ISSN 1004-4140
CN 11-3017/P
江宜桓, 雷子乔. 深度学习在上腹部CT能谱成像中的应用价值[J]. CT理论与应用研究(中英文), xxxx, x(x): 1-12. DOI: 10.15953/j.ctta.2024.157.
引用本文: 江宜桓, 雷子乔. 深度学习在上腹部CT能谱成像中的应用价值[J]. CT理论与应用研究(中英文), xxxx, x(x): 1-12. DOI: 10.15953/j.ctta.2024.157.
Jiang Y H, Lei Z Q. Application value of deep learning in spectral computed tomography of upper abdomen[J]. CT Theory and Applications, xxxx, x(x): 1-12. DOI: 10.15953/j.ctta.2024.157. (in Chinese).
Citation: Jiang Y H, Lei Z Q. Application value of deep learning in spectral computed tomography of upper abdomen[J]. CT Theory and Applications, xxxx, x(x): 1-12. DOI: 10.15953/j.ctta.2024.157. (in Chinese).

深度学习在上腹部CT能谱成像中的应用价值

Application value of deep learning in spectral computed tomography of upper abdomen

  • 摘要: 目的:比较基于深度学习图像重建算法(DLIR)、自适应统计迭代算法(ASIR-V)在上腹部能谱CT虚拟单能量成像(VIMs)的图像质量,探讨DLIR算法在CT能谱成像中的应用价值。方法:前瞻性收集33例上腹部CT能谱增强扫描的病例,分别使用ASIR-V和DLIR的方法重建动脉期、静脉期图像。其中ASIR-V采用50%的权重重建方式,DLIR采用DL-M、DL-H两种重建方式。提取三种不同重建算法下动脉期、静脉期虚拟单能量图像:40 keV、50 keV、60 keV、70 keV。由两位放射医师分别对动脉期12组和静脉期12组图像进行评分,采集各组图像数据,使用SPSS对评分结果与获得数据进行统计学处理。结果:动脉期12组图像,CT值、SD值、CNR和SNR差异均具有统计学意义(P<0.05)。静脉期12组图像,CT值、SD值、CNR和SNR差异均具有统计学意义(P<0.05)。其中,动脉期和静脉期,ASIR-V 40 keV组在肝脏、肾脏、脾脏、胰腺的SD值最高,SNR和CNR值最低,DL-H 70 keV组在肝脏、肾脏、脾脏、胰腺的SD值最低,SNR和CNR值最高。DL-H 60 keV组在肝脏、肾脏、脾脏、胰腺的主观评分最高。结论:与ASIR-V相比,DLIR上腹部CT能谱VIMs图像能够更有效的降低图像噪声、减少图像伪影,能够得到较好的图像质量;CT能谱成像低 keV VIMs图像,通过深度学习重建方法有效抑制噪声,能够较大幅度的提升图像质量;在选择的4个 keV VIMs中,通过高强度的深度学习重建方法重建得到的图像中,60 keV主观评分相较其他 keV VIMs更高。

     

    Abstract:
    Objective To compare the image quality of virtual monochromatic (VIM) imaging of upper abdominal computed tomography (CT) energy spectrum based on deep learning image reconstruction algorithm (DLIR) and adaptive statistical iterative algorithm (ASIR-V) and explore the application value of DLIR algorithm in CT energy spectrum imaging.
    Methods Thirty-three cases of upper abdominal CT spectral enhanced scans were prospectively collected. The arterial and venous phase images were reconstructed using ASIR-V and DLIR, respectively. ASIR-V uses the 50% weight reconstruction method, whereas DLIR uses the deep learning medium strength (DL-M) and high strength (DL-H) reconstruction methods. The virtual single energy images of arterial and venous phases were extracted using three different reconstruction algorithms: 40 keV, 50 keV, 60 keV and 70 keV. Two radiologists scored the images of 12 groups in arterial phase and 12 groups in venous phase, collecting the image data for each group. The statistical package for the social sciences (SPSS) was used to statistically process the obtained data and score the results.
    Results There were significant differences in CT value, standard deviation (SD), contrast-to-noise ratio (CNR), and signal-to-noise ratio (SNR) among the 12 groups of images in arterial phase (P < 0.05). and venous phase (P < 0.05). In the arterial and venous phases, the SD value of liver, kidney, spleen and pancreas in the ASIR-V 40 keV group was the highest, and the SNR and CNR values were the lowest. The SD value of liver, kidney, spleen and pancreas in the DL-H 70 keV group was the lowest, and the SNR and CNR values were the highest. The DL-H 60 keV group had the highest subjective scores for the liver, kidney, spleen and pancreas.
    Conclusion Compared with ASIR-V, DLIR upper abdominal CT spectral VIM images can more effectively reduce image noise, reduce image artifacts, and obtain better image quality. Low keV VIM CT spectral images were reconstructed using deep learning.

     

/

返回文章
返回