人工智能在颈动脉斑块超声检查中的研究进展可视化分析

刘文丽; 张树华; 王艺桦; 刘洋; 张雪; 颜慧珊; 林泓钊; 殷彤; 李宁

doi:10.16766/j.cnki.issn.1674-4152.004457

人工智能在颈动脉斑块超声检查中的研究进展可视化分析

doi: 10.16766/j.cnki.issn.1674-4152.004457

华北理工大学附属医院超声科，河北唐山 063000

基金项目:

河北省2025年政府资助临床医学优秀人才培养项目 ZF2025282

详细信息

通讯作者:
李宁，E-mail：liningtsh@163.com

中图分类号: R445.1 R543.4
计量
- 文章访问数: 3
- HTML全文浏览量: 1
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2025-01-24

Visual analysis of research progress of artificial intelligence in carotid plaque ultrasound examination

Department of Ultrasound, North China University of Science and Technology Affiliated Hospital, Tangshan, Hebei 063000, China

摘要

摘要: 目的通过分析国内外人工智能在颈动脉斑块超声检查中的研究情况和进展，为人工智能应用于颈动脉斑块超声图像识别与分析的研究提供参考方向。方法检索中国知网(CNKI)、万方、Web of Science、PubMed和IEEE数据库建库至2024年12月人工智能在颈动脉斑块超声检查中的相关研究文献，利用CiteSpace进行可视化分析。结果经检索和筛选后，最终纳入14篇中文文献和88篇外文文献，国内外在人工智能应用于颈动脉斑块超声检查方面发表的文献数量较少，发文趋势均趋于平缓，相关研究作者和机构之间存在合作，但合作密切程度较低，出现频次较高的关键词有深度学习、机器学习、斑块分割、脑卒中、卷积神经网络、斑块特征等。结论国内外人工智能在颈动脉斑块超声检查中的研究热点主要集中在深度学习在识别超声图像中颈动脉斑块方面的应用、基于人工智能的斑块分割技术、人工智能分析颈动脉斑块超声特征与脑卒中和心血管疾病发生的关系等方面，计算机辅助诊断和分类算法将成为人工智能在颈动脉斑块超声检查中的研究趋势；同时，由于目前人工智能在颈动脉斑块超声检查中的研究较少，其在临床实践中的应用价值有待证实及提高，未来需要更多研究者投入到人工智能应用于颈动脉斑块超声检查研究中。
- 颈动脉斑块 /
- 人工智能 /
- 超声 /
- CiteSpace /
- 可视化分析
Abstract: Objective To provide a reference direction for the research on the application of artificial intelligence (AI) in the recognition and analysis of carotid plaque ultrasound images by analyzing the research status and progress of AI in carotid plaque ultrasound at home and abroad. Methods Using the China National Knowledge Infrastructure (CNKI), Wanfang Data, Web of Science, PubMed, and IEEE as databases, relevant research literatures on the application of AI in carotid plaque ultrasound from the establishment of the databases to December 2024 were retrieved as the research objects, and CiteSpace was used for visual analysis. Results After retrieval and screening, a total of 14 Chinese-language references and 88 foreign-language references were ultimately included. The number of literatures published at home and abroad on the application of AI in carotid plaque ultrasound is relatively small, and the publishing trends are both tending to be flat. There is cooperation among relevant researchers and institutions, but the degree of close cooperation is low. Keywords with high frequencies of occurrence include deep learning, machine learning, plaque segmentation, stroke, convolutional neural network, carotid plaque characterization, etc. Conclusion The research hotspots of AI in carotid plaque ultrasound at home and abroad mainly focus on the application of deep learning in identifying carotid plaques in ultrasound images, AI - based plaque segmentation technology, and the relationship between AI - analyzed ultrasound characteristics of carotid plaques and the occurrence of stroke and cardiovascular diseases. Computer-aided diagnosis and classification algorithms will become the research trend of AI in carotid plaque ultrasound. Meanwhile, due to the limited research on the application of AI in carotid plaque ultrasound examination at present, its application value in clinical practice remains to be verified and improved. In the future, more researchers are needed to engage in research on the application of AI in carotid plaque ultrasound examination.
- Carotid plaque /
- Artificial intelligence /
- Ultrasound /
- CiteSpace /
- Visual analysis
利益冲突 无

HTML全文

图 1 国内外相关文献年发文量情况

Figure 1. Annual publication volume of relevant domestic and international literature

下载: 全尺寸图片幻灯片

图 2 关键词时间线图谱

注：A为中文文献，B为外文文献。

Figure 2. Timeline map of keywords

下载: 全尺寸图片幻灯片

图 3 突现词图谱

注：A为中文文献，B为外文文献。

Figure 3. Burst keyword map

下载: 全尺寸图片幻灯片

表 1 外文文献发表国家的发文情况

Table 1. Publication volume by country of English-language literature

排序	国家	频数	中心性
1	美国	37	0.39
2	印度	31	0.12
3	意大利	29	0.40
4	加拿大	24	0.20
5	塞浦路斯	22	0.12
6	中国	21	0.03

下载: 导出CSV

表 2 中、外文文献高频关键词及其中心性

Table 2. High-frequency keywords and their centrality in Chinese and English literature

排序	中文文献			排序	外文文献
排序	关键词	中心性	频数	排序	关键词	中心性	频数
1	深度学习	1.16	8	1	deep learning	0.24	24
2	斑块分割	0.29	3	2	carotid artery	0.43	15
3	超声	0.53	3	3	machine learning	0.37	15
4	超声图像	0.06	2	4	carotid plaque	0.31	14
5	颈动脉	0.06	2	5	artificial intelligence	0.29	12
6	脑卒中	0.08	2	6	ultrasound image	0.11	11
7	人工智能	0.20	2	7	image segmentation	0.04	9
8	影像组学	0.22	2	8	convolutional neural network	0.17	9
9	图像处理	0.00	1	9	carotid ultrasound	0.12	8
10	预测模型	0.00	1	10	carotid plaque characterization	0.05	5
11	成分识别	0.00	1	11	cardiovascular disease	0.16	5
12	图像分类	0.00	1	12	plaque segmentation	0.24	4

下载: 导出CSV

参考文献(22)

[1]	张茜, 勉丽, 王霞. 多项超声技术联合探查颈动脉斑块预测缺血性脑卒中复发的价值[J]. 中华全科医学, 2024, 22(7): 1204-1208.
[2]	黄宇璐, 暨文超. 基于CiteSpace的我国住院医师规范化培训教学模式研究进展[J]. 中国继续医学教育, 2023, 15(15): 144-151. HUANG Y L, JI W C. Research Progress on Standardized Training Teaching Mode of Resident Doctors in China Based on CiteSpace[J]. China Continuing Medical Education, 2023, 15(15): 144-151.
[3]	张楚悦, 杨丽娜, 马良, 等. 近10年国内外情境模拟教学在住院医师规范化培训中的应用现状与前沿分析[J]. 中国毕业后医学教育, 2023, 7(8): 655-660, 664. ZHANG C Y, YANG L N, et al. Current situation and frontier trends of the scenario simulation teaching in standardized residency training in the past ten years at home and abroad[J]. Chinese Journal of Graduate Medical Education, 2023, 7(8): 655-660, 664.
[4]	赵琦瑶, 李皎月, 温雅璐, 等. 基于CiteSpace的中医药治疗糖尿病心肌病可视化分析[J]. 中华全科医学, 2023, 21(12): 2064-2067, 2155. ZHAO Q Y, LI J Y, et al. Visual analysis of traditional Chinese medicine in the treatment of diabetic cardiomyopathy based on CiteSpace[J]. Chinese Journal of General Practice, 2023, 21(12): 2064-2067, 2155.
[5]	林芝, 穆艳. 基于CiteSpace的疾病认知研究文献计量分析[J]. 医药前沿, 2024, 14(36): 24-29. LIN Z, MU Y. Bibliometric analysis of disease cognition research based on CiteSpace[J]. Journal of Frontiers of Medicine, 2024, 14(36): 24-29.
[6]	张浩, 常建东. 基于文献计量方法的人工智能在超声心动图中的应用进展研究[J]. 中国医疗设备, 2023, 38(1): 127-133. ZHANG H, CHANG J D. Research of the Application Progress of Artificial Intelligence in Echocardiography Based on Bibliometric Method[J]. China Medical Device, 2023, 38(1): 127-133.
[7]	郑禕婧, 谢雪, 熊晓贤, 等. 基于CiteSpace的甲状腺超声人工智能知识图谱可视化分析[J]. 临床超声医学杂志, 2024, 26(5): 375-382. ZHENG Y J, XIE X, et al. Knowledge atlas of artificial intelligence of thyroid ultrasound research: a CiteSpace visualization analysis[J]. Journal of Clinical Ultrasound in Medicine, 2024, 26(5): 375-382.
[8]	KONG Q, FAN C, ZHANG Y, et al. Rare disease publishing trends worldwide and in China: a CiteSpace-based bibliometric study[J]. Intractable Rare Dis Res, 2025, 14(1): 1-13. doi: 10.5582/irdr.2024.01059
[9]	李云飞, 李淑婷, 张帅, 等. 深度学习在肿瘤影像分类中的研究进展[J]. 中华肿瘤防治杂志, 2024, 31(12): 719-724. LI Y F, LI S T, et al. Research progress of deep learning in tumor images classification[J]. Chinese Journal of Cancer Prevention and Treatment, 2024, 31(12): 719-724.
[10]	王琪, 宋宏萍, 许磊. 多模态超声与其联合深度学习在乳腺癌诊断中的研究进展[J]. 分子影像学杂志, 2024, 47(10): 1119-1123. WANG Q, SONG H P, XU L. Research progress of multimodal ultrasound and its combination with deep learning in breast cancer diagnosis[J]. Journal of Molecular Imaging, 2024, 47(10): 1119-1123.
[11]	赫兰, 申锷, 杨泽堃, 等. 基于深度学习的人工智能模型自动识别颈动脉斑块[J]. 中国医疗器械杂志, 2024, 48(4): 361-366. HE L, SHEN E, et al. Deep Learning-Based Artificial Intelligence Model for Automatic Carotid Plaque Identification[J]. Chinese Journal of Medical Instrumentation, 2024, 48(4): 361-366.
[12]	LIAPI G D, LOIZOU C P, PATTICHIS C S, et al. Assessing the impact of ultrasound image standardization in deep learning-based segmentation of carotid plaque types[J]. Comp Methods Programs Biomed, 2024, 257: 108460. DOI: 10.1016/j.cmpb.2024.108460.
[13]	龚凯琳, 张利丽, 宋佳佳, 等. 基于人工智能斑块分割超声图像的影像组学在颈动脉斑块稳定性评估中的应用[J]. 临床神经外科杂志, 2021, 18(1): 1-4. GONG K L, ZHANG L L, SONG J J, et al. Application of radiomics based on artificial intelligence plaque segmented ultrasound images in evaluation of carotid plaque stability[J]. Journal of Clinical Neurosurgery, 2021, 18(1): 1-4.
[14]	张红珍. 基于深度学习的颈动脉斑块超声图像检测与分类研究[D]. 淮南: 安徽理工大学, 2023. ZHANG H. Deep learning-based detection and classification of carotid plaque in ultrasound images[D]. Huainan: Anhui University of Science and Technology, 2023.
[15]	JAIN P K, DUBEY A, SABA L, et al. Attention-based UNet deep learning model for plaque segmentation in carotid ultrasound for stroke risk stratification: an artificial Intelligence paradigm[J]. J Cardiovasc Dev Dis, 2022, 9(10): 326. DOI: 10.3390/jcdd9100326.
[16]	杨晓, 严圆. 基于CiteSpace的边境口岸研究热点与趋势[J]. 中国商论, 2024, 33(23): 163-168. YANG X, YAN Y. Research hotspots and trends in border ports based on citespace[J]. China Journal of Commerce, 2024, 33(23): 163-168.
[17]	PENG J, HAO C Y, WAN H. Bibliometric analysis of rehabilitation in Alzheimer ' s disease (2000-2023): trends, hotspots and prospects[J]. Front Aging Neurosci, 2024, 16: 1457982. DOI: 10.3389/fnagi.2024.1457982.
[18]	陈炜昊. 基于卷积神经网络的医学影像辅助诊断方法研究[D]. 咸阳: 西北农林科技大学, 2024. CHEN W H. Research on auxiliary diagnosis methods for medical images based on convolutional neural networks[D]. Xianyang: Northwest A&F University, 2024.
[19]	LIU J, ZHOU X, LIN H, et al. Deep learning based on carotid transverse B-mode scan videos for the diagnosis of carotid plaque: a prospective multicenter study[J]. Eur Radiol, 2023, 33(5): 3478-3487.
[20]	LATHA S, MUTHU P, DHANALAKSHMI S, et al. Emerging feature extraction techniques for machine learning-based classification of carotid artery ultrasound images[J]. Comput Intell Neurosci, 2022, 2022: 1847981. DOI: 10.1155/2022/1847981.
[21]	SONG J, ZOU L, LI Y, et al. Combining artificial intelligence assisted image segmentation and ultrasound based radiomics for the prediction of carotid plaque stability[J]. BMC Med Imaging, 2025, 25(1): 89. DOI: 10.1186/s12880-025-01621-4.
[22]	陈爱国. 基于随机森林算法的颈动脉支架植入术后残留预测模型构建分析[J]. 卒中与神经疾病, 2022, 29(4): 338-343. CHEN A G. Construction and analysis of prediction model for residual stenosis after carotid artery stenting based on random forest algorithm[J]. Stroke and Nervous Diseases, 2022, 29(4): 338-343.