Research on Spectral CT Image Denoising Via Fully Convolution Pyramid Residual Network
REN Xue-zhi1, HE Peng1, 2*, LONG Zou-rong1, GUO Xiao-dong1, AN Kang2, LÜ Xiao-jie1, WEI Biao1, 2, FENG Peng1, 2*
1. Key Laboratory of Optoelectronics Technology & System (Chongqing University), Ministry of Education, Chongqing 400044, China
2. ICT-NDT Engineering Research Center (Chongqing University), Ministry of Education, Chongqing 400044, China
Abstract:Traditional computed tomography(CT) uses an integral detector to collect projection, which reflects the average attenuation characteristics of the object and causes the loss of attenuation characteristics to some extent, so it cannot measure the object qualitatively and quantitatively. The spectral CT based on photon-counting detectors can collect the incident photons in different energy ranges by setting several energy thresholds to collect more material composition information of measured objects, which is helpful to identify materials with different physical characteristics, so the spectral CT is widely used in imaging of small lesions, low contrast structures and fine structures. However, dividing the whole energy spectrum into several energy segments for data acquisition will lead to the relatively reduced proportion of effective photons, resulting in more noise in the image and affecting the clinical application of energy spectrum CT. To effectively suppress the noise in different energy segments of spectral CT image, we propose an image denoising method basedondeeplearning. We combine the full convolution network and the residual pyramid network into the full convolution pyramid residual network (FCPRN). Our study, scanned a mouse specimen with spectral CT based on photon-counting detector and used the FDK algorithm and Split-Bregman algorithm for reconstruction to obtain training data and labeled data, respectively. Then we use the data set to train our network for image denoising. To verify our network’s performance, we selected the common denoising networks, denoising convolutional neural networks(DNCNN)and residual encoder-decoder convolutional neural network(REDCNN)for comparison, and the training data and experimental configuration of the three networks are identical. Experimental results demonstrated that the proposed method could reduce the noise of spectral CT images in different energy ranges,and the performance of FCPRN is better than that of other neural networks discussed in this paper for denoising. When the model is trained, the image reconstructed by the FDK algorithm can be processed quickly via the model to improve the denoising efficiency and ensure the reconstructed image’s quality of spectral CT.
Key words:Spectral CT; Image Denoising; Deep learning; Photon-counting detector
[1] ZHANG Yun-gang, YI Ben-shun, WU Chen-yue, et al(章云港, 易本顺, 吴晨玥, 等). Acta Optica Sinica(光学学报), 2018, 38(4): 0410003.
[2] Wu X, He P, Long Z, et al. Journal of X-Ray Science and Technology, 2019, 27(3): 461.
[3] Moghiseh M, Aamir R, Panta R K, et al. JSM Biomed Imaging Data Pap, 2016, 61: 1007.
[4] Clark D P, Badea C T. Physics in Medicine & Biology, 2014, 59(21): 6445.
[5] Rigie D S, La Rivière P J. Physics in Medicine & Biology, 2015, 60(5): 1741.
[6] Sun Y, Liu X, Cong P, et al. Journal of X-Ray Science and Technology, 2018, 26(4): 523.
[7] Yang Q, Yan P, Zhang Y, et al. IEEE Transactions on Medical Imaging, 2018, 37(6): 1348.
[8] Chen H, Zhang Y, Zhang W, et al. Biomedical Optics Express, 2017, 8(2): 679.
[9] Grass M, Köhler T, Proksa R. Physics in Medicine & Biology, 2000, 45(2): 329.
[10] Chen C, Xu G. Computers & Mathematics with Applications, 2016, 71(8): 1537.
[11] Ben-Cohen A, Klang E, Kerpel A, et al. Neurocomputing, 2018, 275: 1585.
[12] Han D, Kim J, Kim J. Deep Pyramidal Residual Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017: 6307.
[13] He K, Zhang X, Ren S, et al. Identity Mappings in Deep Residual Networks. European Conference on Computer Vision. Springer, Cham, 2016. 630.
[14] YANG Liu, QI Hong-liang, XU Yuan, et al(杨 柳, 齐宏亮, 徐 圆, 等). Journal of Southern Medical University(南方医科大学学报),2014,34(6): 783.
[15] Zhang K, Zuo W, Chen Y, et al. IEEE Transactions on Image Processing, 2017, 26(7): 3142.