现代仪器与医疗

自动管电流调制技术联合深度学习重建算法应用于儿童头部CT图像质量及辐射剂量研究

PDF下载

陈锡建 ^1a^,^b , 孙艳 ^1a^,^b , 周杰 ² , 王海平 ^1a^,^b , 宁刚 ^1a^,^b^,^*

现代仪器与医疗 | CT关键技术专栏 2026,32(2): 7-14

收起

现代仪器与医疗 |CT关键技术专栏 2026 , 32 (2) : 7 -14

自动管电流调制技术联合深度学习重建算法应用于儿童头部CT图像质量及辐射剂量研究

全屏

陈锡建^1a^,^b, 孙艳^1a^,^b, 周杰², 王海平^1a^,^b, 宁刚^1a^,^b^,^*

作者信息

^1a.四川大学　华西第二医院放射科，成都　610041

^b.四川大学　出生缺陷与相关妇儿疾病教育部重点实验室，成都　610041

^2.东软医疗系统股份有限公司，大连　110167

通讯作者:

宁刚，男，硕士研究生，主任医师，研究方向：妇儿医学影像技术

作者简介:

陈锡建，男，本科，主管技师，研究方向：妇儿医学影像技术

Application of ATCM and deep learning reconstruction in pediatric head CT: a study on image quality and radiation dose

Xijian Chen^1a^,^b, Yan Sun^1a^,^b, Jie Zhou², Haiping Wang^1a^,^b, Gang Ning^1a^,^b^,^*

Affiliations

^1a.Department of Radiology, West China Second University Hospital, Sichuan University, Chengdu 610041, China

^b.Key Laboratory of Birth Defects and Related Gynecological and Pediatric Diseases, Ministry of Education, Sichuan University, Chengdu 610041, China

^2.Neusoft Medical Systems Co., Ltd., Dalian 110167, China

出版时间: 2026-04-10 doi: 10.11876/mimt202602002

文章导航

摘要

收起

目的

评估自动管电流调制（automatic tube current modulation，ATCM）技术联合深度学习重建算法ClearInfinity的低剂量方案在儿童头部CT平扫中的辐射剂量降低效果及其对图像质量的影响。

方法

回顾性分析行头部CT平扫检查的160例患儿影像数据，按扫描方案分为两组：A组（n=80）采用ATCM技术联合ClearInfinity算法重建的低剂量方案；B组（n=80）采用固定参数联合迭代重建的常规剂量方案。每组患儿按年龄分为4个亚组。采用容积CT剂量指数（volume CT dose index，CTDI_vol）、剂量长度乘积（dose-length product，DLP）、有效剂量（effective dose，ED）等指标对两组辐射暴露水平进行比较。图像质量评价包括客观和主观两个方面。客观评价在4个层面选取面积约为20 mm²的圆形感兴趣区，计算各区域的信噪比（signal-to-noise ratio，SNR）与对比噪声比（contrast-to-noise ratio，CNR）。主观评价由2位医师采用盲法对整体图像质量、解剖细节显示度、后颅窝伪影控制进行评分。统计分析使用SPSS 26.0软件完成，对辐射剂量和图像客观评价指标，采用双因素方差分析进行组间比较；对图像主观评价指标采用Mann-Whitney U检验评估差异，采用组内相关系数（intraclass correlation coefficient，ICC）分析一致性。

结果

两组基线资料比较差异无统计学意义（P>0.05）。CTDI_vol、DLP和ED等辐射剂量指标，不同区域的SNR、CNR等图像客观评价指标，均有显著性差异水平（P<0.05），A组的辐射剂量都显著低于B组。主观评价结果表明，A组的整体图像质量较B组有提升（P<0.001），后颅窝伪影有优化（P<0.001），且两名医师评价一致性优（ICC=0.891~0.923，P<0.001）。

结论

ATCM技术联合深度学习重建算法ClearInfinity可显著降低儿童头部CT辐射剂量。尽管客观评价提示高年龄段图像质量略有下降，但主观评价显示图像质量提升，整体实现了剂量与图像质量的协同优化，有望为儿童头部低剂量CT扫描提供新范式。

关键词

计算机断层扫描 / 儿童 / 深度学习重建算法 / 自动管电流调制 / 辐射剂量 / 图像质量 / 低剂量扫描

Abstract

收起

Objective

This study aimed to assess radiation dose reduction efficacy and image quality impact of automatic tube current modulation (ATCM) combined with deep-learning reconstruction algorithm “ClearInfinity” in low-dose pediatric non-contrast head CT scans.

Methods

This study retrospectively analyzed imaging data from 160 pediatric patients who underwent non-contrast head CT scans. The patients were divided into two groups according to the scanning protocol: group A (n=80) used the low-dose reconstruction protocol based on the ATCM technology combined with the ClearInfinity algorithm; Group B (n=80) adopted the conventional-dose reconstruction protocol using fixed parameters combined with iterative reconstruction. The patients were divided into four age groups, with 20 cases in each group. Radiation dose was evaluated using metrics such as volume CT dose index (CTDI_vol), dose-length product (DLP), and effective dose (ED) to compare the radiation exposure levels between the two groups. Image quality assessment included both objective and subjective evaluations. For the objective evaluation, regions of interest (ROIs) with an area of approximately 20 mm² were selected at four anatomical levels to calculate the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) for each region. Subjective evaluation was performed by two experienced physicians using a blinded method to rate the overall image quality, the degree of anatomical detail display, and the control of posterior cranial fossa artifacts.. Statistical analysis was conducted using SPSS software.

Results

The result shows that there was no statistically significant difference in the baseline data between the two groups. Radiation dose metrics, including CTDI_vol, DLP, and ED, as well as objective image evaluation indicators such as SNR and CNR in different regions, all showed statistically significant differences (P<0.05). The radiation doses in Group A were all significantly lower than those in Group B. The subjective evaluation results indicated that the overall image quality of group A was improved compared to group B (P<0.001), the posterior cranial fossa artifacts were optimized (P<0.001), and the consistency of the evaluations by the two physicians was excellent (ICC=0.891~0.923, P<0.001).

Conclusion

The ATCM technology combined with the ClearInfinity algorithm can significantly reduce the radiation dose of pediatric head CT scans. Although the objective evaluation indicates a slight decline in image quality for older age groups, the subjective evaluation shows an improvement in image quality, achieving a coordinated optimization of dose and image quality, and is expected to provide a new paradigm for low-dose CT scans of the pediatric head.

Key words

Computed tomography (CT) / Pediatric / Deep learning reconstruction algorithm / Automatic tube current modulation / Radiation dose / Image quality / Low-dose scanning

引用本文

陈锡建, 孙艳, 周杰, 王海平, 宁刚. 自动管电流调制技术联合深度学习重建算法应用于儿童头部CT图像质量及辐射剂量研究. 现代仪器与医疗, 2026 , 32 (2) : 7 -14 . DOI: 10.11876/mimt202602002

Xijian Chen, Yan Sun, Jie Zhou, Haiping Wang, Gang Ning. Application of ATCM and deep learning reconstruction in pediatric head CT: a study on image quality and radiation dose[J]. Modern Instruments & Medical Treatment, 2026 , 32 (2) : 7 -14 . DOI: 10.11876/mimt202602002

基金

收起

国家重点研发计划(2024YFC2419303)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Smith-Bindman R, Lipson J, Marcus R, et al. Radiation dose associated with common computed tomography examinations and the associated lifetime attributable risk of cancer[J]. Arch Intern Med, 2009, 169(22): 2078-2086.

[2]

Pearce M S, Salotti J A, Little M P, et al. Radiation exposure from CT scans in childhood and subsequent risk of leukaemia and brain tumours: a retrospective cohort study[J]. Lancet, 2012, 380(9840): 499-505.

[3]

Mathews J D, Forsythe A V, Brady Z, et al. Cancer risk in 680,000 people exposed to computed tomography scans in childhood or adolescence: data linkage study of 11 million Australians[J]. BMJ, 2013, 346: f2360.

[4]

International Commission on Radiological Protection. The 2007 recommendations of the International Commission on Radiological Protection. ICRP publication 103[J]. Ann ICRP, 2007, 37(2-4): 1-332.

[5]

Willemink M J, de Jong P A, Leiner T, et al. Iterative reconstruction techniques for computed tomography part 1: technical principles[J]. Eur Radiol, 2013, 23(6): 1623-1631.

[6]

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

[7]

Greffier J, Hamard A, Pereira F, et al. Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study[J]. Eur Radiol, 2020, 30(7): 3951-3959.

[8]

Yu L, Liu X, Leng S, et al. Radiation dose reduction in computed tomography: techniques and future perspective[J]. Imaging Med, 2009, 1(1): 65-84.

[9]

McCollough C H, Primak A N, Braun N, et al. Strategies for reducing radiation dose in CT[J]. Radiol Clin North Am, 2009, 47(1): 27-40.

[10]

Bostani M, McMillan K, Lu P, et al. Attenuation-based size metric for estimating organ dose to patients undergoing tube current modulated CT exams[J]. Medical Physics, 2015, 42(2): 958-968.

[11]

Hsieh J. Computed tomography: principles, design, artifacts, and recent advances[M]. 3rd ed. Bellingham: SPIE Press, 2015.

[12]

张见, 边传振, 张晓军. 基于头围的固定管电流在儿童头颅CT检查中的应用价值[J]. 实用放射学杂志, 2024, 40(1): 115-118.

[13]

Sun J, Du C, Zhang Q, et al. Relationship between organ dose and age in pediatric head CT examinations using Monte Carlo algorithm[C]//ECR 2026, March 4-8, 2026, Vienna.

[14]

Greffier J, Pereira F, Macri F, et al. CT dose reduction using automatic exposure control and iterative reconstruction: a chest paediatric phantoms study[J]. Physica Medica, 2016, 32(4): 582-589.

[15]

Higaki T, Nakamura Y, Zhou J, et al. Deep learning reconstruction at CT: phantom study of the image characteristics[J]. Acad Radiol, 2020, 27(1): 82-87.

[16]

Benz D C, Ersözlü S, Mojon F L A, et al. Radiation dose reduction with deep-learning image reconstruction for coronary computed tomography angiography[J]. Eur Radiol, 2022, 32: 2620-2628.

[17]

韩泽芳, 上官宏, 张雄, 等. 基于深度学习的低剂量CT成像算法研究进展[J]. CT理论与应用研究, 2022, 31(1): 117-134.

[18]

International Commission on Radiological Protection. Radiological protection in medicine. ICRP publication 105[J]. Ann ICRP, 2007, 37(6): 1-63.

2026年第32卷第2期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.11876/mimt202602002

首发时间：2026-10-23
出版时间：2026-04-10

补充材料

相关文章

文章信息

作者

出版历史

基金

国家重点研发计划(2024YFC2419303)

作者信息

^1a.四川大学　华西第二医院放射科，成都　610041

^b.四川大学　出生缺陷与相关妇儿疾病教育部重点实验室，成都　610041

^2.东软医疗系统股份有限公司，大连　110167

通讯作者:

宁刚，男，硕士研究生，主任医师，研究方向：妇儿医学影像技术

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/xdyqyyl/CN/10.11876/mimt202602002

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