This study addresses challenges in fetal magnetic resonance imaging (MRI) related to motion artifacts, maternal respiration, and hardware limitations. To enhance MRI quality, we employ deep learning techniques, specifically utilizing Cycle GAN. Synthetic pairs of images, simulating artifacts in fetal MRI, are generated to train the model. Our primary contribution is the use of Cycle GAN for fetal MRI restoration, augmented by artificially corrupted data. We compare three approaches (supervised Cycle GAN, Pix2Pix, and Mobile Unet) for artifact removal. Experimental results demonstrate that the proposed supervised Cycle GAN effectively removes artifacts while preserving image details, as validated through Structural Similarity Index Measure (SSIM) and normalized Mean Absolute Error (MAE). The method proves comparable to alternatives but avoids the generation of spurious regions, which is crucial for medical accuracy.
References
[1]
Machado-Rivas, F., Jaimes, C., Kirsch, J.E. and Gee, M.S. (2020) Image-Quality Optimization and Artifact Reduction in Fetal Magnetic Resonance Imaging. Pediatric Radiology, 50, 1830-1838. https://doi.org/10.1007/s00247-020-04672-7
[2]
Victoria, T., Jaramillo, D., Roberts, T.P.L., Zarnow, D., Johnson, A.M., Delgado, J., et al. (2014) Fetal Magnetic Resonance Imaging: Jumping from 1.5 to 3 Tesla (Preliminary Experience). Pediatric Radiology, 44, 376-386.
https://doi.org/10.1007/s00247-013-2857-0
[3]
Victoria, T., Johnson, A.M., Edgar, J.C., Zarnow, D.M., Vossough, A. and Jaramillo, D. (2016) Comparison between 1.5-T and 3-T MRI for Fetal Imaging: Is There an Advantage to Imaging with a Higher Field Strength? American Journal of Roentgenology, 206, 195-201. https://doi.org/10.2214/ajr.14.14205
[4]
Gu, J. and Ye, J.C. (2021) AdaIN-Based Tunable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising. IEEE Transactions on Computational Imaging, 7, 73-85. https://doi.org/10.1109/tci.2021.3050266
[5]
Jin, K.H., Um, J., Lee, D., Lee, J., Park, S. and Ye, J.C. (2016) MRI Artifact Correction Using Sparse + Low-Rank Decomposition of Annihilating Filter-Based Hankel Matrix. Magnetic Resonance in Medicine, 78, 327-340.
https://doi.org/10.1002/mrm.26330
[6]
Landi, G. and Zama, F. (2022) A Variational Approach to Gibbs Artifacts Removal in MRI. Annali Dell’universita’ di Ferrara, 68, 465-481.
https://doi.org/10.1007/s11565-022-00431-8
[7]
Liu, S., Thung, K., Qu, L., Lin, W., Shen, D. and Yap, P. (2021) Learning MRI Artefact Removal with Unpaired Data. Nature Machine Intelligence, 3, 60-67.
https://doi.org/10.1038/s42256-020-00270-2
[8]
Mishro, P.K., Agrawal, S., Panda, R. and Abraham, A. (2022) A Survey on State-of- the-Art Denoising Techniques for Brain Magnetic Resonance Images. IEEE Reviews in Biomedical Engineering, 15, 184-199. https://doi.org/10.1109/rbme.2021.3055556
[9]
Mohan, J., Krishnaveni, V. and Guo, Y. (2014) A Survey on the Magnetic Resonance Image Denoising Methods. Biomedical Signal Processing and Control, 9, 56-69.
https://doi.org/10.1016/j.bspc.2013.10.007
[10]
Ahishakiye, E., Van Gijzen, M.B., Tumwiine, J., Wario, R. and Obungoloch, J. (2021) A Survey on Deep Learning in Medical Image Reconstruction. Intelligent Medicine, 1, 118-127. https://doi.org/10.1016/j.imed.2021.03.003
[11]
Apostolidis, K.D. and Papakostas, G.A. (2021) A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis. Electronics, 10, Article No. 2132.
https://doi.org/10.3390/electronics10172132
[12]
Wang, R., Lei, T., Cui, R., Zhang, B., Meng, H. and Nandi, A.K. (2022) Medical Image Segmentation Using Deep Learning: A Survey. IET Image Processing, 16, 1243- 1267. https://doi.org/10.1049/ipr2.12419
[13]
Armanious, K., Jiang, C., Abdulatif, S., Kustner, T., Gatidis, S. and Yang, B. (2019) Unsupervised Medical Image Translation Using Cycle-MedGAN. 2019 27th European Signal Processing Conference (EUSIPCO), Volume 1, 1-5.
https://doi.org/10.23919/eusipco.2019.8902799
[14]
Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer- Assisted Intervention-MICCAI 2015, Volume 9351, 234-241.
[15]
Demir, U. and Unal, G.B. (2018) Patch-Based Image Inpainting with Generative Adversarial Networks.
[16]
Duffy, B.A., Zhao, L., Sepehrband, F., Min, J., Wang, D.J., Shi, Y., et al. (2021) Retrospective Motion Artifact Correction of Structural MRI Images Using Deep Learning Improves the Quality of Cortical Surface Reconstructions. NeuroImage, 230, Article ID: 117756. https://doi.org/10.1016/j.neuroimage.2021.117756
[17]
Jing, J., Wang, Z., Rätsch, M. and Zhang, H. (2020) Mobile-Unet: An Efficient Convolutional Neural Network for Fabric Defect Detection. Textile Research Journal, 92, 30-42. https://doi.org/10.1177/0040517520928604
[18]
Isola, P., Zhu, J., Zhou, T. and Efros, A.A. (2017) Image-to-Image Translation with Conditional Adversarial Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 5967-5976.
https://doi.org/10.1109/cvpr.2017.632
[19]
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B. and Hochreiter, S. (2017) GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 6629-6666.
[20]
Menéndez, M.L., Pardo, J.A., Pardo, L. and Pardo, M.C. (1997) The Jensen-Shannon Divergence. Journal of the Franklin Institute, 334, 307-318.
https://doi.org/10.1016/s0016-0032(96)00063-4
[21]
Zhu, J., Park, T., Isola, P. and Efros, A.A. (2017). Unpaired Image-to-Image Translation Using Cy-cle-Consistent Adversarial Networks. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 2242-2251.
https://doi.org/10.1109/iccv.2017.244
[22]
Godenschweger, F., K?gebein, U., Stucht, D., Yarach, U., Sciarra, A., Yakupov, R., et al. (2016) Motion Correction in MRI of the Brain. Physics in Medicine and Biology, 61, R32-R56. https://doi.org/10.1088/0031-9155/61/5/r32
[23]
Chen, Z., Pawar, K., Ekanayake, M., Pain, C., Zhong, S. and Egan, G.F. (2022) Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging—State-of-the-Art and Challenges. Journal of Digital Imaging, 36, 204-230.
https://doi.org/10.1007/s10278-022-00721-9
[24]
Lim, A., Lo, J., Wagner, M.W., Ertl-Wagner, B. and Sussman, D. (2023) Motion Artifact Correction in Fetal MRI Based on a Generative Adversarial Network Method. Biomedical Signal Processing and Control, 81, Article ID: 104484.
https://doi.org/10.1016/j.bspc.2022.104484
[25]
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V. and Courville, A.C. (2017) Improved Training of Wasserstein GANs. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 5769-5779.
[26]
Chollet, F. (2017) Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 1800-1807. https://doi.org/10.1109/cvpr.2017.195
[27]
Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M. and Kalinin, A.A. (2020) Albumentations: Fast and Flexible Image Augmentations. Information, 11, Article No. 125. https://doi.org/10.3390/info11020125
[28]
Liu, S., Thung, K.-H., Qu, L., Lin, W., Shen, D. and Yap, P.-T. (2020) Inference Code: Learning MRI Artefact Removal with Unpaired Data.
https://zenodo.org/record/4474599
[29]
Isola, P., Zhu, J.-Y., Zhou, T. and Efros, A.A. (2017) CycleGAN and pix2pix in PyTorch. https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
[30]
Wang, Z., Bovik, A.C., Sheikh, H.R. and Simoncelli, E.P. (2004) Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 13, 600-612. https://doi.org/10.1109/tip.2003.819861
