切换至 "中华医学电子期刊资源库"

中华医学超声杂志(电子版) ›› 2022, Vol. 19 ›› Issue (09) : 983 -989. doi: 10.3877/cma.j.issn.1672-6448.2022.09.019

浅表器官超声影像学

人工智能自动检测系统对不同经验医师诊断乳腺小肿块的辅助作用
吕淑懿1, 张燕1,(), 章美武1, 范晓翔1, 高立博1, 李飞1   
  1. 1. 315010 浙江宁波,中国科学院大学宁波华美医院介入治疗科
  • 收稿日期:2022-02-02 出版日期:2022-09-01
  • 通信作者: 张燕
  • 基金资助:
    浙江省医药卫生科技计划项目(2020KY837)

Role of an automated artificial intelligence detection system in diagnosis of small breast masses by physicians with varying levels of experience

Shuyi Lyu1, Yan Zhang1,(), Meiwu Zhang1, Xiaoxiang Fan1, Libo Gao1, Fei Li1   

  1. 1. Interventional Therapy Department, Hwa Mei Hospital, University of Chinese Academy of Sciences, Ningbo 315010, China
  • Received:2022-02-02 Published:2022-09-01
  • Corresponding author: Yan Zhang
引用本文:

吕淑懿, 张燕, 章美武, 范晓翔, 高立博, 李飞. 人工智能自动检测系统对不同经验医师诊断乳腺小肿块的辅助作用[J/OL]. 中华医学超声杂志(电子版), 2022, 19(09): 983-989.

Shuyi Lyu, Yan Zhang, Meiwu Zhang, Xiaoxiang Fan, Libo Gao, Fei Li. Role of an automated artificial intelligence detection system in diagnosis of small breast masses by physicians with varying levels of experience[J/OL]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2022, 19(09): 983-989.

目的

初步探讨人工智能自动检测系统对乳腺小肿块的诊断效能以及对不同经验医师的辅助作用。

方法

选取中国科学院大学宁波华美医院164个经病理证实的最大直径≤10 mm的乳腺小肿块,由4名不同经验的医师(医师A和医师B归为高年资医师组,医师C和医师D归为低年资医师组)先独立诊断,给出相应的乳腺影像报告与数据系统(BI-RADS)分类,结果设为A1组、B1组、C1组和D1组。4周后,4名医师再次联合应用人工智能自动检测系统诊断,结果设为A2组、B2组、C2组和D2组。人工智能自动检测系统诊断结果设为M组。以病理结果为金标准,计算不同组医师诊断的敏感度、特异度、准确性、阴性预测值和阳性预测值,绘制受试者操作特征曲线。采用Kappa检验比较不同组观察者间的一致性。

结果

病理结果显示,164个乳腺肿块中良性117个(71.34%),恶性47个(28.66%)。人工智能自动检测系统对乳腺小肿块有良好的诊断效能,敏感度、特异度、准确性分别为91.49%、90.6%、90.85%。联合应用人工智能自动检测系统后高年资医师的诊断效能有上升趋势,敏感度、特异度分别为A1组82.98%、82.05%;A2组87.23%、89.74%;B1组80.85%、84.62%;B2组85.11%、89.74%。低年资医师在人工智能自动检测系统的辅助下诊断效能明显提高,敏感度、特异度分别为C1组76.60%、74.36%;C2组82.98%、82.05%;D1组68.09%、73.50%;D2组80.85%、80.34%。此外低年资医师借助人工智能自动检测系统对乳腺小肿块BI-RADS分类的观察者间一致性明显提高,低年资医师间的Kappa值由0.236提高到0.549,低年资医师与高年资医师的Kappa值由0.268~0.284提高到0.432~0.540。

结论

人工智能自动检测系统对乳腺小肿块良恶性的判断具有较高的诊断效能,其对不同经验医师的辅助作用不同,对低年资医师的影响大于高年资医师。人工智能自动检测系统有助于提高低年资医师BI-RADS分类观察者间的一致性。

Objective

To preliminarily investigate the diagnostic efficacy of an automated artificial intelligence (AI) detection system for small breast masses, as well as its complementary role for physicians with varying levels of experience.

Methods

A total of 164 pathologically confirmed small breast masses with a diameter of up to 10 mm were chosen at Hwa Mei Hospital, University of Chinese Academy of Sciences, and four physicians (doctors A and B were senior physicians, and doctors C and D were junior ones) with varying levels of experience independently diagnosed the masses according to the Breast Imaging Reporting and Data System (BI-RADS) classification, and the results were reported as groups A1, B1, C1, and D1. Four weeks later, the four physicians again jointly applied the AI automatic detection system to diagnose the masses, and the results were reported as groups A2, B2, C2, and D2. The results of the AI automatic detection system were reported as group M. Taking pathological results as the gold standard, the sensitivity, specificity, accuracy, negative predictive value, and positive predictive value of diagnosis by physicians in different groups were calculated, and the receiver operating characteristic curve was drawn. The Kappa test was used to calculate the interobserver agreement between groups.

Results

Pathological results showed that among the 164 breast masses, 117 (71.34%) were benign and 47 (28.66%) were malignant. The AI automatic detection system had good diagnostic efficacy for small breast lumps, with a sensitivity, specificity, and accuracy of 91.49%, 90.6%, and 90.85%. The diagnostic efficacy of senior physicians after the joint application of the AI automatic detection system tended to increase, with a sensitivity and specificity of 82.98% and 82.05% in group A1; 87.23% and 89.74% in group A2; 80.85% and 84.62% in group B1; and 85.11% and 89.74% in group B2. The diagnostic efficacy of senior physicians with the aid of the AI automatic detection system was significantly improved, with a sensitivity and specificity of 76.60% and 74.36 in group C1; 82.98% and 82.05% in group C2; 68.09% and 73.50% in group D1; and 80.85% and 80.34% in group D2. The interobserver agreement of BI-RADS classification of small breast masses by low senior physicians with the help of the AI automatic detection system was significantly higher. The Kappa value among junior physicians increased from 0.236 to 0.549. The Kappa value among junior and senior physicians increased from 0.268-0.284 to 0.432-0.540.

Conclusion

The AI automated detection system has high diagnostic efficacy in determining the benignity and malignancy of small breast masses, and its adjunctive effect varies among experienced physicians, with a greater impact on junior physicians than on senior physicians. The AI automated detection system helps to improve the interobserver agreement of BI-RADS classification among junior physicians.

图1 人工智能自动检测系统(AI-SONIC Breast)良性肿块诊断流程图。图a示AI-SONIC Breast自动识别乳腺肿块,并对方向、边缘、结构、回声类型和强回声5个特征自动分析;图b示AI-SONIC Breast自动进行良恶性判断,肿块良恶性概率值为0.23,偏良性;图c该肿块病理提示为乳腺腺病
图2 人工智能自动检测系统(AI-SONIC Breast)恶性肿块诊断流程图。图a示AI-SONIC Breast自动识别乳腺肿块,并对方向、边缘、结构、回声类型和强回声5个特征自动分析;图b示AI-SONIC Breast自动进行良恶性判断,肿块良恶性概率值为0.69,偏恶性;图c该肿块病理提示为乳腺浸润性导管癌
表1 164个乳腺小肿块的病理结果[个(%)]
表2 4名医师BI-RADS分类结果的一致性分析结果
表3 AI-SONIC Breast与不同年资医师的诊断一致性分析结果
表4 不同组医师对乳腺小肿块诊断效能比较
图3 不同诊断方式组诊断乳腺小肿块的受试者操作特征曲线注:A1、B1、C1、D1代表4名医师独立进行人工乳腺肿块分类,A2、B2、C2、D2代表4名医师应用人工智能自动检测系统(AI-SONIC Breast)辅助进行乳腺肿块分类,M组为AI-SONIC Breast分类结果
1
Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J]. CA Cancer J Clin, 2021, 71(3): 209-249.
2
Natarajan B, Spiegel D, Nichols EM, et al. Findings on surveillance imaging after preoperative partial breast irradiation for early stage breast cancer [J/CD]. Int J Radiat Oncol Biol Phys, 2018, 102(4): 1374-1381.
3
朱庆莉, 姜玉新. 乳腺影像报告与数据系统指南(第5版)超声内容更新介绍 [J/CD]. 中华医学超声杂志(电子版), 2016, 13(1): 5-7.
4
Abdullah N, Mesurolle B, Elkhoury M, et al. Breast imaging reporting and data system lexicon for US: interobserver agreement for assessment of breast masses [J]. Radiology, 2009, 252(3): 665-672.
5
Xiao X, Jiang Q, Wu H, et al. Diagnosis of sub-centimetre breast lesions: combining BI-RADS-US with strain elastography and contrast-enhanced ultrasound-a preliminary study in China [J]. Eur Radiol, 2016, 27(6): 2443-2450.
6
Guo X, Liu Z, Sun C, et al. Deep learning radiomics of ultrasonography: identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer [J]. EBioMedicine, 2020, 60: 103018.
7
Tran WT, Sadeghi-Naini A, Lu FI, et al. Computational radiology in breast cancer screening and diagnosis using artificial intelligence [J]. Can Assoc Radiol J, 2021, 72(1): 98-108.
8
Interlenghi M, Salvatore C, Magni V, et al. A machine learning ensemble based on radiomics to predict BI-RADS category and reduce the biopsy rate of ultrasound-detected suspicious breast masses [J]. Diagnostics(Basel), 2022, 12(1): 187.
9
Lei S, Zheng R , Zhang S, et al. Breast cancer incidence and mortality in women in China: temporal trends and projections to 2030 [J]. Cancer Biol Med, 2021, 18(3): 1-12.
10
Sant M, Allemani C, Berrino F, et al. Breast carcinomasurvival in Europe and the United States [J]. Cancer, 2004, 100(4): 715-722.
11
Park CS, Lee JH, Yim HW, et al. Observer agreement using the ACR Breast Imaging Reporting and Data System (BI-RADS)-ultrasound, First Edition (2003) [J]. Korean J Radiol, 2007, 8(5): 397-402.
12
Lee HJ, Kim EK, Kim MJ, et al. Observer variability of Breast Imaging Reporting and Data System (BI-RADS) for breast ultrasound [J]. Eur J Radiol, 2008, 65(2): 293-298.
13
赖兴建, 朱庆莉, 姜玉新, 等. 乳腺病变超声乳腺影像报告和数据系统(BI-RADS)诊断一致性的评估 [J]. 中华超声影像学杂志, 2010, 19(8): 701-704.
14
Berg WA, D'Orsi CJ, Jackson VP, et al. Does training in the Breast Imaging Reporting and Data System (BI-RADS) improve biopsy recommendations or feature analysis agreement with experienced breast imagers at mammography? [J]. Radiology, 2002, 224(3): 871-880.
15
Izumori A, Takebe K, Sato TA. Ultrasound findings and histological features of ductal carcinoma in situ detected by ultrasound examination alone [J]. Breast Cancer, 2010, 17(2): 136-141.
16
陈琮瑛, 王文韬, 余蓉, 等. 乳腺小肿块的超声BI-RADS分析研究 [J]. 中华超声影像学杂志, 2014, 23(11): 957-961.
17
Schmachtenberg C, Fischer T, Hamm B, et al. Diagnostic performance of automated breast volume scanning (ABVS) compared to handheld ultrasonography with breast MRI as the gold standard [J]. Acad Radiol, 2017, 24(8): 954-961.
18
Berg WA. Tailored supplemental screening for breast cancer: what now and what next? [J]. AJR Am J Roentgenol, 2009, 192(2): 390-399.
19
Quon JL, Chen LC, Kim L, et al. Deep learning for automated delineation of pediatric cerebral arteries on pre-operative brain magnetic resonance imaging [J]. Front Surg, 2020, 7: 517375.
20
Klimont M, Oronowicz-Jakowiak A, Flieger M, et al. Deep learning for cerebral angiography segmentation from non-contrast computed tomography [J]. PLoS One, 2020, 15(7): e0237092.
[1] 李洋, 蔡金玉, 党晓智, 常婉英, 巨艳, 高毅, 宋宏萍. 基于深度学习的乳腺超声应变弹性图像生成模型的应用研究[J/OL]. 中华医学超声杂志(电子版), 2024, 21(06): 563-570.
[2] 杨敬武, 周美君, 陈雨凡, 李素淑, 何燕妮, 崔楠, 刘红梅. 人工智能超声结合品管圈活动对低年资超声医师甲状腺结节风险评估能力的作用[J/OL]. 中华医学超声杂志(电子版), 2024, 21(05): 522-526.
[3] 明昊, 肖迎聪, 巨艳, 宋宏萍. 乳腺癌风险预测模型的研究现状[J/OL]. 中华乳腺病杂志(电子版), 2024, 18(05): 287-291.
[4] 李焕玺, 何淳诺, 田志敏, 周胜虎, 吴昊越, 张浩强. 全膝关节置换术后股骨远端假体周围骨折治疗现状[J/OL]. 中华关节外科杂志(电子版), 2024, 18(05): 630-637.
[5] 叶莉, 杜宇. 深度学习在牙髓根尖周病临床诊疗中的应用[J/OL]. 中华口腔医学研究杂志(电子版), 2024, 18(06): 351-356.
[6] 王玲艳, 高春晖, 冯雪园, 崔鑫淼, 刘欢, 赵文明, 张金库. 循环肿瘤细胞在乳腺癌新辅助及术后辅助治疗中的应用[J/OL]. 中华普外科手术学杂志(电子版), 2024, 18(06): 630-633.
[7] 熊鹰, 林敬莱, 白奇, 郭剑明, 王烁. 肾癌自动化病理诊断:AI离临床还有多远?[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(06): 535-540.
[8] 李伟, 宋子健, 赖衍成, 周睿, 吴涵, 邓龙昕, 陈锐. 人工智能应用于前列腺癌患者预后预测的研究现状及展望[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(06): 541-546.
[9] 黄俊龙, 李文双, 李晓阳, 刘柏隆, 陈逸龙, 丘惠平, 周祥福. 基于盆底彩超的人工智能模型在女性压力性尿失禁分度诊断中的应用[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(06): 597-605.
[10] 莫淇舟, 苏劲, 黄健, 李健维, 李思宁, 柳建军. 智能控压输尿管软镜碎石吸引取石术在直径10~25 mm上尿路结石中的应用[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(05): 497-502.
[11] 苏博兴, 肖博, 李建兴. 2024年美国泌尿外科学会年会结石领域手术治疗相关热点研究及解读[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(04): 303-308.
[12] 莫林键, 杨舒博, 农卫赟, 程继文. 人工智能虚拟数字医师在钬激光前列腺剜除日间手术患教管理中的应用[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(04): 318-322.
[13] 李义亮, 苏拉依曼·牙库甫, 麦麦提艾力·麦麦提明, 克力木·阿不都热依木. 机器人与腹腔镜食管裂孔疝修补术联合Nissen 胃底折叠术短期疗效分析[J/OL]. 中华疝和腹壁外科杂志(电子版), 2024, 18(05): 512-517.
[14] 孙铭远, 褚恒, 徐海滨, 张哲. 人工智能应用于多发性肺结节诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 785-790.
[15] 张玮玮, 霍晓川. 人工智能时代医学生批判性思维培养的重要性[J/OL]. 中华脑血管病杂志(电子版), 2024, 18(04): 357-359.
阅读次数
全文


摘要