摘要
计算机断层成像(CT)技术凭借其无损检测、分辨率高和可视化等特点,在工业检测领域展现出显著应用价值。然而,在某些工业检测场景中,极端受限的扫描条件导致投影数据获取难度大,传统重建方法应用受限。为应对这一挑战,本研究提出一种适用于快速CT成像的正交双视角三维重建网络。提出的方法基于编解码架构,并使用二维卷积代替三维卷积,用特征通道维度推断CT体积的深度,提高模型的推理速度。同时引入梯度信息、梯度损失来增强网络对边缘的恢复能力。该方法在核桃和引信数据集上进行验证,实验结果表明,重建分辨率为128的体积仅需0.19 s,且重建图像的结构相似性高于0.98。该方法从双视角2D投影中推断出3D CT体积的有效能力,展现其在快速CT成像中的未来潜力。
Computed tomography(CT)technology has demonstrated significant application value in industrial inspection owing to its non-destructive testing capabilities,high resolution,and visualization features.However,in certain industrial inspection scenarios,extremely limited scanning conditions pose substantial challenges for projection data acquisition,restricting the application of traditional reconstruction methods.To address this challenge,this study proposes an orthogonal dual-view 3D reconstruction network tailored for rapid CT imaging.The proposed method employs an encoder–decoder architecture,utilizing 2D convolutions instead of 3D convolutions to infer the depth dimension of CT volumes through feature channels,thereby enhancing model inference speed.Additionally,gradient information and gradient loss are introduced to strengthen the edge recovery capability of the network.The method is validated on walnut and Fuze datasets.Experimental results showed that reconstructing a volume with a resolution of 128 required only 0.19 s,and the structural similarity of the reconstructed images was higher than 0.98.This approach demonstrates effective capability in inferring 3D CT volumes from dual-view 2D projections,revealing its future potential in rapid CT imaging.
作者
胡海
孙雪琴
李毅红
陈平
HU Hai;SUN Xueqin;LI Yihong;CHEN Ping(College of Information and Communication Engineering,North University of China,Taiyuan 030051,China;College of Mathematics,North University of China,Taiyuan 030051,China;The State Key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument,Taiyuan 030051,China)
出处
《CT理论与应用研究(中英文)》
2025年第4期525-533,共9页
Computerized Tomography Theory and Applications
基金
国家重点研发计划(半导体器件封装质量智能检测关键技术研究与应用示范(2023 YFE0205800))
国家自然科学基金(面向固体火箭发动机内结构剖面动态测试的双视角X射线快速CT成像(62471442))
国家自然科学基金(面向黄土质煤岩层孔裂隙结构动态表征的宽视场高分辨动态CT成像研究(U23 A20285))
山西省自然科学基金(基于双视角X射线CT成像的固体火箭发动机内结构剖面测试方法(202303021211149))
山西省重点研发计划复杂产品三维CT实时成像及缺陷智能识别(202302150401011)。
关键词
双视角投影
CT重建
编解码网络
梯度约束
dual-view projection
CT reconstruction
encoder-decoder network
gradient constraint
作者简介
第一作者:胡海,男,硕士研究生,主要从事基于深度学习的CT重建技术研究,E-mail:hh15955716594@163.com;通信作者:陈平,男,教授、博士生导师,主要从事图像处理与重建、光电检测、人工智能等方面的研究,E-mail:pc0912@163.com。
