Radiation dose reduction with dictionary learning based processing for head CT

Radiation dose reduction with dictionary learning based processing for head CT
复制标题

通过基于字典学习的头部 CT 处理减少辐射剂量

DOI:
10.1007/s13246-014-0276-7
复制
发表时间:
2014-06
影响因子:
--
通讯作者:
Coatrieux Jean-Louis
Coatrieux Jean-Louis
中科院分区:
医学4区
文献类型:
--
作者:
Chen Yang;Shi Luyao;Yang Jiang;Hu Yining;Luo Limin;Yin Xindao;Coatrieux Jean-Louis

文献摘要

参考文献

被引文献

相似文献

在 CT 扫描中,扫描产生的电离辐射引起了患者和医生的广泛关注。这项工作旨在通过使用基于快速词典学习 (DL) 的后处理来改善低剂量扫描的头部 CT 图像。低剂量 CT (LDCT) 和标准剂量 CT (SDCT) 非增强头部图像均在头部检查中通过多探测器排西门子 Somatom Sensation 16 CT 扫描仪获取。一百名患者参与了实验。两组 LDCT 图像是在 SDCT 中以 50% (LDCT50​​%) 和 25% (LDCT25%) 管电流设置获取的。为了进行定量评估,根据 GM、WM 和 CSF 组织的亨斯菲尔德单位 (HU) 测量值计算信噪比 (SNR) 和对比度噪声比 (CNR)。还进行了盲法定性分析来评估处理后的 LDCT 数据集。两个 LDCT 组的剂量减少了 50% 和 75%(LDCT50​​%,1.15±0.1mSv;LDCT25%,0.58±0.1mSv;SDCT,2.32±0.1mSv;P<0.001)。在处理后的所有 GM、WM 和 CSF 组织的 LDCT 图像中观察到 SNR 较原始 LDCT 图像显着增加。 DL 处理的 LDCT 图像中注意到显着的 GM-WM CNR 增强。在处理后的 LDCT50​​% 和 LDCT25% 图像中甚至可以实现比参考 SDCT 图像更高的 SNR 和 CNR。盲法定性审查验证了所提出的方法带来的感知改进。与原始LDCT图像相比,DL处理在头部CT中的应用与图像质量的显着改善相关。
In CT, ionizing radiation exposure from the scan has attracted much concern from patients and doctors. This work is aimed at improving head CT images from low-dose scans by using a fast Dictionary learning (DL) based post-processing. Both Low-dose CT(LDCT) and Standard-dose CT(SDCT) nonenhanced head images were acquired in head examination from a multi-detector row Siemens Somatom Sensation 16 CT scanner. One hundred patients were involved in the experiments. Two groups of LDCT images were acquired with 50 % (LDCT50 %) and 25 % (LDCT25 %) tube current setting in SDCT. To give quantitative evaluation, Signal to noise ratio(SNR) and Contrast to noise ratio (CNR) were computed from the Hounsfield unit (HU) measurements of GM, WM and CSF tissues. A blinded qualitative analysis was also performed to assess the processed LDCT datasets. Fifty and seventy five percent dose reductions are obtained for the two LDCT groups (LDCT50 %, 1.15 ± 0.1 mSv; LDCT25 %, 0.58 ± 0.1 mSv; SDCT, 2.32 ± 0.1 mSv;P< 0.001). Significant SNR increase over the original LDCT images is observed in the processed LDCT images for all the GM, WM and CSF tissues. Significant GM–WM CNR enhancement is noted in the DL processed LDCT images. Higher SNR and CNR than the reference SDCT images can even be achieved in the processed LDCT50 % and LDCT25 % images. Blinded qualitative review validates the perceptual improvements brought by the proposed approach. Compared to the original LDCT images, the application of DL processing in head CT is associated with a significant improvement of image quality.
DOI: 10.1137/070697653
发表时间: 2008-01-01
影响因子: 1.6
作者:
Mairal, Julien;Sapiro, Guillermo;Elad, Michael
通讯作者: Elad, Michael
泊松图像去模糊的字典学习方法
DOI: 10.1109/tmi.2013.2255883
发表时间: 2013-07-01
影响因子: 10.6
作者:
Ma, Liyan;Moisan, Lionel;Zeng, Tieyong
通讯作者: Zeng, Tieyong
使用伪影抑制大规模非局部方法进行胸部低剂量 CT 图像处理
DOI: 10.1088/0031-9155/57/9/2667
发表时间: 2012-05-07
影响因子: 3.5
作者:
Chen, Yang;Yang, Zhou;Toumoulin, Christine
通讯作者: Toumoulin, Christine
DOI: 10.3174/ajnr.a2749
发表时间: 2012-02-01
影响因子: 3.5
作者:
Korn, A.;Fenchel, M.;Brodoefel, H.
通讯作者: Brodoefel, H.
使用基于快速字典学习的处理来改善腹部肿瘤低剂量 CT 图像
DOI: 10.1088/0031-9155/58/16/5803
发表时间: 2013-08-21
影响因子: 3.5
作者:
Chen, Yang;Yin, Xindao;Toumoulin, Christine
通讯作者: Toumoulin, Christine