Abstract
Deep neural networks have shown great success in low dose CT denoising. However, most of these deep neural networks have several hundred thousand trainable parameters. This, combined with the inherent non-linearity of the neural network, makes the deep neural network difficult to understand with low accountability. In this study we introduce JBFnet, a neural network for low dose CT denoising. The architecture of JBFnet implements iterative bilateral filtering. The filter functions of the Joint Bilateral Filter (JBF) are learned via shallow convolutional networks. The guidance image is estimated by a deep neural network. JBFnet is split into four filtering blocks, each of which performs Joint Bilateral Filtering. Each JBF block consists of 112 trainable parameters, making the noise removal process comprehendable. The Noise Map (NM) is added after filtering to preserve high level features. We train JBFnet with the data from the body scans of 10 patients, and test it on the AAPM low dose CT Grand Challenge dataset. We compare JBFnet with state-of-the-art deep learning networks. JBFnet outperforms CPCE3D, GAN and deep GFnet on the test dataset in terms of noise removal while preserving structures. We conduct several ablation studies to test the performance of our network architecture and training method. Our current setup achieves the best performance, while still maintaining behavioural accountability.
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
Angel, E.: AIDR 3D iterative reconstruction: integrated, automated and adaptive dose reduction (2012). https://us.medical.canon/download/aidr-3d-wp-aidr-3d
Fan, F., et al.: Quadratic autoencoder (Q-AE) for low-dose CT denoising. IEEE Trans. Med. Imaging (2019). https://doi.org/10.1109/tmi.2019.2963248
Gilbert, P.: Iterative methods for the three-dimensional reconstruction of an object from projections. J. Theor. Biol. 36(1), 105–117 (1972). https://doi.org/10.1016/0022-5193(72)90180-4
Goodfellow, I.J., Bengio, Y., Courville, A.: Deep Learning (2014). https://doi.org/10.1016/B978-0-12-801775-3.00001-9
Hounsfield, G.N.: Computerized transverse axial scanning (tomography). Br. J. Radiol. 46(552), 1016–1022 (1973). https://doi.org/10.1259/0007-1285-46-552-1016
Kaczmarz, S.: Angenäherte Auflösung von Systemen linearer Gleichungen. Bulletin International de l’Académie Polonaise des Sciences et des Lettres. Classe des Sciences Mathématiques et Naturelles. Série A, Sciences Mathématiques 35, 355–357 (1937)
Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539
Li, M., Hsu, W., Xie, X., Cong, J., Gao, W.: SACNN: self-attention convolutional neural network for low-dose CT denoising with self-supervised perceptual loss network. IEEE Trans. Med. Imaging (2020). https://doi.org/10.1109/TMI.2020.2968472
Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: International Conference on Machine Learning, vol. 30, p. 6 (2013)
Maier, A., Fahrig, R.: GPU denoising for computed tomography. In: Xun, J., Jiang, S. (eds.) Graphics Processing Unit-Based High Performance Computing in Radiation Therapy, 1 edn., pp. 113–128. CRC Press, Boca Raton (2015)
Maier, A., et al.: Precision learning: towards use of known operators in neural networks. In: Proceedings of the International Conference on Pattern Recognition, No. 2, pp. 183–188 (2018). https://doi.org/10.1109/ICPR.2018.8545553
Maier, A.K., et al.: Learning with known operators reduces maximum error bounds. Nature Mach. Intell. 1(8), 373–380 (2019). https://doi.org/10.1038/s42256-019-0077-5
Manduca, A., et al.: Projection space denoising with bilateral filtering and CT noise modeling for dose reduction in CT. Med. Phys. 36(11), 4911–4919 (2009). https://doi.org/10.1118/1.3232004
Manhart, M., Fahrig, R., Hornegger, J., Doerfler, A., Maier, A.: Guided noise reduction for spectral CT with energy-selective photon counting detectors. In: Proceedings of the Third CT Meeting, No. 1, pp. 91–94 (2014)
Mccollough, C.H.: Low Dose CT Grand Challenge (2016)
Nie, D., et al.: Medical image synthesis with context-aware generative adversarial networks. In: Medical Image Computing and Computer Assisted Intervention, vol. 3, pp. 417–425 (2017). https://doi.org/10.1007/978-3-319-66179-7
Oppelt, A.: Noise in computed tomography. In: Aktiengesselschaft, S. (ed.) Imaging Systems for Medical Diagnostics, chap. 13.1.4.2, 2nd edn., p. 996. Publicis Corporate Publishing (2005). https://doi.org/10.1145/2505515.2507827
Ramirez-Giraldo, J.C., Grant, K.L., Raupach, R.: ADMIRE: advanced modeled iterative reconstruction (2015). https://www.siemens-healthineers.com/computed-tomography/technologies-innovations/admire
Shan, H., et al.: Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction. Nature Mach. Intell. 1(6), 269–276 (2019). https://doi.org/10.1038/s42256-019-0057-9
Shan, H., et al.: 3D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2D trained network. IEEE Trans. Med. Imaging 37(6), 1522–1534 (2018). https://doi.org/10.4172/2157-7633.1000305
Syben, C., et al.: Precision learning: reconstruction filter kernel discretization. In: Proceedings of the 5th International Conference on Image Formation in X-ray Computed Tomography, Salt Lake City, pp. 386–390 (2017)
Wolterink, J.M., Dinkla, A.M., Savenije, M.H., Seevinck, P.R., van den Berg, C.A., Isgum, I.: Deep MR to CT synthesis using unpaired data. In: Workshop on Simulation and Synthesis in Medical Imaging, pp. 14–23 (2017). https://doi.org/10.1007/978-3-319-68127-6
Wolterink, J.M., Leiner, T., Viergever, M.A., Isgum, I.: Generative l CT. IEEE Trans. Med. Imaging 36(12), 2536–2545 (2017). https://doi.org/10.1109/TMI.2017.2708987
Wu, H., Zheng, S., Zhang, J., Huang, K.: Fast end-to-end trainable guided filter. In: Computer Vision and Pattern Recognition, pp. 1838–1847 (2018)
Yang, Q., et al.: Low-dose CT Image denoising using a generative adversarial network with wasserstein distance and perceptual loss. IEEE Trans. Med. Imaging 37(6), 1348–1357 (2018). https://doi.org/10.1109/TMI.2018.2827462
Zhang, Y., et al.: Low-dose CT via convolutional neural network. Biomed. Opt. Express 8(2), 679–694 (2017). https://doi.org/10.1364/boe.8.000679
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Patwari, M., Gutjahr, R., Raupach, R., Maier, A. (2020). JBFnet - Low Dose CT Denoising by Trainable Joint Bilateral Filtering. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12262. Springer, Cham. https://doi.org/10.1007/978-3-030-59713-9_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-59713-9_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59712-2
Online ISBN: 978-3-030-59713-9
eBook Packages: Computer ScienceComputer Science (R0)
