Shishuai Wang^{1}, Pedro F Ferreira^{2}, Zohya Khalique^{2}, Margarita Gorodezky^{2}, Malte Roehl^{2}, Jialin Pu^{3}, Dudley J Pennell^{2}, Sonia Nielles-Vallespin^{2}, and Andrew D Scott^{2}

^{1}Department of Physics, Imperial College London, London, United Kingdom, ^{2}Cardiovascular Magnetic Resonance Unit, Royal Brompton Hospital and National Heart and Lung Institute, Imperial College London, London, United Kingdom, ^{3}College of Information And Communication Engineering, Harbin Engineering University, Harbin, China

Spiral trajectories are time efficient but are susceptible to off-resonance artefacts. Many approaches to off-resonance correction require a high-quality B0 field map. Here we train a convolutional neural network to remove the off-resonance artefacts using simulated cardiac spiral MRI and validate our methods by applying this network to diffusion tensor cardiovascular MR (DTCMR) data acquired with spiral trajectories.

Traditional field map-based methods are time consuming and rely heavily on field map's quality

As the 7 available field maps are not co-registered with the EPI images, we generate simulated field maps by segmenting the heart in the 7 field maps and fitting the data within the segmented region to 3

We simulate off-resonance blurred spiral images using the original EPI images and simulated field maps as input. Off-resonance simulation was based on the frequency-segmented correction method

$$\Delta \phi_{\text {off-resonance }}=2 \pi \cdot \mathrm{i} \cdot \mathrm{T} \cdot f_{n}$$

where i indicates the index of the sampling point, T is the time interval between adjacent sampling points, and $$$f_{n}$$$ is the n

The final step of simulation is to pixel-wise select the data from the constant off-resonance images based on simulated field maps. For example, if the off-resonance frequency at $$$(x,y)$$$ in a field map is 50 Hz, then we copy the value at $$$(x,y)$$$ from the 50 Hz constant off-resonance image to $$$(x,y)$$$ in the final image. As field map values do not, in general, correspond exactly with the constant off-resonance frequencies used, linear interpolation between two closest constant frequencies images is used.

Subsequently we set the original images as ground truth and the simulated blurred versions as input to train a deblurring auto-encoder CNN which consists of 6 2D-convolution layers (encoder) and 6 up-sampling layers (decoder). We use mean square error (MSE) as the loss function and ADAM as the optimizer. The dataset is split 80/20 into training and validation sets. Learning rate is set as 0.0003 with 66 epochs.

CNN-based deblurring performance is assessed by applying it to uncorrected STEAM DTCMR data acquired with spiral trajectories in 4 healthy volunteers

Figure 5 shows the sharpness measured in the uncorrected data, the field map-corrected data and the CNN-corrected data. From the 24 randomly selected cases, the mean±standard deviation sharpness is 0.048±0.014, 0.057±0.017 and 0.062±0.015 for the uncorrected, field map corrected and CNN corrected data respectively, showing the superior performance of CNN.

Future work will enhance the CNN’s generalization by using a larger training dataset containing data from other types of acquisitions and using more realistic field maps. We also aim to make use of the multiple frames available in many CMR studies (e.g., b-values, directions, and averages in DTCMR) when training our CNN to improve performance and investigate its performance for correcting other spiral artefacts including T2* related blurring.

2. Man L-C, Pauly JM, Macovski A. Multifrequency interpolation for fast off-resonance correction. Magn. Reson. Med. 1997;37(5):785-92.

3. Zeng DY, Shaikh J, Holmes S, Brunsing RL, Pauly JM, Nishimura DG, et al. Deep residual network for off-resonance artifact correction with application to pediatric body MRA with 3D cones. Magn. Reson. Med. 2019;82(4):1398-411.

4. Lim Y, Bliesener Y, Narayanan S, Nayak KS. Deblurring for spiral real-time MRI using convolutional neural networks. Magn. Reson. Med. 2020;84(6):3438-52.

5. Nielles-Vallespin S, Mekkaoui C, Gatehouse P, Reese TG, Keegan J, Ferreira PF, et al. In vivo diffusion tensor MRI of the human heart: Reproducibility of breath-hold and navigator-based approaches. Magn. Reson. Med. 2013;70(2):454-65.

6. Scott AD, Nielles-Vallespin S, Ferreira PF, Khalique Z, Gatehouse PD, Kilner P, et al. An in-vivo comparison of stimulated-echo and motion compensated spin-echo sequences for 3 T diffusion tensor cardiovascular magnetic resonance at multiple cardiac phases. J. Cardiovasc. Magn. Reson. 2018;20(1):1.

7. Khalique Z, Scott AD, Ferreira PF, Nielles-Vallespin S, Firmin DN, Pennell DJ. Diffusion tensor cardiovascular magnetic resonance in hypertrophic cardiomyopathy: a comparison of motion-compensated spin echo and stimulated echo techniques. MAGMA. 2020;33(3):331-42.

8. Gorodezky M, Ferreira PF, Nielles-Vallespin S, Gatehouse PD, Pennell DJ, Scott AD, et al. High resolution in-vivo DT-CMR using an interleaved variable density spiral STEAM sequence. Magn. Reson. Med. 2019;81(3):1580-94.

9. Gorodezky M, Ferreira PF, Khalique Z, Nielles-Vallespin S, Silva R, Pennell DJ, Scott AD, and Firmin DN. Diffusion tensor cardiovascular magnetic resonance in myocardial infarction: A comparison between high resolution spiral and standard resolution EPI STEAM. In: International Society for Magnetic Resonance in Medicine Annual Meeting. ; 2019. p. #0780.

10. Ahmad R, Ding Y, Simonetti OP. Edge sharpness assessment by parametric modeling: Application to magnetic resonance imaging. Concepts in Magnetic Resonance Part A. 2015;44(3):138-49.

Figure 1: 7 Simulated field maps based on the 7 real field maps. Note that these simulated field maps are smooth everywhere and avoid producing misaligned edge artefacts and noise related artefacts in the final simulated images. We also generate more simulated field maps by rotating these surfaces (90/180/270˚) or adding constant offsets (amplitude 50/100/150 Hz) to them, where the latter option is used to simulate severe off-resonance effects.

Figure 2: Example of off-resonance simulation results for one subject. The blurred versions (1)-(7) are generated by the simulated field maps (1)-(7) in Figure 1 respectively.

Figure 3: Examples of CNN deblurring results for simulated images. From visual evaluation, the proposed CNN can restore the lost information and details due to blurring. The deblurring results are very similar to the corresponding ground truth images.

Figure 4: Examples of CNN deblurring results applied to data acquired with spiral trajectories. We use 4 groups of images (corresponding to 4 different subjects) with off-resonance artefacts to evaluate the proposed CNN’s performance. Red arrows point the additional artefacts introduced by the field map-correction method, while images corrected with the CNN-based method do not include these artefacts.

Figure 5: Endocardial sharpness measurements, where a higher value indicates a sharper edge. We randomly choose 6 of the images acquired with a spiral trajectory from each subject and provide the mean±standard deviation in each case. The sharpness was calculated in the uncorrected (blurred version), field map-corrected and CNN-corrected images. Note that in some cases the field map-based method gives lower sharpness than the uncorrected data due to imperfections in the field map at the endocardium.

DOI: https://doi.org/10.58530/2022/1765