现代仪器与医疗

探讨深度学习重建算法联合低剂量对比剂在腹部增强CT扫描中应用的可行性研究

PDF下载

刘硕 ¹ , 史灵雪 ²^,^*

现代仪器与医疗 | 临床研究 2025,31(2): 61-65

收起

现代仪器与医疗 |临床研究 2025 , 31 (2) : 61 -65

探讨深度学习重建算法联合低剂量对比剂在腹部增强CT扫描中应用的可行性研究

全屏

[Author(id=1320388925953262108, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1320388926028759582, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, authorId=1320388925953262108, language=EN, stringName=Shuo Liu, firstName=Shuo, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=¹, address=^1.Department of Radiology, Xiongan Xuanwu Hospital, Xiong'an New Area, 070001 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320388926095868447, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, authorId=1320388925953262108, language=CN, stringName=刘硕, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=¹, address=^1.河北省雄安宣武医院放射科，雄安新区　070001, bio={"content":"

刘硕，男，硕士研究生，主治医师，研究方向：腹部影像诊断

"}, bioImg=null, bioContent=

刘硕，男，硕士研究生，主治医师，研究方向：腹部影像诊断

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320388925772907029, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, xref=1., ext=[AuthorCompanyExt(id=1320388925793878550, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, companyId=1320388925772907029, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^1.Department of Radiology, Xiongan Xuanwu Hospital, Xiong'an New Area, 070001 China), AuthorCompanyExt(id=1320388925798072855, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, companyId=1320388925772907029, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^1.河北省雄安宣武医院放射科，雄安新区　070001)])]), Author(id=1320388926162977313, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1320388926221697571, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, authorId=1320388926162977313, language=EN, stringName=Lingxue Shi, firstName=Lingxue, middleName=null, lastName=Shi, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=²^,^*, address=^2.Department of Radiology, Jilin Provincial People' Hospital, Changchun 130027, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320388926293000740, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, authorId=1320388926162977313, language=CN, stringName=史灵雪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=²^,^*, address=^2.吉林省人民医院放射线科，长春　130021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320388925865181720, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, xref=2., ext=[AuthorCompanyExt(id=1320388925873570329, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, companyId=1320388925865181720, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^2.Department of Radiology, Jilin Provincial People' Hospital, Changchun 130027, China), AuthorCompanyExt(id=1320388925881958938, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320388925085041170, companyId=1320388925865181720, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=^2.吉林省人民医院放射线科，长春　130021)])])]

刘硕¹, 史灵雪²^,^*

作者信息

^1.河北省雄安宣武医院放射科，雄安新区　070001

^2.吉林省人民医院放射线科，长春　130021

通讯作者:

史灵雪，女，硕士研究生，主治医师，研究方向：腹部影像诊断

作者简介:

刘硕，男，硕士研究生，主治医师，研究方向：腹部影像诊断

To investigate the feasibility of DLIR algorithm combined with low-dose contrast agent in abdominal enhanced CT scan

Shuo Liu¹, Lingxue Shi²^,^*

Affiliations

^1.Department of Radiology, Xiongan Xuanwu Hospital, Xiong'an New Area, 070001 China

^2.Department of Radiology, Jilin Provincial People' Hospital, Changchun 130027, China

出版时间: 2025-04-10 doi: 10.11876/mimt202502013

文章导航

摘要

收起

目的

探究深度学习重建（Deep Learning Image Reconstruction，DLIR）算法联合低剂量造影剂在腹部增强CT应用可行性。

方法

收集因病情需要行上腹部CT增强扫描检查的128例患者随机分成两组，每组64例，行能谱CT腹部增强检查，扫描参数一致。常规剂量组扫描采用1.5ml/kg比剂用量，多模型自适应统计迭代重建（Adaptive Statistical Iterative Reconstruction，ASIR）算法进行重建，ASIR迭代率选取60%。低剂量组扫描采用1.0ml/kg对比剂用量，并用不同水平DLIR算法进行重建分组，包括A组中强度深度学习图像重建（Deep Learning Image Reconstruction-Medium，DLIR-M）、B组高强度深度学习重建（Deep Learning Image Reconstruction-Medium，DLIR-H）。对比分析不同重建算法图像间的各项客观评价指标[噪声、对比度（Contrast to Noise Ratio，CNR）、信噪比（Signal to Noise Ratio，SNR）]和主观评价指标（噪声、整体图像质量）。

结果

客观评价，常规剂量组、低剂量A组、低剂量B组图像的噪声逐渐减低，各组两两比较差异均具有统计学意义（P<0.05）。常规剂量组、低剂量A组、低剂量B组图像的SNR肝脏、SNR胰腺、CNR肝脏、CNR胰腺逐渐升高，其中常规剂量组与低剂量A组间差异无统计学意义，其余各组间的差异具有统计学意义。主观评价上，常规剂量组、低剂量A组、低剂量B组的主观噪声和总体图像质量评分大多数情况下都超过4分，均能满足临床诊疗的需求。主观噪声评分逐渐升高，各组两两比较差异均具有统计学意义（P<0.05）。主观图像质量评分方面，低剂量B组评分高于低剂量A组、常规剂量组，差异具有统计学意义（P<0.05）。

结论

采用DLIR算法联合低剂量造影剂获得的影像图像质量要优于ASIR算法结合常规剂量造影剂，并能够满足日常诊断的需求，同时还能将所需造影剂量减少三分之一左右。

关键词

低对比剂用量 / 自适应统计迭代重建算法 / 深度学习重建算法 / 对比度 / 信噪比

Abstract

收起

Objective

To explore the feasibility of applying deep learning image reconstruction (DLIR) algorithm combined with low-dose contrast agent in abdominal enhanced CT Method 28 patients who needed upper abdominal enhanced CT scan due to their conditions were randomly divided into two groups, with 64 cases in each group. They underwent spectral CT abdominal enhanced examination with consistent scanning parameters. The conventional dose group was scanned with a contrast agent dosage of 1.5 ml/kg and reconstructed using the adaptive statistical iterative reconstruction (ASIR) algorithm, with an ASIR iteration rate of 60%. The low-dose group was scanned with a contrast agent dosage of 1.0 ml/kg and reconstructed using different levels of DLIR algorithms, including group A with medium-intensity deep learning image reconstruction (DLIR-M) and group B with high-intensity deep learning image reconstruction (DLIR-H).

Methods

evaluation indicators [noise, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR)] and subjective evaluation indicators (noise, overall image quality) were compared and analyzed among images reconstructed by different algorithms.

Results

In objective evaluation, the noise of images in the conventional dose group, low-dose group A, and low-dose group B gradually decreased, and the differences between each pair of groups were statistically significant (P<0.05). The SNR of liver, SNR of pancreas, CNR of liver, and CNR of pancreas in the conventional dose group, low-dose group A, and low-dose group B gradually increased. There was no statistically significant difference between the conventional dose group and low-dose group A, but the differences among the other groups were statistically significant. In subjective evaluation, the subjective noise and overall image quality scores of the conventional dose group, low-dose group A, and low-dose group B were mostly above 4 points, which could meet the clinical diagnosis and treatment needs. The subjective noise scores gradually increased, and the differences between each pair of groups were statistically significant (P<0.05). In terms of subjective image quality scores, the score of low-dose group B was higher than that of low-dose group A and the conventional dose group, and the difference was statistically significant (P<0.05).

Conclusion

The image quality obtained by using DLIR algorithm combined with low-dose contrast agent is superior to that of ASIR algorithm combined with conventional dose contrast agent, and it can meet the needs of daily diagnosis. At the same time, it can reduce the required contrast agent dosage by about one-third.

Key words

Low contrast agent dosage / Adaptive statistical iterative reconstruction algorithm / Deep learning reconstruction algorithm / Contrast to Noise Ratio / Signal to Noise Ratio

引用本文

刘硕, 史灵雪. 探讨深度学习重建算法联合低剂量对比剂在腹部增强CT扫描中应用的可行性研究. 现代仪器与医疗, 2025 , 31 (2) : 61 -65 . DOI: 10.11876/mimt202502013

Shuo Liu, Lingxue Shi. To investigate the feasibility of DLIR algorithm combined with low-dose contrast agent in abdominal enhanced CT scan[J]. Modern Instruments & Medical Treatment, 2025 , 31 (2) : 61 -65 . DOI: 10.11876/mimt202502013

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Koetzier LR, Mastrodicasa D, Szczykutowicz TP, et al. Deep learning image reconstruction for CT: Technical principles and clinical prospects[J]. Radiology, 2023, 306(3): 221257-221257.

[2]

朱永琪, 王振华, 陈大治, 等. 深度学习重建算法改善腹部门静脉期CT图像质量的应用价值[J]. 中国临床医学影像杂志, 2024, 35(7): 498-502.

[3]

吕培杰, 耿琪, 刘娜娜, 等. 基于深度学习的CT图像重建算法临床初步应用进展[J]. 中华放射学杂志, 2022, 56(11): 6.

[4]

付芮, 张成亮, 沈云, 等. 深度学习图像重建算法对图像质量的影响: 体模研究[J]. 放射学实践, 2023, 38(12): 1617-1622.

[5]

杨彦兵, 田艳鑫, 王泽润, 等. 深度学习重建算法联合”双低”技术在肺动脉CT血管造影中的可行性研究[J]. 临床放射学杂志, 2023, 42(3): 493-497.

[6]

Zhang D, MU C, Zhang X, et al. Image quality comparison of lower extremity CTA between CT routine reconstruction algorithms and deep learning reconstruction[J]. BMC Med Imaging, 2023, 23(1): 33.

[7]

刘建强, 刘晶哲, 綦维维. 100kV管电压联合全模型迭代重组算法在腹盆联合CT增强扫描成像中的价值[J]. 临床放射学杂志, 2022, 41(8): 1575-1580.

[8]

王旭, 刘义军, 赵莹, 等. 深度学习重建算法在不同剂量水平下对CT影像组学特征的影响: 体模研究[J]. 临床放射学杂志, 2023, 42(5): 863-867.

[9]

Yi Y, Zhao XM, Wu RZ, et al. Low dose and low contrast medium coronary CT angiography using dual-layer spectral detector CT[J]. Int Heart J, 2019, 60(3): 608-617.

[10]

Jiang B, Li N, Shi X, et al. Deep learning reconstruction shows better lung nodule detection for ultra-low-dose chest CT[J]. Radiology, 2022, 303(1): 202-212.

[11]

Kaga T, Noda Y, Fujimoto K, et al. Deep-learning-based image reconstruction in dynami ccontrast-enhanced abdominal CT: image quality and lesion detection among reconstr uction strength levels[J]. Clin Radiol, 2021, 76(9): 710, e15-710.e24.

[12]

张超, 董栋, 王铭君, 等. 深度学习图像重建算法在提高CCTA图像质量中的临床价值研究[J]. 临床放射学杂志, 2021, 40(6): 1126-1130.

[13]

Kim I, Kang H, Yoon HJ, et al. Deep learning-based image reconstruction for brain CT: Improved image quality compared with adaptive statistical iterative reconstructi on-Veo (ASIR-V)[J]. Neuroradiology, 2021, 63(6): 905-912.

[14]

Tatsugami F, Higaki T, Nakamura Y, et al. Deep learning-based image restoration algor ithm for coronary CT angiography[J]. Eur Radiol, 2019, 29(10): 5322-5329.

[15]

Zeng L, XuX, Zeng W, et al. Deep learning trained algorithm maintains the quality of half-dose contrast-enhanced liver computed tomography images: Comparison with hybr id iterative reconstruction: Study for the application of deep learning noise redu ction technology in low dose[J]. Eur J Radiol, 2021, 135(2): 109487.

[16]

Li LL, Wang H, Song J, et al. A feasibility study of realizing low-dose abdominal CT using deep learning image reconstruction algorithm[J]. J Xray Sci Technol, 2021, 29(2): 361-372.

[17]

Jensen CT, Liu X, Tamm EP, et al. Image quality assessment of abdominal ct by use of new deep learning image reconstruction: initial experience[J]. AJR, 2020, 215(1): 50-57.

2025年第31卷第2期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.11876/mimt202502013

首发时间：2026-10-23
出版时间：2025-04-10

补充材料

相关文章

文章信息

作者

出版历史

基金

作者信息

^1.河北省雄安宣武医院放射科，雄安新区　070001

^2.吉林省人民医院放射线科，长春　130021

通讯作者:

史灵雪，女，硕士研究生，主治医师，研究方向：腹部影像诊断

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/xdyqyyl/CN/10.11876/mimt202502013

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT