Abstract
Intensity inhomogeneity in magnetic resonance (MR) images can decrease the performance of image processing, such as segmentation and registration. In this work, we propose an unsupervised learning approach to correct the inhomogeneity of an MR image based on deep image priors (DIPs). In DIPs, the structure of the convolutional neural networks was previously shown to capture the prior probability of an image, which has been demonstrated in several applications such as image denoising, segmentation, and super resolution. To obtain an inhomogeneity-free MR image, the problem was formulated in a Bayesian inference framework. The priors of the image and inhomogeneity field were captured by two DIPs and their likelihood was modeled based on the observed image. The approximated expectation of the posterior was calculated to get the corrected image using a stochastic gradient Langevin dynamics algorithm. Since we modeled the noise distribution, the proposed method is simultaneously capable of denoising to some extent. We compared our method with N4, a popular inhomogeneity correction method, in a simulated data set and a couple of real data sets, statistically showing that it has comparable or even superior performance than N4 when the inhomogeneity is severe or noise is high.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aubert-Broche, B., Griffin, M., Pike, G.B., Evans, A.C., Collins, D.L.: Twenty new digital brain phantoms for creation of validation image data bases. IEEE Trans. Med. Imaging 25(11), 1410–1416 (2006)
Chen, G., Zhu, F., Heng, P.A.: An efficient statistical method for image noise level estimation. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp. 477–485. IEEE Computer Society (2015)
Cheng, Z., Gadelha, M., Maji, S., Sheldon, D.: A Bayesian perspective on the deep image prior. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019
Gandelsman, Y., Shocher, A., Irani, M.: “Double-DIP”: unsupervised image decomposition via coupled deep-image-priors. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019
Ganzetti, M., Wenderoth, N., Mantini, D.: Quantitative evaluation of intensity inhomogeneity correction methods for structural MR brain images. Neuroinformatics 14, 5–21 (2016)
George, M.M., Kalaivani, S.: Retrospective correction of intensity inhomogeneity with sparsity constraints in transform-domain: application to brain MRI. Magn. Reson. Imaging 61, 207–223 (2019)
Hou, Z.: A review on MR image intensity inhomogeneity correction. Int. J. Biomed. Imaging 2006, 1–11 (2006)
Huo, Y., et al.: Consistent cortical reconstruction and multi-atlas brain segmentation. NeuroImage 138, 197–210 (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
LaMontagne, P.J., et al.: OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease. medRxiv (2019)
Lempitsky, V., Vedaldi, A., Ulyanov, D.: Deep image prior. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9446–9454 (2018)
Ren, D., Zhang, K., Wang, Q., Hu, Q., Zuo, W.: Neural blind deconvolution using deep priors. arXiv preprint arXiv:1908.02197 (2019)
Romero, J.E., et al.: CERES: a new cerebellum lobule segmentation method. NeuroImage 147, 916–924 (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 234–241 (2015)
Sled, J.G., Zijdenbos, A.P., Evans, A.C.: A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans. Med. Imaging 17(1), 87–97 (1998)
Tustison, N.J., et al.: N4ITK: improved N3 bias correction. IEEE Trans. Med. Imaging 29(6), 1310–1320 (2010)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Improved texture networks: maximizing quality and diversity in feed-forward stylization and texture synthesis. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6924–6932 (2017)
Vovk, U., Pernus, F., Likar, B.: A review of methods for correction of intensity inhomogeneity in MRI. IEEE Trans. Med. Imaging 26(3), 405–421 (2007)
Welling, M., Teh, Y.W.: Bayesian learning via stochastic gradient Langevin dynamics. In: Proceedings of the 28th International Conference on International Conference on Machine Learning, pp. 681–688 (2011)
Yushkevich, P.A., et al.: A high-resolution computational atlas of the human hippocampus from postmortem magnetic resonance imaging at 9.4 T. NeuroImage 44(2), 385–398 (2009)
Zhang, Z., Song, J.: A robust brain MRI segmentation and bias field correction method integrating local contextual information into a clustering model. Appl. Sci. 9(7), 1332 (2019)
Zhao, X., Xie, H., Li, W., Yang, G., Yan, X.: MRI intensity inhomogeneity correction based on similar points. In: 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 1–6 (2017)
Acknowledgments
The authors would thank colleagues from the Image Analysis and Communications Laboratory at the Johns Hopkins University for their support and help.
Data were provided in part by OASIS-3: Principal Investigators: T. Benzinger, D. Marcus, J. Morris; NIH P50AG00561, P30NS09857781, P01AG026276, P01AG003991, R01AG043434, UL1TR000448, R01EB009352. AV-45 doses were provided by Avid Radiopharmaceuticals, a wholly owned subsidiary of Eli Lilly.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Han, S., Prince, J.L., Carass, A. (2020). Inhomogeneity Correction in Magnetic Resonance Images Using Deep Image Priors. In: Liu, M., Yan, P., Lian, C., Cao, X. (eds) Machine Learning in Medical Imaging. MLMI 2020. Lecture Notes in Computer Science(), vol 12436. Springer, Cham. https://doi.org/10.1007/978-3-030-59861-7_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-59861-7_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59860-0
Online ISBN: 978-3-030-59861-7
eBook Packages: Computer ScienceComputer Science (R0)
