Abstract
For collecting high-quality high-resolution (HR) MR image, we propose a novel image reconstruction network named IREM, which is trained on multiple low-resolution (LR) MR images and achieve an arbitrary up-sampling rate for HR image reconstruction. In this work, we suppose the desired HR image as an implicit continuous function of the 3D image spatial coordinate, and the thick-slice LR images as several sparse discrete samplings of this function. Then the super-resolution (SR) task is to learn the continuous volumetric function from a limited observation using a fully-connected neural network combined with Fourier feature positional encoding. By simply minimizing the error between the network prediction and the acquired LR image intensity across each imaging plane, IREM is trained to represent a continuous model of the observed tissue anatomy. Experimental results indicate that IREM succeeds in representing high-frequency image features, and in real scene data collection, IREM reduces scan time and achieves high-quality high-resolution MR imaging in terms of SNR and local image detail.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chen, Y., Christodoulou, A.G., Zhou, Z., Shi, F., Xie, Y., Li, D.: MRI super-resolution with GAN and 3d multi-level DenseNet: smaller, faster, and better. arXiv preprint arXiv:2003.01217 (2020)
Chen, Y., Shi, F., Christodoulou, A., Zhou, Z., Xie, Y., Li, D.: Efficient and Accurate MRI Super-Resolution Using a Generative Adversarial Network and 3D Multi-level Densely Connected Network, pp. 91–99, September 2018. https://doi.org/10.1007/978-3-030-00928-1_11
Delannoy, Q., et al.: SegSRGAN: super-resolution and segmentation using generative adversarial networks-application to neonatal brain MRI. Comput. Biol. Med. 120, 103755 (2020)
Ebner, M., et al.: An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI. NeuroImage 206, 116324 (2019). https://doi.org/10.1016/j.neuroimage.2019.116324
Gholipour, A., Estroff, J., Warfield, S.: Robust super-resolution volume reconstruction from slice acquisitions: application to fetal brain MRI. IEEE Trans. Med. Imag. 29, 1739–58 (2010). https://doi.org/10.1109/TMI.2010.2051680
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE International Conference on Computer Vision (ICCV 2015), vol. 1502, February 2015. https://doi.org/10.1109/ICCV.2015.123
Hornik, K., Stinchcomb, M., White, H.: Multilayer feedforward networks are universal approximator. IEEE Trans. Neural Netw. 2, 359–366 (1989)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift, February 2015
Jia, Y., He, Z., Gholipour, A., Warfield, S.: Single anisotropic 3-d MR image upsampling via overcomplete dictionary trained from in-plane high resolution slices. IEEE J. Biomed. Health Inform. 20 (2015). https://doi.org/10.1109/JBHI.2015.2470682
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, December 2014
Lyu, Q., et al.: Multi-contrast super-resolution MRI through a progressive network. IEEE Trans. Med. Imaging 39(9), 2738–2749 (2020)
Lyu, Q., Shan, H., Wang, G.: MRI super-resolution with ensemble learning and complementary priors. IEEE Trans. Comput. Imag. 6, 615–624 (2020)
Mildenhall, B., Srinivasan, P., Tancik, M., Barron, J., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis, pp. 405–421, November 2020. https://doi.org/10.1007/978-3-030-58452-8_24
Peled, S., Yeshurun, Y.: Superresolution in MRI: application to human white matter fiber tract visualization by diffusion tensor imaging. Magn. Reson. Med. Off. J. Soc. Magn. Reson. Med. Soc. Magn. Reson. Med. 45, 29–35 (2001). https://doi.org/10.1002/1522-2594(200101)45:18216;29::aid-mrm10058217;3.0.co;2-z
Pham, C.H., Ducournau, A., Fablet, R., Rousseau, F.: Brain MRI super-resolution using deep 3d convolutional networks. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp. 197–200. IEEE (2017)
Rahaman, N., et al.: On the spectral bias of neural networks. In: International Conference on Machine Learning, pp. 5301–5310. PMLR (2019)
Rueda, A., Malpica, N., Romero, E.: Single-image super-resolution of brain MR images using overcomplete dictionaries. Med. Image Anal. 17, 113–132 (2012). https://doi.org/10.1016/j.media.2012.09.003
Scherrer, B., Gholipour, A., Warfield, S.K.: Super-resolution reconstruction to increase the spatial resolution of diffusion weighted images from orthogonal anisotropic acquisitions. Med. Image Anal. 16(7), 1465–1476 (2012)
Shi, F., Cheng, J., Wang, L., Yap, P.T., Shen, D.: LRTV: MR image super-resolution with low-rank and total variation regularizations. IEEE Trans. Med. Imag. 34 (2015). https://doi.org/10.1109/TMI.2015.2437894
Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. arXiv preprint arXiv:2006.10739 (2020)
Ur Rahman, S., Wesarg, S.: Combining short-axis and long-axis cardiac MR images by applying a super-resolution reconstruction algorithm. Fraunhofer IGD 7623, March 2010. https://doi.org/10.1117/12.844356
Van Reeth, E., Tan, C.H., Tham, I., Poh, C.L.: Isotropic reconstruction of a 4-d MRI thoracic sequence using super-resolution. Magn. Reson. Med. Off. J. Soc. Magn. Reson. Med. Soc. Magn. Reson. Med. 73 (2015). https://doi.org/10.1002/mrm.25157
Wang, Z., Bovik, A., Sheikh, H., Member, S., Simoncelli, E.: Image quality assessment: from error measurement to structural similarity. IEEE Trans. Imag. Process. 13 (2003)
Yang, J., Wright, J., Yu, L.: Image super-resolution via sparse representation. Image Process. IEEE Trans. 19, 2861–2873 (2010). https://doi.org/10.1109/TIP.2010.2050625
Acknowledgements
This study is supported by the National Natural Science Foundation of China (No. 62071299, 61901256).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, Q. et al. (2021). IREM: High-Resolution Magnetic Resonance Image Reconstruction via Implicit Neural Representation. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12906. Springer, Cham. https://doi.org/10.1007/978-3-030-87231-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-87231-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87230-4
Online ISBN: 978-3-030-87231-1
eBook Packages: Computer ScienceComputer Science (R0)
