Clinical study of construction of artificial intelligence-based localization model for venous puncture sites in contrast-enhanced imaging examination
Received date: 2025-09-08
Online published: 2025-10-28
Objective To evaluate the scientificity of artificial intelligence (AI)-based localization model for venous puncture sites in contrast-enhanced imaging examination and evaluate its clinical efficacy. Methods A prospective observational study was conducted. A total of 433 patients who underwent contrast-enhanced imaging examination at Sun Yat-sen Memorial Hospital of Sun Yat-sen University and Shenshan Central Hospital of Sun Yat-sen Memorial Hospital of Sun Yat-sen University from June 25 to July 11, 2025 were collected. Data were summarized and analyzed with reference to the indicators in the standardized application of a three-level evaluation model for inspecting peripheral venous access through image enhancement. Multimodal data were collected to establish an intelligent data preprocessing framework and develop an AI-based localization model for venous puncture sites in contrast-enhanced imaging examination. Taking the puncture sites confirmed by nurses with more than 5 years of working experience in Radiology Department as the gold standard, the degree of agreement between the puncture sites recommended by the AI-based localization model and the gold standard was evaluated. Results Among 433 patients, 380 cases were allocated into the low-risk group and 53 into the high-risk group. The Dice coefficient and Intersection over Union (IoU) of the AI-based localization model were 0.593 1 and 0.496 8, respectively, with an overall accuracy of 0.967 1. In the low-risk group, the Dice coefficient and IoU were 0.617 8 and 0.506 9, the recall rate reached 0.791 2, and the MLE score was 68.07, respectively. In the high-risk group, the Dice coefficient and IoU were 0.553 1 and 0.478 2, the recall rate was 0.702 4, and the MLE score was 64.18, respectively. There were significant differences in the Dice coefficient, IoU, accuracy rate, recall rate and MLE score between the low-risk and high-risk groups (all P < 0.001). In the age stratification analysis, the Dice coefficients in the youth, middle-aged and middle-aged groups were 0.581 0, 0.659 8 and 0.629 2, and the IoU was 0.456 3, 0.502 1 and 0.529 8, the accuracy rates exceeded 0.95 and the recall rates were 0.635 0, 0.759 1 and 0.710 4, respectively. The Dice coefficient and IoU in the elderly group were 0.550 6 and 0.524 7, the accuracy rate was 0.946 3 and recall rate was 0.670 1, respectively. There was statistical significance in each index between any of two groups (all P < 0.05). Conclusion The AI-based localization model established in this study can effectively improve the robustness of puncture site localization, provide consistent explanations aligned with clinical intuition, and offer an efficient, safe guidance regimen for selecting venous puncture sites.
DENG Hong , HUANG Zhenwei , XU Yanjun , ZHANG Yuanyuan , WANG Changdong , YANG Zehong . Clinical study of construction of artificial intelligence-based localization model for venous puncture sites in contrast-enhanced imaging examination[J]. JOURNAL OF NEW MEDICINE, 2025 , 56(10) : 968 -976 . DOI: 10.12464/j.issn.0253-9802.2025-0263
感谢中山大学孙逸仙纪念医院放射科护理团队冯艳冰主管护师、王一凡护师、唐杏萍护师、彭燕丽护师、冯舒丽护师,中山大学孙逸仙纪念医院深汕中心医院放射科黄加奕主治医师、黄艳琳主管护师在数据收集过程中的鼎力相助。
| [1] |
中华护理学会内科专业委员会. 含碘对比剂静脉外渗护理管理实践指南[J]. 中华护理杂志, 2021, 56(7): 1008. DOI: 10.3761/j.issn.0254-1769.2021.07.008.
Internal Medicine Nursing Committee of Chinese Nursing Association. Clinical practice guideline for nursing management of iodinated contrast media extravasation[J]. Chin J Nurs, 2021, 56(7): 1008. DOI: 10.3761/j.issn.0254-1769.2021.07.008.
|
| [2] |
王孝高, 马强, 官泽宇, 等. 超声可视化血管穿刺技术在血管外科临床教学中的应用[J]. 中华全科医学, 2023, 21(9): 1593-1595. DOI: 10.16766/j.cnki.issn.1674-4152.003178.
|
| [3] |
广东省精准医学应用学会. T/GDPMAA 0016-2024 影像增强检查外周静脉通路三级评价模式应用规范[S]. [2025-05-18]. https://www.gdpmaa.com/Content/ueditor1_4_3_3-utf8-net/net/upload/file/20240518/6385162990883459488159114.pdf.
Guangdong Precision Medicine Application Association. T/GDPMAA 0016-2024 The Standardized Application of a Three-level Evaluation Model for Inspecting Peripheral Venous Access through Image Enhancement[S]. [2025-05-18]. https://www.gdpmaa.com/Content/ueditor1_4_3_3-utf8-net/net/upload/file/20240518/6385162990883459488159114.pdf.
|
| [4] |
彭燕丽, 王一凡, 冯舒丽, 等. 标准化耐高压输液港护理流程在恶性肿瘤患者CT增强检查对比剂注射中的效果评 价[J]. 中国实用护理杂志, 2024, 40(22): 1705-1709. DOI:10.3760/cma.j.cn211501-20240228-00446.
|
| [5] |
邓虹, 杨泽宏, 苏赟, 等. 新型耐高压PICC作为CT增强检查对比剂注射通路的临床应用研究[J]. 中华介入放射学电子杂志, 2020, 8(3): 256-259.DOI: 10.3877/cma.j.issn.2095-5782.2020.03.014.
|
| [6] |
卢文婧, 薛峰. 专项护理对超声引导下外周动静脉精准穿刺患者穿刺成功率及护理满意度的影响[J]. 临床医学研究与实践, 2025, 10(4): 151-154. DOI: 10.19347/j.cnki.2096-1413.202504037.
|
| [7] |
|
| [8] |
|
| [9] |
|
| [10] |
陈晓华. 投影式红外血管成像仪结合金字塔分阶培训对低年资儿科护士静脉穿刺成功率的影响[J]. 医疗装备, 2023, 36(4): 146-149. DOI: 10.3969/j.issn.1002-2376.2023.04.045.
|
| [11] |
任怡璇, 崔容宇. 人工智能深度学习在单光子计算机断层显像中的研究进展[J]. 新医学, 2024, 55(3): 159-164. DOI: 10.3969/j.issn.0253-9802.2024.03.002.
|
| [12] |
诸露冰, 汪建华. 医学影像人工智能在胰腺癌精准诊疗中的研究进展[J]. 新医学, 2024, 55(3): 153-158. DOI: 10.3969/j.issn.0253-9802.2024.03.001.
|
| [13] |
郝兆虎, 赵小莹, 姚俊鑫, 等. 基于真实环境的人工智能辅助免散瞳眼底照相筛查糖尿病视网膜病变的临床应用研究[J]. 新医学, 2025, 56(7): 638-644. DOI: 10.12464/j.issn.0253-9802.2025-0076.
|
| [14] |
罗超, 朱玲. 超声引导下动态针尖定位技术在静脉穿刺困难患儿外周静脉置管中的应用[J]. 实用临床医药杂志, 2024, 28(9): 115-117. DOI: 10.7619/jcmp.20240075.
|
| [15] |
|
| [16] |
|
| [17] |
|
| [18] |
|
| [19] |
|
| [20] |
程婷婷, 刘丹, 张从. 外周静脉穿刺辅助技术临床应用进展[J]. 临床护理杂志, 2021, 20(4): 61-64. DOI: 10.3969/j.issn.1671-8933.2021.04.021.
|
| [21] |
段云娇, 赵永祯. 颈内静脉穿刺超声辅助定位法在急诊住院医师规范化培训中的应用[J]. 中国病案, 2024, 25(1): 97-99. DOI: 10.3969/j.issn.1672-2566.2024.01.031.
|
| [22] |
|
| [23] |
|
| [24] |
刘坤, 李基, 晏行伟, 等. 基于多维特征优化的红外小型无人机目标检测[J]. 光子学报, 2025, 54(8): 0810001. DOI: 10.3788/gzxb20255408.0810001.
|
| [25] |
|
| [26] |
|
| [27] |
|
| [28] |
|
| [29] |
|
/
| 〈 |
|
〉 |