ISSN 1004-4140
CN 11-3017/P
| Citation: |
ZHANG R, KONG H H, LI J X, et al. Dense Sandstone Material Decomposition Based on Improved Convolutional Neural Network[J]. CT Theory and Applications, 2025, 34(1): 117-128. DOI: 10.15953/j.ctta.2024.131. (in Chinese).
|
Energy spectrum computed tomography can provide quantitative information of scanned objects and realize material decomposition. At present, the material decomposition method based on neural networks overcomes the limited decomposition effect of traditional iterative algorithms. However, the performance of traditional neural networks in feature detail recovery is still not satisfactory. To improve the material decomposition accuracy, a material decomposition method based on a Resnet and Squeeze excitation network (RS-Net) is proposed. The proposed method uses the structure of the U-Net network and Resnet-152 as the backbone network to extract multi-scale features. Parallel asymmetric convolution is used to complete the large kernel convolution, which reduces the number of parameters and computation of the network. The HD-SE attention mechanism is introduced in the decoder part to help the network recover the image features. Hybrid loss supervised network learning is used to improve the decomposition accuracy of the network. The feasibility of this method is verified on simulated rock and artificial sandstone datasets. The simulation and experimental results show that RS-Net combined with mixing loss can retain more internal details of the image, the decomposed image edge is clearer, and the image quality is higher.
| [1] |
ALVAREZ R E, MACOVSKI A. Energy-selective reconstructions in X-ray computerised tomography[J]. Physics in Medicine and Biology, 1976, 21(5): 733-744. DOI: 10.1088/0031-9155/21/5/002.
|
| [2] |
GENG M, TIAN Z, JIANG Z, et al. PMS-GAN: Parallel multi-stream generative adversarial network for multi-material decomposition in spectral computed tomography[J]. IEEE Transactions on Medical Imaging, 2021, 40(2): 571-584. DOI: 10.1109/TMI.2020.3031617.
|
| [3] |
FANG W, WU D, KIM K, et al. Iterative material decomposition for spectral CT using self-supervised Noise2Noise prior[J]. Physics in Medicine and Biology, 2021, 66(15): 155013. DOI: 10.1088/1361-6560/ac0afd.
|
| [4] |
YAO Y, LI L, CHEN Z. Dynamic-dual-energy spectral CT for improving multi-material decomposition in image-domain[J]. Physics in Medicine and Biology, 2019, 64(13): 135006. DOI: 10.1088/1361-6560/ab196d.
|
| [5] |
BARBER R F, SIDKY E Y, SCHMIDT T G, et al. An algorithm for constrained one-step inversion of spectral CT data[J]. Physics in Medicine and Biology, 2016, 61(10): 3784-3818. DOI: 10.1088/0031-9155/61/10/3784.
|
| [6] |
LEHMANN L A, ALVAREZ R E, MACOVSKI A, et al. Generalized image combinations in dual kVP digital radiography[J]. Medical Physics, 1981, 8(5): 659-667. DOI: 10.1118/1.595025.
|
| [7] |
LI Z, LENG S, YU L, et al. Image-based material decomposition with a general volume constraint for photon-counting CT[A]. Proceedings of SPIE the International Society for Optical Engineering, 2015, 94120T.
|
| [8] |
SUKOVIC P, CLINTHORNE N H. Penalized weighted least-squares image reconstruction for dual energy X-ray transmission tomography[J]. IEEE Transactions on Medical Imaging, 2000, 19(11): 1075-1081. DOI: 10.1109/42.896783.
|
| [9] |
HEISMANN B J, LEPPERT J, STIERSTORFER K. Density and atomic number measurements with spectral X-ray attenuation method[J]. Journal of Applied Physics, 2003, 94(3): 2073-2079. DOI: 10.1063/1.1586963.
|
| [10] |
SCHLOMKA J P, ROESSL E, DORSCHEID R, et al. Experimental feasibility of multi-energy photon-counting K-edge imaging in pre-clinical computed tomography[J]. Physics in Medicine and Biology, 2008, 53(15): 4031-4047. DOI: 10.1088/0031-9155/53/15/002.
|
| [11] |
CARMI R, NAVEH G, ALTMAN A. Material separation with dual-layer CT[A]. IEEE Nuclear Science Symposium Conference Record, 2005, 1876-1878. DOI: 10.1109/NSSMIC.2005.1596697.
|
| [12] |
WANG G. A perspective on deep imaging[J]. IEEE Access, 2016, 4: 8914-8924. DOI: 10.1109/ACCESS.2016.2624938.
|
| [13] |
GONG H, TAO S, RAJENDRAN K, et al. Deep-learning-based direct inversion for material decomposition[J]. Medical Physics, 2020, 47(12): 6294-6309. DOI: 10.1002/mp.14523.
|
| [14] |
WU X, HE P, LONG Z, et al. Multi-material decomposition of spectral CT images via Fully Convolutional DenseNets[J]. Journal of X-ray Science and Technology, 2019, 27(3): 461-471. DOI: 10.3233/XST-190500.
|
| [15] |
JI X, LU Y, ZHANG Y, et al. SeNAS-Net: Self-supervised noise and artifact suppression network for material decomposition in spectral CT[J]. IEEE Transactions on Computational Imaging, Computational Imaging, IEEE Transactions on, IEEE Trans Comput Imaging, 2024, 10: 677-689. DOI: 10.1109/TCI.2024.3394772.
|
| [16] |
王冲旭, 陈平, 潘晋孝, 等. 基于迭代残差网络的双能CT图像材料分解研究[J]. CT理论与应用研究, 2022, 31(1): 47-54. DOI: 10.15953/j.1004-4140.2022.31.01.05.
WANG C X, CHEN P, PAN J X, et al. Research on material decomposition of dual-energy CT images based on iterative residual network[J]. CT Theory and Applications, 2022, 31(1): 47-54. DOI: 10.15953/j.1004-4140.2022.31.01.05. (in Chinese).
|
| [17] |
ZIMMERMAN K C, SCHMIDT T G. Experimental comparison of empirical material decomposition methods for spectral CT[J]. Physics in Medicine and Biology, 2015, 60(8): 3175-3191. DOI: 10.1088/0031-9155/60/8/3175.
|
| [18] |
NADKARNI R, ALLPHIN A, CLARK D P, et al. Material decomposition from photon-counting CT using a convolutional neural network and energy-integrating CT training labels[J]. Physics in Medicine and Biology, 2022, 67(15): 155003. DOI: 10.1088/1361-6560/ac7d34.
|
| [19] |
HU J, SHEN L, SAMUEL A, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.
|
| [20] |
WANG Q L, WU B G, ZHU P F, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks[C]// 2020 IEEE Transaction on Pattern Analysis and Machine Intelligence. 2020: 11531–11539. DOI: 10.1109/TPAMI.2019.2913372.
|
| [21] |
WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]//Lecture Notes in Computer Science, 2018: 3-19. DOI: 10.1007/978-3-030-01234-2_1.
|
| [22] |
吕振虎, 许新征, 张芳艳. 基于挤压激励的轻量化注意力机制模块[J]. 计算机应用, 2022, 42(8): 2353-2360. DOI: 10.11772/j.issn.1001-9081.2021061037.
LV Z H, XU X Z, ZHANG F Y. Lightweight attention mechanism module based on squeeze incentive[J]. Computer Applications, 2022, 42(8): 2353-2360. DOI: 10.11772/j.issn.1001-9081.2021061037. (in Chinese).
|
| [23] |
SEIF G, ANDROUTSOS D. Edge-based loss function for single image super-resolution[A]. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2018: 1468-1472. DOI: 10.1109/ICASSP.2018.8461664.
|
| [24] |
王晋庥, 王海鹏, 刘锐, 等. 人造砂岩样品多尺度微观结构表征和流体流动模拟[J]. 山西大学学报(自然科学版), 2023, 46(6): 1378-1385. DOI: 10.13451/j.sxu.ns.2023030.
WANG J X, WANG H P, LIU R, et al. Multi-scale microstructure characterization and fluid flow simulation of artificial sandstone samples[J]. Journal of Shanxi University (Natural Science Edition), 2023, 46(6): 1378-1385. DOI: 10.13451/j.sxu.ns.2023030. (in Chinese).
|
| [1] | WANG Lingyun, SHI Bowen, LI Jiqiang, DONG Haipeng, LV Xiaoyu, PAN Zhaocheng. Application of Ultra-high-resolution Scanning in Abdominal Artery CTA Using Photon-counting CT[J]. CT Theory and Applications, 2025, 34(3): 469-475. DOI: 10.15953/j.ctta.2024.266 |
| [2] | CAO Jiasheng, LI Baolei. Analysis of Accuracy Related Factors in Photon Counting X-ray CT Energy Imaging[J]. CT Theory and Applications, 2025, 34(2): 255-262. DOI: 10.15953/j.ctta.2024.254 |
| [3] | LIU Xiangcheng, HUANG Xiaoying, WEI Pengyue, WANG Pengchao, GUO Fangkai, BAO Yunfeng. Clinical Research Progress on Deep Learning for Metal Artifact Reduction in CT Images[J]. CT Theory and Applications. DOI: 10.15953/j.ctta.2025.222 |
| [4] | WEI Pengyue, HUANG Xiaoying, WU Tong, GUO Fangkai, GUAN Jing, BAO Yunfeng. Effect of denture materials on CT image artifacts: phantom experiment[J]. CT Theory and Applications. DOI: 10.15953/j.ctta.2024.339 |
| [5] | NING xianying, HU Liu, FAN Wenliang, YU Jianming, LEI Ziqiao. The Application Value of Monoenergetic Imaging on Dual-layer Spectral Detector Computed Tomography in Dacryocystography[J]. CT Theory and Applications, 2024, 33(6): 677-682. DOI: 10.15953/j.ctta.2024.144 |
| [6] | ZHANG Wenjun, HUANG Gang, DING Haining, XU Hongchun. Research Progress of Scattering Artifact Correction in Medical Cone-beam Computed Tomography Imaging Based on Deep Learning[J]. CT Theory and Applications, 2023, 32(2): 285-296. DOI: 10.15953/j.ctta.2022.131 |
| [7] | ZUO Shunji, FENG Peng, HUANG Pan, YAN Shenghao, HE Peng, WEI Biao. Metal Artifact Reduction Algorithm for CT Images of Rock and Mineral Samples Based on Dual-domain Adaptive Network[J]. CT Theory and Applications, 2022, 31(6): 783-792. DOI: 10.15953/j.ctta.2022.041 |
| [8] | DENG Xiaolin, XIE Hui, QU Yalin, WU Shaoquan, ZHOU Bangjian, YANG Zhengbin, FENG Lian, WANG Min. The Value of Optimal Monochromatic Spectral CT Imaging in Gastric Variceal Bleeding before Endoscopic Treatment[J]. CT Theory and Applications, 2021, 30(5): 603-609. DOI: 10.15953/j.1004-4140.2021.30.05.08 |
| [9] | ZHAO Qingqing, SUN Xiaoli, LI Xi, WANG Yanwen, LIU Weina, DUAN Yongli, WANG Rengui. Utility of Spectral CT Monochromatic Imaging with Metal Artifacts Reduction (MAR) for the Reduction of Metal Artifacts of Embolization Coil Implants[J]. CT Theory and Applications, 2019, 28(5): 529-539. DOI: 10.15953/j.1004-4140.2019.28.05.02 |
| [10] | XU Pin, CHEN Shi, YUAN Gang, ZHANG Yin, ZHENG Jian, XING Xiao-man, SUN Ming-shan. Study of Spectral CT Based on a Photon Counting Detector[J]. CT Theory and Applications, 2015, 24(6): 819-825. DOI: 10.15953/j.1004-4140.2015.24.06.07 |
| 1. |
孙宇飞，汤若薇，丁贺宇，徐宁，钟朝辉，杨正汉，王振常，赵鹏飞. 超高分辨率骨质CT与多层螺旋CT显示中耳关键传声结构的对比研究. 中国耳鼻咽喉头颈外科. 2025(04): 225-228+233 .
|
Supported by: Beijing Renhe Information Technology Co. Ltd 
DownLoad: