金属遮挡条件下光子层析快速重构方法研究

doi:10.3969/j.issn.1007-5461.2022.04.010

量子电子学报 ›› 2022, Vol. 39 ›› Issue (4): 558-565.doi: 10.3969/j.issn.1007-5461.2022.04.010

金属遮挡条件下光子层析快速重构方法研究

杨一杉1, 梁华为1, 姚瑶2, 陈帅3∗

( 1 中国科学院合肥物质科学研究院智能机械研究所, 安徽合肥230031; 2 中北大学仪器与电子学院, 山西太原030000; 3 中国科学院合肥物质科学研究院核能安全技术研究所, 安徽合肥230031 )

收稿日期:2021-01-07 修回日期:2021-03-29 出版日期:2022-07-28 发布日期:2022-07-28
通讯作者: E-mail: shuai.chen@inest.cas.cn E-mail:E-mail: shuai.chen@inest.cas.cn
作者简介:杨一杉( 1992 - ), 安徽蚌埠人, 博士生, 主要从事人工智能方面的研究。E-mail: rossyoung@163.com
基金资助:
Supported by Strategic Priority Research Program of Chinese Academy of Sciences (中国科学院战略性先导科技专项资助项目, XDA14020503)

Fast reconstruction method of photon tomography under metal shielding condition

YANG Yishan1, LIANG Huawei1, YAO Yao2, CHEN Shuai3∗

( 1 Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei 230031, China; 2 School of Instrument and Electronics, North University of China, Taiyuan 030000, China; 3 Institute of Nuclear Energy Safety Technology, HFIPS, Chinese Academy of Sciences, Hefei 230031, China )

Received:2021-01-07 Revised:2021-03-29 Published:2022-07-28 Online:2022-07-28

摘要/Abstract

摘要： 传统的光子层析方法难以适用于含有大量重金属遮挡物的对象中。本研究拟从光子层析的视觉特征出发, 通过针对层析投影开展基于无监督学习的像素预测, 构建了基于金属遮挡物周边信息的编码器, 以生成受遮挡区域结构。同时, 在生成对抗网络架构的基础上, 将编码器作为生成网络, 并构建判别器用于编码器的训练。研究表明, 基于像素预测的重构方法能够实现金属结构覆盖区域内光子层析信息的再合成, 并且合成结果能够准确反映真实的物体的内部细节。这表明基于像素预测的重构方法能够有效降低物体内金属结构对层析结果的影响。

关键词: 图像处理, 快速重构方法, 像素预测, 无监督学习

Abstract: The traditional photon tomography method cannot be suitable for the objects containing heavy metal shielding. So in this study, based on the visual characteristics of photon tomography, pixel prediction based on unsupervised learning is carried out for the tomographic projection, and an encoder based on the surrounding information of metal shielding is constructed to generate the structure of the sheilded area. At the same time, on the basis of the generative adversarial network (GAN), the encoder is used as the generative network, and the discriminator is built for the training of the encoder. The results show that the reconstruction method based on pixel prediction can reconstruct the photonic tomography information in the area covered by heavy metal shielding, and the reconstruction results can accurately reflect the internal details of real objects, which indicates that the reconstruction method based on pixel prediction can effectively reduce the influence of metal structure in the object on the tomography results.

Key words: image processing, fast reconstruction method, pixel prediction, unsupervised learning

中图分类号:

TP391.41

杨一杉, 梁华为, 姚瑶, 陈帅∗. 金属遮挡条件下光子层析快速重构方法研究[J]. 量子电子学报, 2022, 39(4): 558-565.

YANG Yishan, LIANG Huawei, YAO Yao, CHEN Shuai∗. Fast reconstruction method of photon tomography under metal shielding condition[J]. Chinese Journal of Quantum Electronics, 2022, 39(4): 558-565.

参考文献

[1]Sun F, Markoetter H, Manke I, et al.Complementary X-ray and neutron radiography study of the initial lithiation process in lithium-ion batteries containing silicon electrodes[J].Applied Surface Science, 2017, 399(31):359-366
[2]Pohlmann C, Herbrig K, Gondek L, et al.In operando visualization of hydride-graphite composites during cyclic hydrogenation by high-resolution neutron imaging[J].Journal of Power Sources, 2015, 277(1):360-369
[3]Schrapp M J, Goldammer M, Schulz M, et al.Data fusion in neutron and X-ray computed tomography[J].Journal of Applied Physics, 2014, 116(16):055302-1302
[4]杨富强, 张定华, 黄魁东, 等.投影采样策略对重建质量影响综述[J].软件学报, 2018, 029(007):2133-2151
[5] Ter Pogossian, Michel, M.Image Reconstruction from Projections, The Fundamentals of Computerized Tomography by G. T. Herman[J].Medical Physics, 1982, 9(3):446-448
[6] Baek J, Pelc N J .Local and global 3D noise power spectrum in cone-beam CT system with FDK reconstruction[J].Medical Physics, 2011, 38(4):22-31
[7]Zeng R, Gavrielides M A, Petrick N, et al.Estimating local noise power spectrum from a few FBP-reconstructed CT scans[J].Medical Physics, 2016, 43(1):568-582
[8]Brown J M C, Garbe U, Pelliccia D.Statistical image reconstruction for high-throughput thermal Neutron Computed Tomography[J].Nuclear instruments and methods in physics research, 2019, 942(21):162396-162396
[9] J.A. Fessler. Statistical image reconstruction methods for transmission tomography [M] Handb Medical Imaging, 2000.
[10]高阔.35kV及以下电力设备的可视化检测技术应用研究[D].华北电力大学(保定), 2014
[11] 卢孝强, 孙怡.基于乘性正则化的有限角度CT重建算法[J].光学学报, 2010, 30(5):1285-1290
[12]Bappy D M, Jeon I.Modified simultaneous iterative reconstruction technique for fast,high-quality CT reconstruction[J].IET Image Processing, 2017, 11(9):701-708
[13] 班晓征.面向稀疏采样的图像重建算法研究[D].江南大学，2019.
[14]Krizhevsky A, Sutskever I, Hinton G E.Imagenet classification with deep convolutional neural networks[J].Advances in neural information processing systems, 2012, 25(2):84-90
[15][15] Kalendralis P , Traverso A , Shi Z.Multicenter CT phantoms public dataset for radiomics reproducibility tests[J].Medical Physics, 2019, 46(3):1512-1518

金属遮挡条件下光子层析快速重构方法研究

Fast reconstruction method of photon tomography under metal shielding condition

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	於康杰, 方波, 李剑敏, 王震, 蔡晋辉, 邬佳璐, 何正龙 . 太赫兹成像三维块匹配自适应Canny边缘检测算法[J]. 量子电子学报, 2023, 40(4): 458-468.
[2]	葛宏义 , 王飞 , 蒋玉英 , 李丽 , 张元 , 贾柯柯 , . 基于宽度学习的太赫兹光谱图像小麦霉变识别研究[J]. 量子电子学报, 2023, 40(3): 360-368.
[3]	杜天宇, 高昆∗ , 吴朝. 光栅相衬 CT 中吸收信号环形伪影的去除方法[J]. 量子电子学报, 2023, 40(1): 40-47.
[4]	陈建明, , 曾祥津, , 钟丽云, , 邸江磊, ∗ , 秦玉文, ∗. 基于深度学习的图像配准方法研究进展综述[J]. 量子电子学报, 2022, 39(6): 899-926.
[5]	吴琼, 马雷∗. 一种基于 LoG 算子的量子图像边缘检测算法[J]. 量子电子学报, 2022, 39(5): 720-727.
[6]	张杨∗, 程正东, 朱斌. 基于改进 Faster R-CNN 的无人机小目标检测算法[J]. 量子电子学报, 2022, 39(3): 354-363.
[7]	毛仁祥, 常建华, 张树益李红旭, 张露瑶. 基于3D-MobileNetv2 的多目标实时跟踪框架[J]. 量子电子学报, 2022, 39(3): 364-372.
[8]	臧一鸣, 朱尚超, 魏战红∗, 刘志飞, 林小竹, 孙文韬. 一种量子图像伪彩色编码方法[J]. 量子电子学报, 2022, 39(3): 343-353.
[9]	洪富祥, 陈冲, 丘仲锋∗. 一种基于机器视觉的无人机同心圆靶精准降落方法[J]. 量子电子学报, 2021, 38(3): 307-315.
[10]	陈儒, 杨义勤, 秦凡凯, 孟昭晖, 苗昕扬, 赵昆, 詹洪磊∗. 样本内部缺陷的太赫兹光谱成像与算法优化[J]. 量子电子学报, 2021, 38(3): 265-271.
[11]	王昱皓, 唐泽恬, 钟岷哲, 王阳, 曾瑞敏, 朱登玮, 杨晨. 基于相位相关和纹理分类的SIFT 图像拼接算法[J]. 量子电子学报, 2020, 37(6): 650-658.
[12]	王振武, 高隽, 范之国, 王昕, 张强. 利用正交偏振信息的透玻透膜成像方法[J]. 量子电子学报, 2019, 36(6): 691-698.
[13]	汪炜怡, 徐青山, 杨明翰. 基于光学灰度图像辨识的系统故障诊断方法[J]. 量子电子学报, 2019, 36(6): 699-704.
[14]	张健，胡明勇，吕敏，赵础矗，曹明坡. 基于CCD图像处理的双波长激光聚焦点定位方法[J]. 量子电子学报, 2019, 36(3): 317-323.
[15]	郭海儒1，许权1*，杜娅颖1. 基于像素颜色置乱的彩色量子图像加密方法[J]. 量子电子学报, 2019, 36(1): 1-5.