全模型迭代重建(Iterative Model Reconstruction,IMR)技术是最新一代的迭代重建算法,其理论上在降低噪声、提高图像质量效果方面较滤波反投影重建技术及高级混合迭代重建更有优势。应用IMR技术可在降低辐射剂量的条件下保证图像质量。...全模型迭代重建(Iterative Model Reconstruction,IMR)技术是最新一代的迭代重建算法,其理论上在降低噪声、提高图像质量效果方面较滤波反投影重建技术及高级混合迭代重建更有优势。应用IMR技术可在降低辐射剂量的条件下保证图像质量。本文就IMR技术在各系统CT检查中的临床应用进展进行综述,综述其在头颈部、心血管、胸腹部检查等方面的应用进展,并对IMR技术的未来发展方向做出了展望,以期为相关研究提供参考。展开更多
目的:观察不同级别全模型迭代重建(iterative model reconstruction,IMR)技术对脑部CT图像质量和噪声的影响,找到同等摄影条件下能够取得脑部扫描最佳图像质量的迭代重建级别。方法:回顾性分析2020年1—4月以头晕、头疼等症状到某院急...目的:观察不同级别全模型迭代重建(iterative model reconstruction,IMR)技术对脑部CT图像质量和噪声的影响,找到同等摄影条件下能够取得脑部扫描最佳图像质量的迭代重建级别。方法:回顾性分析2020年1—4月以头晕、头疼等症状到某院急诊就诊,且行头部CT平扫检查的36例患者的临床资料。对36例患者的脑部CT分别采用滤波反投影法(filtered back projection,FBP)、混合迭代重建(iDose4)及IMR-1(level 1)、IMR-2(level 2)和IMR-3(level 3)薄层重建。比较各重建图像脑灰、白质的CT值、噪声[标准差(SD值)]、信噪比(signal-to-noise ratio,SNR)和对比噪声比(contrast-to-noise radio,CNR),并分析图像质量主观评分的差异。数据采用IBM SPSS 21.0软件进行分析。结果:各重建图像CT值差异无统计学意义(F=1.01,P>0.05);SD值和IMR的3组不同级别的CNR值的差异均具有统计学意义(P<0.05),其中SD值依次为FBP>IMR-3>iDose4>IMR-2>IMR-1,CNR值依次为IMR-1>IMR-2>IMR-3;SNR值差异无统计学意义(F=0.99,P=0.42)。图像主观评分为IMR-1<iDode4<FBP<IMR-2<IMR-3,差异有统计学意义(F=289.68,P<0.01)。结论:IMR技术可显著减低脑组织的图像噪声,提高图像质量,以IMR-1效果最佳。展开更多
A GMM (Gaussian Mixture Model) based adaptive image restoration is proposed in this paper. The feature vectors of pixels are selected and extracted. Pixels are clustered into smooth,edge or detail texture region accor...A GMM (Gaussian Mixture Model) based adaptive image restoration is proposed in this paper. The feature vectors of pixels are selected and extracted. Pixels are clustered into smooth,edge or detail texture region according to variance-sum criteria function of the feature vectors. Then pa-rameters of GMM are calculated by using the statistical information of these feature vectors. GMM predicts the regularization parameter for each pixel adaptively. Hopfield Neural Network (Hopfield-NN) is used to optimize the objective function of image restoration,and network weight value matrix is updated by the output of GMM. Since GMM is used,the regularization parameters share properties of different kind of regions. In addition,the regularization parameters are different from pixel to pixel. GMM-based regularization method is consistent with human visual system,and it has strong gener-alization capability. Comparing with non-adaptive and some adaptive image restoration algorithms,experimental results show that the proposed algorithm obtains more preferable restored images.展开更多
文摘全模型迭代重建(Iterative Model Reconstruction,IMR)技术是最新一代的迭代重建算法,其理论上在降低噪声、提高图像质量效果方面较滤波反投影重建技术及高级混合迭代重建更有优势。应用IMR技术可在降低辐射剂量的条件下保证图像质量。本文就IMR技术在各系统CT检查中的临床应用进展进行综述,综述其在头颈部、心血管、胸腹部检查等方面的应用进展,并对IMR技术的未来发展方向做出了展望,以期为相关研究提供参考。
文摘A GMM (Gaussian Mixture Model) based adaptive image restoration is proposed in this paper. The feature vectors of pixels are selected and extracted. Pixels are clustered into smooth,edge or detail texture region according to variance-sum criteria function of the feature vectors. Then pa-rameters of GMM are calculated by using the statistical information of these feature vectors. GMM predicts the regularization parameter for each pixel adaptively. Hopfield Neural Network (Hopfield-NN) is used to optimize the objective function of image restoration,and network weight value matrix is updated by the output of GMM. Since GMM is used,the regularization parameters share properties of different kind of regions. In addition,the regularization parameters are different from pixel to pixel. GMM-based regularization method is consistent with human visual system,and it has strong gener-alization capability. Comparing with non-adaptive and some adaptive image restoration algorithms,experimental results show that the proposed algorithm obtains more preferable restored images.
