier transform[4].
The cut
surface of the intestine was used for tracking (Fig.2, middle left), as it
represents a typical tumor size and has a high contrast to the surrounding
similar to lung cancers. Contours were manually defined from the images with 75
spokes.
For all
videos, manual contours were created in 50 images. The first 10 images were
used as reference frames to represent different breathing states. The following
40 images were used to test the tracking performance with the Dice coefficient[5], which measures the overlap of two areas A and B between 1 for perfect and
0 for no overlap (Dice=2(A∩B)/(A+B)).
The
following three auto-contouring methods were applied for motion tracking:
Convolutional neuronal
network with a U-net[6]
architecture: The 10 training images were split for learning and validation
within a 5-fold cross validation. Network parameters: batch size=1, epochs=150,
initial learning rate 10−5, which was reduced by a factor of 10 when
the Adam optimizer did not improve the cross-entropy loss during the preceding
3 epochs. Image augmentation to generate more
diverse training images was performed with the following parameters: rotation
range=5°, height shift range=10%, width shift range=5%, shear range=0.2°.
Multi-template
matching[7] (MTM): Ten same-sized templates of the tracked object were cut out
from the reference frames. In every new video frame, the normalized cross
correlation coefficient was used to find the position of the best match with
the templates, and the contour of the frame with the highest correlation was
used as contour of the new image.
Deformable
image registration[8]
(DIR): Firstly, the most similar reference image to the current frame was
estimated using cross correlation. Secondly, a non-rigid deformation map
was calculated from these two
pictures. The contour in the new image was given by applying the same
deformation on the contour of the chosen reference image.
Computation
times per frame were: 2.8ms (MTM), 55ms (U-Net) and 7.9s (DIR). U-Net needs 30min
for learning on a 64-bit Windows 10 computer with Intel Core i7-6700 CPU, 32GB
RAM. The code was not time-optimized.Results
The Dice coefficient mean and minimum
values from the three tumor patients are shown in the table of Fig.4. The
results show that the three tested tracking methods do not show significant
differences in the tracking precision and accuracy, as the standard deviations
of the Dice coefficient overlap with each other and with the inter-observer
test (Fig.4). Data augmentation improved the mean and minimum Dice coefficient
of the U-Net for all patients slightly but not significantly.
Results for the radial images of the healthy
volunteer are shown in Fig.5. With 75 spokes, all tracking methods perform very
similarly. Going to smaller reconstruction windows, the minimum Dice coefficient
drops rapidly below 60 spokes for the deformable image registration and below 30
spokes for the multi-template matching. The U-Net implementation achieves
superior results for all numbers of spokes above 10.Discussion
In the Cartesian images of lung tumors, all three tracking methods obtain
similar results. In the radial images of the healthy volunteer, the U-Net is
more robust for undersampled images, which are accompanied by streaking
artifacts and reduced signal-to-noise ratio. Data augmentation during U-Net
training can improve the segmentation by artificially increasing the
variability of the training images, as can be seen for the Cartesian images.
The augmentation parameters for the radial images have to be further adapted to
show an improvement. Moreover, the undersampling artifacts could be compensated
for with iterative reconstructions.Conclusion
All three evaluated tracking methods are applicable for tumor tracking in
Cartesian images for MR-guided radiotherapy. Radial acquisition has the potential
to speed up the imaging, with only a small decline of the
tracking results when a U-Net is used.Acknowledgements
No acknowledgement found.References
1. Wen
N, et al. Evaluation of a magnetic resonance guided linear accelerator for
stereotactic radiosurgery treatment. Radiotherapy and Oncology 127.3
(2018): 460-466
2. Scheffler K, Lehnhardt S. Principles and
applications of balanced SSFP techniques. Eur Radiol.
2003;13(11):2409-2418. doi:10.1007/s00330-003-1957-x
3. Wundrak S, Paul J, Ulrici J, et al. Golden ratio
sparse MRI using tiny golden angles. Magn Reson Med.
2016;75(6):2372-2378. doi:10.1002/mrm.25831
4. Fessler JA, Sutton BP. Nonuniform fast Fourier
transforms using min-max interpolation. IEEE Trans Signal Process.
2003;51(2):560-574. doi:10.1109/TSP.2002.807005
5. Dice, Lee R. Measures of the amount of ecologic
association between species. Ecology 26.3 (1945): 297-302
6. Ronneberger O, Fischer P, Brox T. U-net:
Convolutional networks for biomedical image segmentation. Med Image Comput
Comput Interv. 2015;9351:234-241. doi:10.1007/978-3-319-24574-4_28
7. Thomas LS, Gehrig J. Multi-Template Matching: a
versatile tool for object- localization in microscopy images. bioRxiv 619338.
2019. doi:https://doi.org/10.1101/619338
8. Avants BB, Epstein CL, Grossman M, Gee JC.
Symmetric diffeomorphic image registration with cross-correlation: evaluating
automated labeling of elderly and neurodegenerative brain. Med Image Anal.
2008;12(1):26-41. doi:10.1021/nn300902w.Release