现代仪器与医疗

人工智能在肺动脉CT血管成像全流程中的研究进展

PDF下载

刘近妹 , 王芷玥 , 范亚明 ^*

现代仪器与医疗 | 综述 2026,32(2): 112-120

收起

现代仪器与医疗 |综述 2026 , 32 (2) : 112 -120

人工智能在肺动脉CT血管成像全流程中的研究进展

全屏

[Author(id=1320381157607325941, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, 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=1320381157699600631, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, authorId=1320381157607325941, language=EN, stringName=Jinmei Liu, firstName=Jinmei, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Medical Imaging Department, the Third People's Hospital of Bengbu, Bengbu 233000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320381157825429752, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, authorId=1320381157607325941, language=CN, stringName=刘近妹, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=蚌埠市第三人民医院医学影像科，蚌埠　233000, bio={"content":"

刘近妹，女，本科，技师，研究方向：影像技术

"}, bioImg=null, bioContent=

刘近妹，女，本科，技师，研究方向：影像技术

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320381156072210673, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, xref=null, ext=[AuthorCompanyExt(id=1320381156080599282, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, companyId=1320381156072210673, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Medical Imaging Department, the Third People's Hospital of Bengbu, Bengbu 233000, China), AuthorCompanyExt(id=1320381156088987891, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, companyId=1320381156072210673, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=蚌埠市第三人民医院医学影像科，蚌埠　233000)])]), Author(id=1320381157917704442, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, 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=0, authorType=1, ext={EN=AuthorExt(id=1320381158001590524, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, authorId=1320381157917704442, language=EN, stringName=Zhiyue Wang, firstName=Zhiyue, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Medical Imaging Department, the Third People's Hospital of Bengbu, Bengbu 233000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320381158098059517, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, authorId=1320381157917704442, language=CN, stringName=王芷玥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=蚌埠市第三人民医院医学影像科，蚌埠　233000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320381156072210673, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, xref=null, ext=[AuthorCompanyExt(id=1320381156080599282, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, companyId=1320381156072210673, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Medical Imaging Department, the Third People's Hospital of Bengbu, Bengbu 233000, China), AuthorCompanyExt(id=1320381156088987891, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, companyId=1320381156072210673, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=蚌埠市第三人民医院医学影像科，蚌埠　233000)])]), Author(id=1320381158169362687, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, orderNo=2, 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=1320381158249054465, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, authorId=1320381158169362687, language=EN, stringName=Yaming Fan, firstName=Yaming, middleName=null, lastName=Fan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=^*, address=Medical Imaging Department, the Third People's Hospital of Bengbu, Bengbu 233000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320381158341329154, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, authorId=1320381158169362687, language=CN, stringName=范亚明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=^*, address=蚌埠市第三人民医院医学影像科，蚌埠　233000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320381156072210673, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, xref=null, ext=[AuthorCompanyExt(id=1320381156080599282, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, companyId=1320381156072210673, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Medical Imaging Department, the Third People's Hospital of Bengbu, Bengbu 233000, China), AuthorCompanyExt(id=1320381156088987891, tenantId=1146029695717560320, journalId=1319373289681944729, articleId=1320381155417899246, companyId=1320381156072210673, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=蚌埠市第三人民医院医学影像科，蚌埠　233000)])])]

刘近妹, 王芷玥, 范亚明^*

作者信息

蚌埠市第三人民医院医学影像科，蚌埠　233000

通讯作者:

范亚明，男，硕士研究生，工程师，研究方向：医学物理与放射线设备

作者简介:

刘近妹，女，本科，技师，研究方向：影像技术

Research progress of artificial intelligence in the entire workflow of computed tomography pulmonary angiography

Jinmei Liu, Zhiyue Wang, Yaming Fan^*

Affiliations

Medical Imaging Department, the Third People's Hospital of Bengbu, Bengbu 233000, China

出版时间: 2026-04-10 doi: 10.11876/mimt202602018

文章导航

摘要

收起

肺动脉栓塞（pulmonary embolism，PE）是一种发病率、病死率均较高的急性肺部疾病，早发现、早治疗至关重要。尽管肺动脉CT血管成像（computed tomography pulmonary angiography，CTPA）是诊断PE的“金标准”，具有快捷、无创、灵敏度高的优势，但在临床实践中仍面临图像质量不稳定、微小栓子漏诊、诊断流程烦琐及定量分析精度不足等挑战。本文深入探究人工智能（artificial intelligence，AI）在CTPA全流程应用中的临床价值，系统综述了AI在扫描前优化、图像处理、肺动脉树自动分割、肺栓塞智能检测与定量分析及预后风险评估等方面的最新研究进展，探讨了AI在CTPA临床应用中面临的难点与挑战，并展望了其多模态、智能化、便携化的发展方向，旨在为AI在CTPA诊断PE领域的应用研究和临床转化提供参考，助力CTPA的创新与医疗服务质量的提升。

关键词

人工智能 / 肺动脉CT血管成像 / 肺栓塞 / 图像处理

Abstract

收起

Pulmonary embolism (PE) is an acute cardiopulmonary disease characterized by high morbidity and mortality, making early detection and prompt treatment crucial. Although computed tomography pulmonary angiography (CTPA) serves as the “gold standard” for diagnosing PE due to its speed, non-invasiveness, and high sensitivity, it still presents several challenges in clinical practice. These include inconsistent image quality, the risk of missing small emboli, cumbersome diagnostic workflows, and insufficient precision in quantitative analysis. This article delves into the clinical value of artificial intelligence (AI) throughout the entire CTPA workflow. It systematically reviews research progress on AI applications, ranging from pre-scan optimization, image processing, automatic segmentation of pulmonary artery tree, to intelligent detection and quantitative analysis of pulmonary embolism, and prognosis risk assessment. It also discusses the current difficulties and challenges of implementing AI in clinical CTPA practice and explores future directions toward multimodal, intelligent, and portable solutions. This review aims to provide a reference for the research and clinical application of AI in the diagnosis of PE using CTPA, and to facilitate the innovation of CTPA and the improvement of medical service quality.

Key words

Artificial intelligence / Computed tomography pulmonary angiography / Pulmonary embolism / Image processing

引用本文

刘近妹, 王芷玥, 范亚明. 人工智能在肺动脉CT血管成像全流程中的研究进展. 现代仪器与医疗, 2026 , 32 (2) : 112 -120 . DOI: 10.11876/mimt202602018

Jinmei Liu, Zhiyue Wang, Yaming Fan. Research progress of artificial intelligence in the entire workflow of computed tomography pulmonary angiography[J]. Modern Instruments & Medical Treatment, 2026 , 32 (2) : 112 -120 . DOI: 10.11876/mimt202602018

基金

收起

蚌埠医科大学科技项目(2024byzd484)
蚌埠市科技创新指导类项目(2025ZD0004)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

中华医学会呼吸病学分会肺栓塞与肺血管病学组, 中国医师协会呼吸医师分会肺栓塞与肺血管病工作委员会, 全国肺栓塞与肺血管病防治协作组. 中国肺血栓栓塞症诊治、预防和管理指南(2025版)[J]. 中华医学杂志, 2025, 105(26): 2162-2194.

[2]

杨芙蓉, 谢万木. 《慢性血栓栓塞性肺动脉高压诊断与治疗指南(2024版)》解读[J]. 协和医学杂志, 2025, 16(3): 673-679.

[3]

Diaz-Lorenzo I, Alonso-Burgos A, Reyes A F, et al. Current role of CT pulmonary angiography in pulmonary embolism: a state-of-the-art review[J]. Journal of Imaging, 2024, 10(12): 323.

[4]

Kristiansen C H, Thomas O, Nyquist A B, et al. A randomised controlled trial comparing three clinical administration strategies in spectral detector CT pulmonary angiography with low contrast medium dose[J]. European Radiology, 2025, 35(8): 4649-4660.

[5]

Saeed S, Niehoff J H, Boriesosdick J, et al. Minimizing contrast media dose in CT pulmonary angiography with clinical photon counting using high pitch technique[J]. Acad Radiol, 2024, 31(2): 686-692.

[6]

范欣, 李琦, 张越, 等. 肺血栓栓塞症CTPA假阳性诊断常见原因分析及影像表现[J]. 放射学实践, 2024, 39(1): 70-76.

[7]

赵颖, 汪雁博, 谷新顺, 等. 肾阻力指数评估肺动脉高压患者CTPA检查后对比剂肾病发生风险的研究[J]. 中国循证心血管医学杂志, 2021, 13(9): 1082-1085, 1089.

[8]

Hafner D, Pasukonis J, Ba J, et al. Mastering diverse control tasks through world models[J]. Nature, 2025, 640: 647-653.

[9]

He X, Yang Y, Jiang X, et al. Unified medical image pretraining in language-guided common semantic space[EB/OL]. (2023-11-24) [2025-12-13]. https://arxiv.org/abs/2311.14851.

[10]

Cai G, Huang F, Gao Y, et al. Artificial intelligence-based models enabling accurate diagnosis of ovarian cancer using laboratory tests in China: a multicentre, retrospective cohort study[J]. Lancet Digit Health, 2024, 6: e176-e186.

[11]

Li J, Guan Z, Wang J, et al. Integrated image-based deep learning and language models for primary diabetes care[J]. Nature Medicine, 2024, 30: 2886-2896.

[12]

Qiu P, Wu C, Zhang X, et al. Towards building multilingual language model for medicine[J]. Nature Communications, 2024, 15: 8384.

[13]

Johri S, Jeong J, Tran B A, et al. An evaluation framework for clinical use of large language models in patient interaction tasks[J]. Nature Medicine, 2025, 31: 77-86.

[14]

于淼淼, 赵伟涛, 程广婷, 等. 小剂量团注测试技术与智能跟踪触发技术在肺动脉成像中的对比分析[J]. 医学影像学杂志, 2024, 34(10): 46-48, 52.

[15]

刘云福, 康天良, 张永县, 等. 两段式对比剂注射结合团注跟踪技术在肺动脉CTA检查中的应用研究[J]. CT理论与应用研究, 2023, 32(4): 531-538.

[16]

Klok F A, Barco S, Bertoletti L, et al. Optimal approach to performing and reporting computed tomography angiography for suspected acute pulmonary embolism: a clinical consensus statement of the ESC Working Group on Pulmonary Circulation & Right Ventricular Function, the Fleischner Society, the Association for Acute Cardiovascular Care (ACVC) and the European Association of Cardiovascular Imaging (EACVI) of the ESC, endorsed by European Respiratory Society (ERS), Asian Society of Thoracic Radiology (ASTR), European Society of Thoracic Imaging (ESTI), and Society of Thoracic Radiology (STR)[J]. Radiology, 2025, 315(3): e243833.

[17]

Ratnakanthan P J, Kavnoudias H, Paul E, et al. Weight-adjusted contrast administration in the computed tomography evaluation of pulmonary embolism[J]. J Med Imaging Radiat Sci, 2020, 51(3): 451-461.

[18]

Jamali L, Alikhani B, Getzin T, et al. Arterial attenuation in individualized computed tomography pulmonary angiography injection protocol adjusted based on the patient's body mass index[J]. Journal of Research in Medical Sciences, 2020, 25: 94.

[19]

Smith-Bindman R, Chu P W, Azman Firdaus H, et al. Projected lifetime cancer risks from current computed tomography imaging[J]. JAMA Intern Med, 2025, 185(6): 710-719.

[20]

Smith-Bindman R, Alber S A, Kwan M L, et al. Medical imaging and pediatric and adolescent hematologic cancer risk[J]. N Engl J Med, 2025, 393(13): 1269-1278.

[21]

Shen L, Lu J, Zhou C, et al. Deep learning reconstruction combined with contrast-enhancement boost in dual-low dose CT pulmonary angiography: a two-center prospective trial[J]. European Radiology, 2025, 35: 7225-7234.

[22]

张振明, 董险峰, 李立强, 等. 迭代算法不同管电压对肺栓塞患者肺动脉CT成像质量及辐射剂量的影响[J]. 中国医学装备, 2021, 18(6): 21-25.

[23]

曹建新, 朱卓, 张清, 等. 联合人工智能模型迭代重建和70kV超低管电压大幅度降低肺动脉CTA辐射剂量的研究[J]. 放射学实践, 2024, 39(10): 1361-1366.

[24]

Zhang Y, Wang L, Yuan D, et al. Clinical value of the 70-kVp ultra-low-dose CT pulmonary angiography with deep learning image reconstruction[J]. European Radiology, 2026, 36(1): 564-574.

[25]

Zhao Y X, Zuo Z W, Suo H N, et al. CT pulmonary angiography using automatic tube current modulation combination with different noise index with iterative reconstruction algorithm in different body mass index: image quality and radiation dose[J]. Acad Radiol, 2016, 23(12): 1513-1520.

[26]

刘晓彤, 王静, 许小毛, 等. 结合噪声指数的自动管电流调制技术联合全模型迭代重建算法在老年人低碘对比剂CT肺动脉血管成像中的应用[J]. 中华老年医学杂志, 2025, 44(5): 577-583.

[27]

Kirsch J, Brown R K, Henry T S, et al. ACR Appropriateness Criteria® acute chest pain-suspected pulmonary embolism[J]. Journal of the American College of Radiology, 2017, 14(5S): S2-S12.

[28]

陆金娟, 沈蕾蕾, 毕正宏, 等. 超低辐射剂量CT肺动脉成像联合深度学习重建算法诊断肺栓塞的可行性研究[J]. 中华放射学杂志, 2025, 59(8): 886-893.

[29]

邱慎满, 张贺, 刘忠啸, 等. 深度学习重建在改善双低肺动脉CTA图像质量、评估Qanadli栓塞指数中的应用价值[J]. 中华医学杂志, 2023, 103(19): 1477-1482.

[30]

樊雪林, 文昱齐, 乔志伟. 基于Transformer增强型U-net的CT图像稀疏重建与伪影抑制[J]. CT理论与应用研究, 2024, 33(1): 1-12.

[31]

Sun Q, Liu Z, Ding T, et al. Machine learning-based Objective evaluation model of CTPA image quality: a multicenter study[J]. Int J Gen Med, 2025, 18: 997-1005.

[32]

李曼, 蒋德攀, 王麦林, 等. 基于Res2Net注意力机制网络智能检测CT肺动脉成像急性肺动脉栓塞[J]. 中国医学影像学杂志, 2025, 33(4): 356-361, 369.

[33]

Chu Y, Luo G, Zhou L, et al. Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differences[J]. Nature Communications, 2025, 16: 2262.

[34]

Fan C J, Luan H, Qiao Y, et al. Detection and segmentation of pulmonary embolism in 3D CT pulmonary angiography using a threshold adjustment segmentation network[J]. Scientific Reports, 2025, 15: 7263.

[35]

Kahraman A T, Fröding T, Toumpanakis D, et al. Enhanced classification performance using deep learning based segmentation for pulmonary embolism detection in CT angiography[J]. Heliyon, 2024, 10(19): e38118.

[36]

Foley R W, Glenn-Cox S, Rossdale J, et al. Automated calculation of the right ventricle to left ventricle ratio on CT for the risk stratification of patients with acute pulmonary embolism[J]. Eur Radiol, 2021, 31(8): 6013-6020.

[37]

郭润财, 王蕾, 黄振国, 等. 基于从头训练模式深度学习卷积神经网络模型评估急性肺栓塞的价值[J]. 实用医学杂志, 2023, 39(22): 2979-2983.

[38]

Zhong Z, Zhang H, Fayad F H, et al. Pulmonary embolism mortality prediction using multimodal learning based on computed tomography angiography and clinical data[EB/OL]. (2024-06-03) [2025-12-13]. https://arxiv.org/abs/2406.01302.

[39]

Wang D, Chen R, Wang W, et al. Prediction of short-term adverse clinical outcomes of acute pulmonary embolism using conventional machine learning and deep learning based on CTPA images[J]. Journal of Thrombosis and Thrombolysis, 2025, 58(2): 331-339.

[40]

Li L, Peng M, Zou Y, et al. The promise and limitations of artificial intelligence in CTPA-based pulmonary embolism detection[J]. Frontiers in Medicine, 2025, 12: 1514931.

[41]

Cianflone F, Maris B, Bertolo R, et al. Development of artificial intelligence-based real-time automatic fusion of multiparametric magnetic resonance imaging and transrectal ultrasonography of the prostate[J]. Urology, 2025, 199: 27-34.

[42]

Hou J, Zhang R, Xie Y, et al. Multimodal deep learning for cancer prognosis prediction with clinical information prompts integration[J/OL]. NPJ Digit Med, 2025[2025-12-13]. https://www.nature.com/articles/s41746-025-02257-y.

[43]

Langius-Wiffen E, de Jong P A, Mohamed Hoesein F A, et al. Added value of an artificial intelligence algorithm in reducing the number of missed incidental acute pulmonary embolism in routine portal venous phase chest CT[J]. European Radiology, 2024, 34(1): 367-373.

[44]

Luciani D, Magrini A, Berzuini C, et al. Finding the needle by modeling the haystack: pulmonary embolism in an emergency patient with cardiorespiratory manifestations[J]. Expert Systems With Applications, 2022, 189: 116066.

[45]

邱景, 赵笑尘, 胡徐茜, 等. 大数据医疗时代的人工智能与患者个人隐私保护的技术方案研究[J]. 国外电子测量技术, 2025, 44(7): 294-300.

[46]

Dutta J, Puthal D. Advancing eHealth in Society 5.0: a fuzzy logic and blockchain-enhanced framework for integrating IoMT, Edge, and Cloud with AI[J]. IEEE Access, 2024, 12: 195710-195730.

2026年第32卷第2期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.11876/mimt202602018

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

蚌埠医科大学科技项目(2024byzd484)

蚌埠市科技创新指导类项目(2025ZD0004)

作者信息

蚌埠市第三人民医院医学影像科，蚌埠　233000

通讯作者:

范亚明，男，硕士研究生，工程师，研究方向：医学物理与放射线设备

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/xdyqyyl/CN/10.11876/mimt202602018

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