ISSN 1004-4140
CN 11-3017/P

探讨CT扫描剂量对人工智能检测肺结节效能的影响

温德英, 潘雪琳, 姚辉, 李吉杰, 邓巧, 唐露, 伍希, 孙家瑜

温德英, 潘雪琳, 姚辉, 李吉杰, 邓巧, 唐露, 伍希, 孙家瑜. 探讨CT扫描剂量对人工智能检测肺结节效能的影响[J]. CT理论与应用研究, 2021, 30(4): 455-465. DOI: 10.15953/j.1004-4140.2021.30.04.06
引用本文: 温德英, 潘雪琳, 姚辉, 李吉杰, 邓巧, 唐露, 伍希, 孙家瑜. 探讨CT扫描剂量对人工智能检测肺结节效能的影响[J]. CT理论与应用研究, 2021, 30(4): 455-465. DOI: 10.15953/j.1004-4140.2021.30.04.06
WEN Deying, PAN Xuelin, YAO Hui, LI Jijie, DENG Qiao, TANG Lu, WU Xi, SUN Jiayu. To Explore the Effect of CT Scan Dose on the Efficacy of Artificial Intelligence in Detecting Lung Nodules[J]. CT Theory and Applications, 2021, 30(4): 455-465. DOI: 10.15953/j.1004-4140.2021.30.04.06
Citation: WEN Deying, PAN Xuelin, YAO Hui, LI Jijie, DENG Qiao, TANG Lu, WU Xi, SUN Jiayu. To Explore the Effect of CT Scan Dose on the Efficacy of Artificial Intelligence in Detecting Lung Nodules[J]. CT Theory and Applications, 2021, 30(4): 455-465. DOI: 10.15953/j.1004-4140.2021.30.04.06

探讨CT扫描剂量对人工智能检测肺结节效能的影响

基金项目: 

四川省科技厅重点研发项目(2020YFS0123)。

详细信息
    作者简介:

    温德英,女,本科,四川大学华西医院放射科初级技师,主要从事CT、MR成像技术研究,E-mail:940035866@qq.com;孙家瑜*,影像医学与核医学硕士,四川大学华西医院放射科主任技师,主要从事CT、MR成像及心脏MR技术研究,E-mail:sjy080512@163.com。

  • 中图分类号: TP18;R814

To Explore the Effect of CT Scan Dose on the Efficacy of Artificial Intelligence in Detecting Lung Nodules

  • 摘要: 目的:探讨影响人工智能检测肺结节效能的因素,力求为不同性质的结节提供个性化的扫描剂量及人工智能系统,同时为各人工智能系统适宜的扫描条件提供参考。方法:标准成人男子胸部X线/CT影像模型,内部随机分布15个不同密度和大小的模拟肺结节,采用不同的管电压和管电流对模型进行扫描,共扫描50次。应用不同公司的人工智能系统进行肺结节检测,采用Pearson χ2检验或Fisher确切概率法比较各组检出率和假阴性率;采用Kruskal-Wallis H检验比较假阳性率。结果:①不同管电压条件下,公司A和公司C对不同性质肺结节的检出率无统计学差异;公司B对+100HU结节的检出率,70kV(100%)组高于120kV(80%)和140kV(80%)组;公司B对3mm结节的检出率,70kV组(33.33%)高于120kV(0%)和140kV(0%)组,差异有统计学意义。②各管电压组内不同管电流间及各管电压组间,检出率、假阴性率的差异无统计学意义。各管电压组间假阳性率的差异具有统计学意义。③公司A在70kV组检出率(64.44%)低于公司B(80.00%)、假阴性率(35.56%)高于公司B(20.00%);公司A的假阳性率高于公司B和公司C;公司B和公司C间检出率、假阴性率、假阳性率无统计学差异。结论:人工智能辅助肺结节检测的灵敏度与CT扫描剂量无关,与结节性质及AI系统性能有关。本研究中公司B和公司C整体性能高于公司A,最佳扫描管电压分别是70kV、70kV和100kV。
    Abstract: Objective: To explore the factors that affect the effectiveness of artificial intelligence systems in detecting lung nodules, and strive to provide personalized scanning conditions and artificial intelligence systems for nodules of different natures, and provide references for the appropriate scanning conditions of various artificial intelligence systems. Methods: Standard adult male chest X-ray/CT image model, in which 15 simulated lung nodules with different density and size are randomly distributed was scanned by different tube voltages and tube current at a total of 50 times. The artificial intelligence systems of different companies are used to detect lung nodules. The Pearson χ2 test or Fisher exact probability method is used to compare the detection rate and false negative rate of each group; the Kruskal-Wallis H test is used to compare the false positive rate. Results: (1) Under different kV conditions, the detection rates of nodules of different densities and sizes of company A and C were not statistically different; the detection rate of +100 nodules in company B is higher in the 70kV (100%) group than that in the 120kV (80%) and 140kV (80%) group; the detection rate of 3mm nodules in company B was higher in the 70kV group (33.33%) than in the 120kV (0%) and 140kV (0%) group. (2) There was no significant difference in detection rate and false negative rate among different mAs in each kV group of the three companies or each kV group. The difference in false positive rate among the kV groups was statistically significant. (3) The detection rate of company A in the70kV group (64.44%) is lower than that of company B (80.00%), and the false negative rate (35.56%) is higher than that of company B (20.00%); The false positive rate of company A is higher than that of company B and company C. There is no statistical difference in the detection rate, false negative rate, and false positive rate between company B and C. Conclusions: The sensitivity of artificial intelligence-assisted lung nodule detection has nothing to do with the CT scan dose, but is related to the nature of the nodule and the performance of the AI system. In this study, the overall performance of company B and C is higher than that of company A, and the best scanning tube voltages are 70kV, 70kV, and 100kV respectively.
  • [1] 肖佳龙, 郑莹. 全球肺癌的流行及预防进展[J]. 中国癌症杂志, 2020, 30(10):721-725.

    XIAO J L, ZHENG Y. The global prevalence and prevention progress of lung cancer[J]. China Oncology, 2020, 30(10):721-725. (in Chinese).

    [2] 王婧璇, 林岚, 赵思远, 等. 基于深度学习的肺结节计算机断层扫描影像检测与分类的研究进展[J]. 生物医学工程学杂志, 2019, 36(4):670-676.

    WANG J X, LIN L, ZHAO S Y, et al. Research progress on computed tomography image detection and classification of pulmonary nodule based on deep learning[J]. Journal of biomedical engineering, 2019, 36(4):670-676. (in Chinese).

    [3] 姚本波, 余建群. CT纹理特征分析在孤立性肺结节诊断中的研究进展[J]. CT理论与应用研究, 2020, 29(1):111-118.

    DOI:10.15953/j.1004-4140.2020.29.01.14. YAO B B, YU J Q. Advance of CT texture feature analysis in diagnosis of solitary pulmonary nodules[J]. CT Theory and Applications, 2020, 29(1):111-118. DOI:10.15953/j.1004-4140. 2020.29.01.14. (in Chinese).

    [4] 陈震, 郁开朗. 人工智能影像软件在体检肺结节筛查中的应用分析[J]. 当代医学, 2020, 26(28):171-173.
    [5] 陈中博, 陆青云, 王艳. 人工智能在胸部低剂量CT体检人群中应用的评价[J]. 影像研究与医学应用, 2020, 4(7):98-99.
    [6] 周其敏, 吴志伟, 钟庆童, 等. 人工智能肺小结节检测系统在低剂量CT肺筛查中的价值[J]. 医学影像学杂志, 2020, 30(11):2025-2028.

    ZHOU Q M, WU Z W, ZHONG Q T, et al. The value of artificial intelligence pulmonary nodules detection system in low-dose CT lung screening[J]. Journal of Medical Imaging, 2020, 30(11):2025-2028. (in Chinese).

    [7]

    CHRISTE A, SZUCS-FARKAS Z, HUBER A, et al. Optimal dose levels in screening chest CT for unimpaired detection and volumetry of lung nodules, with and without computer assisted detection at minimal patient radiation[J]. PLoS One, 2013, 8(12):e82919.

    [8] 杨文洁, 吴梦熊, 张欢, 等. 胸部低剂量CT中肺结节自动测量软件的体模研究[J]. 中国医学计算机成像杂志, 2015, 21(4):382-386.

    YANG W J, WU M X, ZHANG H, et al. Influence of exposure parameters nodule characteristics on computer-assisted lung nodule volumetry in low-dose CT:A phantom study[J]. Chinese Computed Medical Imaging, 2015, 21(4):382-386. (in Chinese).

    [9] 崔兆国, 吴昊, 汤敏, 等. 重建层厚(1/2/3mm)对人工智能检测肺结节效能的影响[J]. 中国医疗设备, 2020, 35(10):103-105.

    CUI Z G, WU H, TANG M, et al. Effect of reconstruction thickness (1/2/3mm) on effectiveness of artificial intelligence in detecting pulmonary nodules[J]. China Medical Devices, 2020, 35(10):103-105. (in Chinese).

    [10] 朱熹, 夏巍, 周中柱, 等. 低剂量CT不同重建技术对计算机辅助诊断肺结节的影响[J]. 放射学实践, 2019, 34(11):1255-1259.

    ZHU X, XIA W, ZHOU Z Z, et al. Effect of different reconstruction techniques on computer-aided diagnosis of pulmonary nodules in low-dose CT[J]. Radiologic Practice, 2019, 34(11):1255-1259. (in Chinese).

    [11] 曹源, 李丹阳, 张扬, 等. 100kVP管电压不同重建算法对AI辅助检测肺结节效能影响[J]. 放射学实践, 2020, 35(10):1324-1328.

    CAO Y, LI D Y, ZHANG Y, et al. Influence of iterative reconstruction algorithm on deep learning-based pulmonary nodule detection in 100kVp CT scans[J]. Radiologic Practice, 2020, 35(10):1324-1328. (in Chinese).

    [12] 杨尚文, 胡安宁, 徐亚运, 等. CT图像分辨率对人工智能肺结节辅助诊断系统诊断准确性的影响[J]. 医学影像学杂志, 2020, 30(6):965-968.

    YANG S W, HU A N, XU Y Y, et al. Effect of CT image resolution on diagnostic accuracy of artificial intelligence pulmonary nodule-assisted diagnosis system[J]. Journal of Medical Imaging, 2020, 30(6):965-968. (in Chinese).

    [13] 李欣菱, 郭芳芳, 周振, 等. 基于深度学习的人工智能胸部CT肺结节检测效能评估[J]. 中国肺癌杂志, 2019, 22(6):336-340.

    LI X L, GUO F F, ZHOU Z, et al. Performance of deep-learning-based artificial intelligence on detection of pulmonary nodules in chest CT[J]. Chinese Journal of Lung Cancer, 2019, 22(6):336-340. (in Chinese).

    [14]

    ZHENG S, CUI X, VONDER M, et al. Deep learning-based pulmonary nodule detection:Effect of slab thickness in maximum intensity projections at the nodule candidate detection stage[J]. Computer Methods and Programs in Biomedicine, 2020, 196:105620.

    [15]

    BLANC D, RACINE V, KHALIL A, et al. Artificial intelligence solution to classify pulmonary nodules on CT[J]. Diagnostic and Interventional Imaging, 2020, 101(12):803-810.

    [16]

    FU B, WANG G, WU M, et al. Influence of CT effective dose and convolution kernel on the detection of pulmonary nodules in different artificial intelligence software systems:A phantom study[J]. European Journal of Radiology, 2020, 126:108928.

    [17] 赵超. 人工智能识别软件辅助阅片在胸部CT肺结节检出中的应用价值[J]. 医疗装备, 2020, 33(22):23-24.
    [18] 张正华, 蔡雅倩, 韩丹, 等. 人工智能与不同级别医师对肺结节检出效能的对照研究[J]. 中国医学影像学杂志, 2020, 28(9):662-665.

    ZHANG Z H, CAI Y Q, HAN D, et al. Artificial intelligence and various levels of physicians in detection of pulmonary nodules:A comparative Study[J]. Chinese Journal of Medical Imaging, 2020, 28(9):662-665. (in Chinese).

    [19]

    PRAKASHINI K, BABU S, RAJGOPAL K V, et al. Role of computer aided diagnosis (CAD) in the detection of pulmonary nodules on 64 row multi detector computed tomography[J]. Lung India, 2016, 33(4):391.

    [20]

    BODELLE B, KLEMENT D, KERL J M, et al. 70kV computed tomography of the thorax:Valence for computer-assisted nodule evaluation and radiation dose-first clinical results[J]. Acta Radiologica, 2014, 55(9):1056-1062.

    [21] 宫敬, 焦桥, 马质君. 人工智能辅助诊断技术在低剂量CT肺结节筛查中的应用及质控[J]. 影像研究与医学应用, 2020, 4(22):120-121.
    [22] 宋婷妮, 曾勇明, 周旸, 等. 双能CT单能谱成像检测不同性质孤立性肺结节的实验研究[J]. 中国医学计算机成像杂志, 2016, 22(1):33-38.

    SONG T N, ZENG Y M, ZHOU Y, et al. Virtual monochromatic spectral imaging on solitary pulmonary nodules:A phantom study[J]. Chinese Computed Medical Imaging, 2016, 22(1):33-38. (in Chinese).

  • 期刊类型引用(4)

    1. 尹振琪,吴俊峰,朱石柱. 人工智能辅助诊断系统结合低剂量CT在肺小结节筛查中的应用进展. 影像研究与医学应用. 2024(24): 7-9 . 百度学术
    2. 王璟琛,柴军. 人工智能体积密度法判断肺亚实性结节的浸润性研究. CT理论与应用研究. 2023(02): 241-248 . 本站查看
    3. 王和良,苏良宝,蔡少辉,杜丽珠. 人工智能辅助诊断系统在肺结节CT检测中的应用分析. 中国医疗器械信息. 2023(05): 91-93+161 . 百度学术
    4. 苏寅晨,张晓琴. 人工智能在肺结节检测及诊断中的应用进展. 内蒙古医学杂志. 2023(04): 506-508 . 百度学术

    其他类型引用(1)

计量
  • 文章访问数:  175
  • HTML全文浏览量:  8
  • PDF下载量:  21
  • 被引次数: 5
出版历程
  • 收稿日期:  2021-04-28
  • 网络出版日期:  2021-09-23

目录

    /

    返回文章
    返回
    x 关闭 永久关闭