Madiha Arshad1, Mahmood Qureshi1, Omair Inam1, and Hammad Omer1
1Medical Image Processing Research Group (MIPRG), Dept. of Elect. & Comp. Engineering, COMSATS University, Islamabad, Pakistan
Synopsis
Many
Parallel MRI algorithms (e.g. Sensitivity Encoding (SENSE)) require knowledge
of the receiver coil sensitivity maps. Magnetic field strength is an important
factor in defining the sensitivity maps of the receiver coils in MRI. This
paper presents a method to estimate the receiver coil sensitivity maps of a
higher magnetic field strength scanner utilizing a deep learning network (denoted
as ResU-Net-34), initially trained on the receiver coil sensitivity maps of a lower
field strength scanner using transfer learning. SENSE reconstruction results
show a successful domain transfer between the receiver coil sensitivities of different
magnetic field strengths with the proposed method.
Introduction
Successful
reconstruction of MR images in SENSE1 (and many other pMRI
algorithms) is strongly associated with an accurate knowledge of receiver coil
sensitivities1. The coil sensitivities change with the magnetic field
strength2. A receiver coil array at higher field strength might
perform differently than a coil array with an identical geometry at a lower
field strength2. Moreover, as the number of receiver coils in an
array changes, the sensitivity of an individual receiver coil also changes e.g.
an array of 8 receiver coils will have different sensitivity information as
compared to an array of 12 receiver coils. This paper presents a new method to
estimate the receiver coil sensitivity maps of 3T scanner from a pre-trained ResU-Net-34
via transfer learning. Firstly, the knowledge of sensitivity maps estimation is
learnt for an array of 8 receiver coils of 1.5T scanner. Later, the learnt
knowledge of sensitivity maps is transferred and fine-tuned for an array of 8 and
12 receiver coils of 3T scanner, separately.Method
The
proposed deep learning framework (Figure 1) is used to estimate the 8 and 12
receiver coil sensitivity maps of 3T scanner via transfer learning. In the
proposed methods, the source domain dataset (Table 1) is extracted from human
brain Cartesian dataset (of
30 patients of Multiple Sclerosis (MS)) acquired using 1.5T scanner3.
The Target Domain-1 dataset (Table 1) is extracted from the human brain Cartesian dataset
(of cognitively normal and cognitively declined patients) from Open Access
Series of Imaging Studies-3 (OASIS-3)4, which is acquired using 3T
scanner. The Target Domain-2 dataset (Table 1) is extracted from human brain
Cartesian dataset acquired using 3.0T Siemens Skyra scanner at Case Western
Reserve University, Cleveland, OH, USA.
Firstly,
the customized architecture of ResU-Net-346 (i.e. U-Net integrated with ResNet-34) is trained to generate the
sensitivity maps for an array of 8 receiver coils of 1.5T scanner. For training
and validation purpose, 1600 simulated images3 from an array of 8
receiver coils of 1.5T scanner are used. The raw sensitivity maps are generated
by dividing the low-resolution 8 coil images with the sum of squares image for
each dataset1. For label, the sensitivity maps are generated using Eigen
value method5 from the corresponding 1600 low-resolution images
obtained using 12 auto-calibration signal lines (ACS). Receiver coil
sensitivity map is a complex valued data; therefore, the magnitude and phase of
the sensitivity maps are trained separately.
Training of the ResU-Net-34 is performed on
Python 3.7.1 by Keras using TensorFlow as a backend on Intel(R) core (TM)
i7-4790 CPU, clock frequency 3.6GHz, 16GB RAM and GPU NVIDIA GeForce GTX 780
for approximately 7 hours. For training purpose, Adam optimizer with a learning
rate of 0.001 is used. The network is trained by using a two-part loss function
i.e. Mean Squared Error (MSE) loss and regularization loss (L2-norm). SENSE
reconstruction is performed using the estimated coil sensitivity maps by ResU-Net-34
for an array of 8 receiver coils of 1.5T scanner in MATLAB 2018.
In the second phase (i.e.
Proposed Method 1), the learnt knowledge of sensitivity maps is transferred and
fine-tuned for the sensitivity maps of 8 receiver coils array of 3T scanner4
for 15 epochs. In the third phase (i.e. Proposed Method 2), the learnt
knowledge of sensitivity maps is transferred and fine-tuned for the sensitivity
maps of 12 receiver coils array of 3T scanner for 20 epochs. In
Proposed Methods 1 and 2, end-to-end fine tuning of the pre-trained ResU-Net-34
is performed on Target domain-1 and 2 (Table 1), respectively, using Adam
optimizer with a
learning rate of 0.0001 (lower as compared to the learning rate used in initial
training). SENSE reconstruction (of the under-sampled data
(AF=2) acquired from 3T scanner) is performed using ten datasets of 8 channel
receiver coil complex sensitivity maps and two datasets of 12 channel receiver
coil complex sensitivity maps estimated by Proposed Methods 1 and 2,
respectively, in MATLAB 2018.Results
Figure
3 shows SENSE reconstruction results of the uniformly under-sampled (AF=2)
human brain datasets by using the sensitivity maps for the 8 and 12 receiver
coils array of 3T scanner estimated by the Proposed Methods 1, 2 and Eigen value5
method. Discussion and Conclusion
For
any discrepancy between the training and testing datasets, retraining of the
neural networks is required from a scratch which may be costly and time
consuming. This paper uses the
concept of fine tuning for estimating the 8 and 12 receiver coil sensitivity
maps of a 3T scanner by utilizing our customized network, initially trained on
the 8 receiver coil sensitivity maps of 1.5T scanner. Peak Signal-to-Noise Ratio (PSNR) and Root Mean Square
Error (RMSE) values (of the SENSE reconstructed images) show a successful SENSE
reconstruction by utilizing the receiver coil sensitivity maps estimated by the
proposed methods.Acknowledgements
No acknowledgement found.References
1.
Pruessmann, Klaas P., et al.
"SENSE: sensitivity encoding for fast MRI." Magnetic resonance
in medicine 42.5 (1999): 952-962.
2.
Wiesinger, Florian, et al.
"Parallel imaging performance as a function of field strength—an
experimental investigation using electrodynamic scaling." Magnetic
Resonance in Medicine: An Official Journal of the International Society for
Magnetic Resonance in Medicine 52.5 (2004): 953-964.
3.
Loizou et al. (2011), Multiscale
amplitude-modulation frequency-modulation (AM–FM) texture analysis of multiple
sclerosis in brain MRI images, IEEE Transactions on Information Technology in
Biomedicine 15.1 (2010): 119-129.
4.
Pamela
J. LaMontagne et al, OASIS-3: longitudinal
neuroimaging, clinical, and cognitive dataset for normal aging and alzheimer’s
disease, https://doi.org/10.1016/j.jalz.2018.06.1439.
5.
Irfan, Amna Shafa, et al.
"Sensitivity maps estimation using eigenvalues in sense
reconstruction." Applied Magnetic Resonance 47.5 (2016):
487-498.
6.
S. Nishank, UNet with ResBlock
for Semantic Segmentation,
https://medium.com/@nishanksingla/unet-with-resblock-for-semantic-segmentation-dd1766b4ff66.