| 崔津津,刘贯中,胡兴和,韩邵军,孙红,王新江,姚洪祥.深度学习重建算法改善颅脑低剂量CT图像质量的可行性研究[J].中华放射医学与防护杂志,2023,43(9):736-740 |
| 深度学习重建算法改善颅脑低剂量CT图像质量的可行性研究 |
| Feasibility study on deep learning image reconstruction algorithm to improve the quality of low-dose CT images of the brain |
| 投稿时间：2023-06-02 |
| DOI：10.3760/cma.j.cn112271-20230602-00174 |
| 中文关键词: 深度学习重建算法 迭代重建 低辐射剂量 图像质量 腔隙性梗死灶 |
| 英文关键词:Deep learning image reconstruction Adaptive statistical iterative reconstruction-V Low radiation dose Image quality Lacunar infarction |
| 基金项目:国家自然科学基金面上项目（82172018）；军队保健专项课题（21BJZ21）；科技创新2030（2022ZD0211600） |
|
| 摘要点击次数: 799 |
| 全文下载次数: 243 |
| 中文摘要: |
| 目的 探讨深度学习重建算法（DLIR）较自适应统计迭代重建（ASIR-V）算法在改善颅脑低剂量CT图像质量方面的效果。方法 回顾性纳入2021年11月至2022年8月在解放军总医院第二医学中心接受颅脑CT检查的患者，对所有患者的低剂量CT采用4种不同算法重建：获得30%强度ASIR-V（ASIR-V-30%）图像、低强度DLIR（DLIR-L）图像、中等强度DLIR（DLIR-M）图像和高强度DLIR（DLIR-H）图像。在4组图像的表浅白质、表浅灰质、深部白质和深部灰质内选取感兴趣区并测量其CT值，计算信噪比（SNR）和对比噪声比（CNR）。由3名神经影像医师按照Likert 5分量表对图像质量进行主观评分。对4组图像的客观、主观评分进行分析，若总体存在差异，则进行组内两两比较。结果 共纳入109例患者，男104例、女5例，年龄65~110岁，平均（89.16±9.53）岁。颅脑CT低剂量扫描的辐射剂量为（0.93±0.01）mSv，显著低于常规扫描（2.92±0.01）mSv（t=56.15，P < 0.05）。颅脑低剂量CT的4组图像的SNR深部灰质、SNR深部白质、SNR表浅灰质、SNR表浅白质、CNR深部灰白质、CNR表浅灰白质客观图像质量分析差异具有统计学意义（F=98.23、72.95、68.43、58.24、241.13、289.91，P < 0.05），其中DLIR-H图像在深部灰质、深部白质、表浅灰质、表浅白质中噪声最低，与其他图像组间差异有统计学意义（t=167.43、275.46、182.32、361.54，P < 0.05）。DLIR-H图像质量主观评分优于ASIR-V-30%、DLIR-L、DLIR-M，且差异具有统计学意义（t=7.25、8.32、9.63，P < 0.05）。结论 与ASIR-V相比，DLIR算法能够有效降低颅脑低剂量CT的图像噪声和伪影，并提高SNR和CNR，其中DLIR-H图像质量最佳。 |
| 英文摘要: |
| Objective To explore the effectiveness of deep learning image reconstruction (DLIR) algorithm compared to adaptive statistical iterative reconstruction (ASIR-V) algorithm in improving the quality of low-dose brain CT images.Methods Retrospective inclusion of patients who underwent brain CT examination in the People's Liberation Army General Hospital from November 2021 to August 2022. Four different algorithms were used to reconstruct low-dose CT scans of all patients to obtain 30% intensity ASIR-V (ASIR-V-30%) images, low intensity DLIR (DLIR-L) images, medium intensity DLIR (DLIR-M) images, and high intensity DLIR (DLIR-H) images. The regions of interest were selected from four sets of images, including superficial white matter, superficial gray matter, deep white matter, and deep gray matter, and their CT values and standard deviations were measured for calculating signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR).Subjective evaluation of image quality was conducted by three neuroimaging physicians based on the Likert 5-component scale. The objective and subjective scores of the 4 groups of images were analyzed using ANOVA or Kruskal Wallis. If there are overall differences, pairwise comparisons were conducted within the group.Results A total of 109 patients were enrolled, including 104 males and 5 females, aged 65-110 years (89.16 ±9.53) years. The radiation exposure of brain CT low-dose scanning was (0.93 ±0.01)mSv, significantly lower than that of conventional scanning (2.92 ±0.01) mSv (t=56.15, P < 0.05). The differences in objective image quality analysis of ASIR-V-30%, DLIR-L, DLIR-M, and DLIR-H images of low-dose CT in SNRdeep gray matter, SNR deep white matter, SNR superficial gray matter, SNR superficial white matter, CNR deep gray white matter, and CNRsuperficial gray white matter were statistically significant(F=98.23, 72.95, 68.43, 58.24, 241.13, 289.91, P < 0.05). Among them, DLIR-H images had the lowest noise in deep gray matter, deep white matter, superficial gray matter, and superficial white matter, and had statistically significant differences compared to other image groups (t=167.43, 275.46, 182.32, 361.54, P < 0.05). The subjective score of DLIR-H image quality was superior to ASIR-V-30%, DLIR-L, and DLIR-M, with the statistically significant difference (t=7.25, 8.32, 9.63, P < 0.05).Conclusions Compared with ASIR-V, DLIR algorithm can effectively reduce image noise and artifacts in low-dose brain CT, and improve SNR and CNR. The subjective and objective image quality evaluation of DLIR-H is the best. |
| HTML 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|