Ultra-Low-Dose Spectral CT Based on a Multi-level Wavelet Convolutional Neural Network
Tóm tắt
Spectral computed tomography (CT) based on a photon-counting detector (PCD) is a promising technique with the potential to improve lesion detection, tissue characterization, and material decomposition. PCD-based scanners have several technical issues including operation in the step-and-scan mode and long data acquisition time. One straightforward solution to these issues is to reduce the number of projection views. However, if the projection data are under-sampled or noisy, it would be challenging to produce a correct solution without precise prior information. Recently, deep-learning approaches have demonstrated impressive performance for under-sampled CT reconstruction. In this work, the authors present a multilevel wavelet convolutional neural network (MWCNN) to address the limitations of PCD-based scanners. Data properties of the proposed method in under-sampled spectral CT are analyzed with respect to the proposed deep-running-network-based image reconstruction using two measures: sampling density and data incoherence. This work presents the proposed method and four different methods to restore sparse sampling. We investigate and compare these methods through a simulation and real experiments. In addition, data properties are quantitatively analyzed and compared for the effect of sparse sampling on the image quality. Our results indicate that both sampling density and data incoherence affect the image quality in the studied methods. Among the different methods, the proposed MWCNN shows promising results. Our method shows the highest performance in terms of various evaluation parameters such as the structural similarity, root mean square error, and resolution. Based on the results of imaging and quantitative evaluation, this study confirms that the proposed deep-running network structure shows excellent image reconstruction in sparse-view PCD-based CT. These results demonstrate the feasibility of sparse-view PCD-based CT using the MWCNN. The advantage of sparse view CT is that it can significantly reduce the radiation dose and obtain images with several energy bands by fusing PCDs. These results indicate that the MWCNN possesses great potential for sparse-view PCD-based CT.
Tài liệu tham khảo
Wang G, Yu H, De Man B. An outlook on x-ray CT research and development. Med Phys. 2008;35(3):1051‐1064. https://doi.org/10.1118/1.2836950
Alvarez RE, Macovski A. Energy-selective reconstructions in X-ray computerized tomography. Phys Med Biol. 1976;21(5):733‐744. https://doi.org/10.1088/0031-9155/21/5/002
De Man B, Nuyts J, Dupont P, Marchal G, Suetens P. An iterative maximum-likelihood polychromatic algorithm for CT. IEEE Trans Med Imaging. 2001;20(10):999‐1008. https://doi.org/10.1109/42.959297
Graser A, Johnson TR, Chandarana H, Macari M. Dual energy CT: preliminary observations and potential clinical applications in the abdomen. Eur Radiol. 2009;19(1):13‐23. https://doi.org/10.1007/s00330-008-1122-7
Yu L, Leng S, McCollough CH. Dual-energy CT-based monochromatic imaging. AJR Am J Roentgenol. 2012;199(5 Suppl):S9‐S15. https://doi.org/10.2214/AJR.12.9121
Lv P, Lin XZ, Chen K, Gao J. Spectral CT in patients with small HCC: investigation of image quality and diagnostic accuracy. Eur Radiol. 2012;22(10):2117‐2124. https://doi.org/10.1007/s00330-012-2485-3
Zhao LQ, He W, Li JY, Chen JH, Wang KY, Tan L. Improving image quality in portal venography with spectral CT imaging. Eur J Radiol. 2012;81(8):1677‐1681. https://doi.org/10.1016/j.ejrad.2011.02.063
Heismann BJ, Schmidt BT, Flohr T. Spectral computed tomography. Bellingham, WA: SPIE; 2012.
Yang Q, Cong W, Xi Y, Wang G. Spectral X-Ray CT Image Reconstruction with a Combination of Energy-Integrating and Photon-Counting Detectors. PLoS One. 2016;11(5):e0155374. Published 2016 May 12. https://doi.org/10.1371/journal.pone.0155374
Shikhaliev PM, Fritz SG. Photon counting spectral CT versus conventional CT: comparative evaluation for breast imaging application. Phys Med Biol. 2011;56(7):1905‐1930. https://doi.org/10.1088/0031-9155/56/7/001
Leng S, Yu L, Wang J, Fletcher JG, Mistretta CA, McCollough CH. Noise reduction in spectral CT: reducing dose and breaking the trade-off between image noise and energy bin selection. Med Phys. 2011;38(9):4946‐4957. https://doi.org/10.1118/1.3609097
Yu Z, Leng S, Li Z, McCollough CH. Spectral prior image constrained compressed sensing (spectral PICCS) for photon-counting computed tomography. Phys Med Biol. 2016;61(18):6707‐6732. https://doi.org/10.1088/0031-9155/61/18/6707
Zeng D, Huang J, Zhang H, et al. Spectral CT Image Restoration via an Average Image-Induced Nonlocal Means Filter. IEEE Trans Biomed Eng. 2016;63(5):1044‐1057. https://doi.org/10.1109/TBME.2015.2476371
Zeng D, Gao Y, Huang J, et al. Penalized weighted least-squares approach for multienergy computed tomography image reconstruction via structure tensor total variation regularization. Comput Med Imaging Graph. 2016;53:19‐29. https://doi.org/10.1016/j.compmedimag.2016.07.002
Roessl E, Proksa R. K-edge imaging in x-ray computed tomography using multi-bin photon counting detectors. Phys Med Biol. 2007;52(15):4679‐4696. https://doi.org/10.1088/0031-9155/52/15/020
He P, Wei B, Cong W, Wang G. Optimization of K-edge imaging with spectral CT. Med Phys. 2012;39(11):6572‐6579. https://doi.org/10.1118/1.4754587
Schirra CO, Roessl E, Koehler T, et al. Statistical reconstruction of material decomposed data in spectral CT. IEEE Trans Med Imaging. 2013;32(7):1249‐1257. https://doi.org/10.1109/TMI.2013.2250991
Elbakri IA, Fessler JA. Statistical image reconstruction for polyenergetic X-ray computed tomography. IEEE Trans Med Imaging. 2002;21(2):89‐99. https://doi.org/10.1109/42.993128
Sawatzky A, Xu Q, Schirra CO, Anastasio MA. Proximal ADMM for multi-channel image reconstruction in spectral X-ray CT. IEEE Trans Med Imaging. 2014;33(8):1657‐1668. https://doi.org/10.1109/TMI.2014.2321098
Kim K, Ye JC, Worstell W, et al. Sparse-view spectral CT reconstruction using spectral patch-based low-rank penalty. IEEE Trans Med Imaging. 2015;34(3):748‐760. https://doi.org/10.1109/TMI.2014.2380993
Zhang Y, Mou X, Wang G, Yu H. Tensor-Based Dictionary Learning for Spectral CT Reconstruction. IEEE Trans Med Imaging. 2017;36(1):142‐154. https://doi.org/10.1109/TMI.2016.2600249
Wang M, Zhang Y, Liu R, Guo S, Yu H. An adaptive reconstruction algorithm for spectral CT regularized by a reference image. Phys Med Biol. 2016;61(24):8699‐8719. https://doi.org/10.1088/1361-6560/61/24/8699
Li S, Zeng D, Peng J, et al. An Efficient Iterative Cerebral Perfusion CT Reconstruction via Low-Rank Tensor Decomposition With Spatial-Temporal Total Variation Regularization. IEEE Trans Med Imaging. 2019;38(2):360‐370. https://doi.org/10.1109/TMI.2018.2865198
Chen GH, Tang J, Leng S. Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. Med Phys. 2008;35(2):660‐663. https://doi.org/10.1118/1.2836423
Sidky EY, Pan X. Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization. Phys Med Biol. 2008;53(17):4777‐4807. https://doi.org/10.1088/0031-9155/53/17/021
Singh S, Kalra MK, Gilman MD, et al. Adaptive statistical iterative reconstruction technique for radiation dose reduction in chest CT: a pilot study. Radiology. 2011;259(2):565‐573. https://doi.org/10.1148/radiol.11101450
Andersen AH, Kak AC. Simultaneous algebraic reconstruction technique (SART): a superior implementation of the art algorithm. Ultrason Imaging. 1984;6(1):81‐94. https://doi.org/10.1177/016173468400600107
Donoho DL. Compressed sensing. IEEE Transactions on information theory. 2006;52(4):1289-1306.
Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 2012.
Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015.
Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Trans Image Proces. 2017;26(7):3142‐3155. https://doi.org/10.1109/TIP.2017.2662206
Shi, W., Caballero, J., Huszár, F., Totz, J., Aitken, A. P., Bishop, R., ... & Wang, Z. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 1874–1883.
Kang E, Min J, Ye JC. A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Med Phys. 2017;44(10):e360‐e375. https://doi.org/10.1002/mp.12344
Kang, E., & Ye, J. C. "Wavelet domain residual network (WavResNet) for low-dose X-ray CT reconstruction." arXiv preprint arXiv 1703.01383; 2017.
Kang E, Chang W, Yoo J, Ye JC. Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network. IEEE Trans Med Imaging. 2018;37(6):1358‐1369. https://doi.org/10.1109/TMI.2018.2823756
Mao X, Shen C, Yang YB. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. Advances in neural information processing systems. 2016.
Xie J, Xu L, Chen E. Image denoising and inpainting with deep neural networks. Advances in neural information processing systems. 2012.
Kyong Hwan Jin, McCann MT, Froustey E, Unser M. Deep Convolutional Neural Network for Inverse Problems in Imaging. IEEE Trans Image Process. 2017;26(9):4509‐4522. https://doi.org/10.1109/TIP.2017.2713099
Han YS, Yoo J, Ye JC. Deep residual learning for compressed sensing CT reconstruction via persistent homology analysis. 2016. arXiv preprint arXiv 1611.06391.
Daubechies I. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on information theory. 1990;36(5):961-1005.
Daubechies I. Ten lectures on wavelets. Vol. 61. Siam; 1992.
Taguchi K, Stierstorfer K, Polster C, Lee O, Kappler S. Spatio-energetic cross-talk in photon counting detectors: Numerical detector model (PcTK) and workflow for CT image quality assessment. Med Phys. 2018;45(5):1985‐1998. https://doi.org/10.1002/mp.12863
ICRU Report 44. Tissue Substitutes in Radiation Dosimetry and Measurement. Bethesda, MD: International Commission on Radiation Units and Measurements (ICRU); 1989.
Yu F, and Koltun V. Multi-scale context aggregation by dilated convolutions. 2015. arXiv preprint arXiv 1511.07122.
Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations. International conference on curves and surfaces. Springer, Berlin, Heidelberg; 2010.
Wang P, Chen P, Yuan Y, et al. Understanding convolution for semantic segmentation. 2018 IEEE winter conference on applications of computer vision (WACV). IEEE; 2018.
Ye JC, Han Y, Cha E. Deep convolutional framelets: A general deep learning framework for inverse problems. SIAM Journal on Imaging Sciences. 2018;11(2):991-1048.
Lehmann LA, Alvarez RE, Macovski A, et al. Generalized image combinations in dual KVP digital radiography. Med Phys. 1981;8(5):659‐667. https://doi.org/10.1118/1.595025.
Kelcz F, Joseph PM, Hilal SK. Noise considerations in dual energy CT scanning. Med Phys. 1979;6(5):418‐425. https://doi.org/10.1118/1.594520.
Cho HM, Barber WC, Ding H, Iwanczyk JS, Molloi S. Characteristic performance evaluation of a photon counting Si strip detector for low dose spectral breast CT imaging. Med Phys. 2014;41(9):091903. https://doi.org/10.1118/1.4892174.
Lee MJ, Lee DH, Kim DH, et al. Development of a non-linear dual-energy technique in chest radiography. Radiation Physics and Chemistry. 2020;108811.
Xue H, Zhang L, Cheng Z, Xing Y, Xiao Y. An improved TV minimization algorithm for incomplete data problem in computer tomography. In: IEEE Nuclear Science Symposuim & Medical Imaging Conference. IEEE; 2010.
Gao Y, Bian Z, Huang J, et al. Low-dose X-ray computed tomography image reconstruction with a combined low-mAs and sparse-view protocol. Opt Express. 2014;22(12):15190-15210.
Lee M, Kim H, Kim HJ. Sparse-view CT reconstruction based on multi-level wavelet convolution neural network. Phys Med. 2020;80:352-362. https://doi.org/10.1016/j.ejmp.2020.11.021.
Taguchi K, Iwanczyk JS. Vision 20/20: Single photon counting x-ray detectors in medical imaging. Med Phys. 2013;40(10):100901. https://doi.org/10.1118/1.4820371.
Leng S, Bruesewitz M, Tao S, et al. Photon-counting Detector CT: System Design and Clinical Applications of an Emerging Technology. Radiographics. 2019;39(3):729-743. https://doi.org/10.1148/rg.2019180115.
Willemink MJ, Persson M, Pourmorteza A, Pelc NJ, Fleischmann D. Photon-counting CT: Technical Principles and Clinical Prospects. Radiology. 2018;289(2):293-312. https://doi.org/10.1148/radiol.2018172656
Mahmoudi G, Fouladi MR, Ay MR, Rahmim A, Ghadiri H. Sparse-view statistical image reconstruction with improved total variation regularization for X-ray micro-CT imaging. J Instru. 2019;14(08):P08023-P08023.
Szczykutowicz, TP, Chen, GH. Dual energy CT using slow kVp switching acquisition and prior image constrained compressed sensing. Phys Med Biol 2010; 55.21: 6411.
Abbas, S et al. Effects of sparse sampling schemes on image quality in low‐dose CT. Medical Phys 2013; 40.11: 111915.
Lee, T et al. Moving beam-blocker-based low-dose cone-beam CT. IEEE Trans Nuclear Sci 2016; 63.5: 2540–2549.
Pan, X, Sidky, EM, Vannier, M. Why do commercial CT scanners still employ traditional, filtered back-projection for image reconstruction?. Inverse Problems 2009; 25.12: 123009.
Bian, J et al. Evaluation of sparse-view reconstruction from flat-panel-detector cone-beam CT. Phys Med Biol 2010; 55.22: 6575.