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) ›› 2021, Vol. 18 ›› Issue (08) : 795 -799. doi: 10.3877/cma.j.issn.1672-6448.2021.08.015

所属专题: 乳腺超声

浅表器官超声影像学

人工智能系统评估BI-RADS 4类乳腺肿块的应用价值
臧爱华1, 姜明1, 孟聪2, 刘梦泽1, 李霞,1   
  1. 1. 266000 青岛市市立医院超声科
    2. 266000 青岛大学附属医院肿瘤科
  • 收稿日期:2020-06-16 出版日期:2021-08-01
  • 通信作者: 李霞

Application value of artificial intelligence system in BI-RADS grade 4 breast masses

Aihua Zang1, Ming Jiang1, Cong Meng2, Mengze Liu1, Xia Li,1   

  1. 1. Department of Ultrasound, Qingdao Municipal Hospital, Qingdao 266000, China
    2. Department of Oncology, Affiliated Hospital of Qingdao University, Qingdao 266000, China
  • Received:2020-06-16 Published:2021-08-01
  • Corresponding author: Xia Li
引用本文:

臧爱华, 姜明, 孟聪, 刘梦泽, 李霞. 人工智能系统评估BI-RADS 4类乳腺肿块的应用价值[J/OL]. 中华医学超声杂志(电子版), 2021, 18(08): 795-799.

Aihua Zang, Ming Jiang, Cong Meng, Mengze Liu, Xia Li. Application value of artificial intelligence system in BI-RADS grade 4 breast masses[J/OL]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2021, 18(08): 795-799.

目的

探讨人工智能(AI)系统在乳腺影像报告与数据系统(BI-RADS)4类乳腺肿块良恶性鉴别诊断中的价值。

方法

回顾性选取2018年1月至2020年2月于青岛市市立医院超声科初诊为BI-RADS 4类乳腺肿块的女性患者226例。所有患者均行常规超声检查,并经手术或穿刺活检取得病理结果。AI系统与不同年资乳腺超声专科医师(2、4、6年)分别对乳腺肿块超声图像进行分析并判断良恶性,应用四格表计算AI系统及不同年资医师对乳腺癌的诊断准确性,采用χ2检验比较AI系统与不同年资医师对不同大小乳腺癌肿块的诊断准确性。

结果

226例乳腺肿块均经病理证实,其中良性病灶96例,恶性病灶130例。AI系统诊断乳腺恶性肿块的敏感度、特异度、阳性预测值、阴性预测值和准确性分别为93.84%、92.71%、94.57%、91.75%、93.36%,均高于不同年资医师。AI系统与不同年资医师诊断≤0.5 cm、>0.5~1.0 cm、>1.0~1.5 cm的乳腺癌肿块,其诊断准确性差异均有统计学意义(P=0.029、0.011、0.002);诊断>1.5~2.0 cm、>2.0 cm的乳腺癌肿块,其诊断准确性差异均无统计学意义(P=0.117、0.668)。AI系统与2年资医师诊断≤0.5 cm、>0.5~1.0 cm、>1.0~1.5 cm的乳腺癌肿块,其诊断准确性差异均有统计学意义(P=0.006、0.002、0.001)。

结论

AI系统在BI-RADS 4类乳腺肿块良恶性判断中具有较高的诊断价值,尤其对直径≤1.5 cm的乳腺癌的诊断;其可辅助低年资超声医师提高乳腺癌的诊断率。

Objective

To assess the diagnostic value of artificial intelligence(AI) system in the differential diagnosis of benign and malignant breast tumors of breast imaging reporting and data system(BI-RADS) grade 4.

Methods

A retrospective study was performed on 226 female patients with BI-RADS grade 4 breast masses from January 2018 to February 2020 at the Ultrasound Department of Qingdao Municipal Hospital. All the tumors were examined by routine ultrasonography and pathological results were obtained by operation or puncture biopsy. The AI system and breast ultrasound specialists with different years of experiences (2, 4, and 6 years) were used to analyze the breast mass ultrasound images and judge the lesion nature, and the diagnostic accuracy of the AI system and the doctors with different years of experience for breast cancer were calculated by the four-fold table method, and the χ2 test was used to compare the diagnostic accuracy of AI system with that of physicians with different years of experience in breast cancer masses of different sizes.

Results

A total of 226 breast masses were confirmed by pathology, including 96 benign lesions and 130 malignant lesions. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the AI system were 93.84%, 92.71%, 94.57%, 91.75%, and 93.36%, respectively, which were higher than those of doctors with different years of experience. There were significant differences in diagnostic accuracy between the AI system and physicians with different years of experiences (P=0.029, 0.011, and 0.002, respectively) in breast cancer masses ≤0.5 cm,>0.5-1.0 cm, and>1.0-1.5 cm, although there was no significant difference in diagnostic accuracy of breast cancer masses>1.5-2.0 cm and>2.0 cm (P=0.117 and 0.668, respectively). There were significant differences in diagnostic accuracy between the AI system and physicians with 2 years of experience (P=0.006, 0.002, and 0.001, respectively) in breast cancer masses ≤0.5 cm,>0.5-1.0 cm, and>1.0-1.5 cm.

Conclusion

The AI system has high diagnostic value in the differentiation of benign and malignant breast masses of BI-RADS grade 4, especially in the diagnosis of breast cancer whose diameter is less than 1.5 cm, and it can assist junior doctors to improve the diagnostic rate of breast cancer.

表1 226个不同大小乳腺肿块的病理结果(个)
图1 患者,女,42岁,左侧乳腺病灶常规超声及病理图像。图a为超声图像示病灶最大径为1.7 cm,AI系统诊断为良性,高年资医师考虑为恶性肿块;图b为病理证实为左侧乳腺浸润性导管癌(HE ×200)
表2 AI系统、不同年资医师对乳腺良恶性肿块诊断结果与病理诊断结果比较(个)
表3 AI系统与不同年资医师对乳腺良恶性肿块的诊断效能分析(%)
图2 患者,女,38岁,左侧乳腺病灶常规超声及病理图像。图a为超声图像示病灶最大径为0.5 cm,AI系统诊断为恶性,所有年资医师均考虑为良性肿块;图b为病理证实为左侧乳腺导管原位癌(HE ×200)
表4 AI系统与不同年资医师对不同大小乳腺癌肿块的诊断准确性比较[个(%)]
1
Siegel RI, Miller KD, Jemal A. Cancer statistics, 2017 [J]. CA Cancer J Clin, 2017, 67(1): 7-30.
2
Youn I, Choi SH, Moon HJ, et a1. Phyllodes tumors of the breast: ultrasonographic findings and diagnostic performance of ultrasound-guided core needle biopsy [J]. Ultrasound Med Biol, 2013, 39(6): 987-992.
3
周建桥, 詹维伟. 超声乳腺影像报告数据系统及其解读 [J/CD]. 中华医学超声杂志(电子版), 2011, 10(3): 1332-1341.
4
Nakano S, Otsuka M, Mibu A, et al. Significance of fine needleaspiration cytology and vacuum-assisted core needle biopsy forsmall breast lesions [J]. Clin Breast Cancer, 2015, 15(1): e23-e26.
5
张意珍, 黄品同, 洪玉蓉, 等. 超声造影与弹性成像联合评分对乳腺 BI-RADS 4 类病灶的应用价值 [J/CD]. 中华医学超声杂志(电子版), 2019, 2 (16):120-125.
6
Kim K, Song MK, Kim EK, et al. Clinical application of S-Detect to breast masses on ultrasonography: a study evaluating the diagnostic performance and agreement with a dedicated breast radiologist [J]. Ultrasonography, 2017, 36(1): 3-9.
7
Choi JH, Kang BJ, Baek JE, et al. Application of computer-aideddiagnosis in breast ultrasound interpretation: improvementsin diagnostic performance according to reader experience [J]. Ultrasonography, 2018, 37(3): 217-225.
8
唐金海, 姚宇锋. 早期乳腺癌的诊断和外科治疗进展 [J] .中国普外基础与临床杂志, 2011, 18(9): 913-916.
9
Chen CM, Chou YH, Han KC, et al. Breast lesions on sonograms: computer-aided diagnosiswithnearlysetting-independentfeatures and artificial neural networks [J]. Radiology, 2003, 226(2): 504-514.
10
Doi K. Computer-aided diagnosis in medical imaging:historical review, current status and future potential [J]. Comput Med Imaging Graph, 2007, 31(4-5): 198-211.
11
周永刚, 袁丽君, 邢长洋, 等. 超声S-Detect 分类技术在乳腺包块良恶性诊断中的应用价值 [J]. 中华超声影像学杂志, 2017, 26(12): 1053-1056.
12
罗晓, 李安华. 人工智能在乳腺癌诊治中的应用与思考 [J/CD]. 中华医学超声杂志(电子版), 2019, 4(16): 247-250.
[1] 王亚红, 蔡胜, 葛志通, 杨筱, 李建初. 颅骨骨膜窦的超声表现一例[J/OL]. 中华医学超声杂志(电子版), 2024, 21(11): 1089-1091.
[2] 章建全, 程杰, 陈红琼, 闫磊. 采用ACR-TIRADS评估甲状腺消融区的调查研究[J/OL]. 中华医学超声杂志(电子版), 2024, 21(10): 966-971.
[3] 罗辉, 方晔. 品管圈在提高甲状腺结节细针穿刺检出率中的应用[J/OL]. 中华医学超声杂志(电子版), 2024, 21(10): 972-977.
[4] 杨忠, 时敬业, 邓学东, 姜纬, 殷林亮, 潘琦, 梁泓, 马建芳, 王珍奇, 张俊, 董姗姗. 产前超声在胎儿22q11.2 微缺失综合征中的应用价值[J/OL]. 中华医学超声杂志(电子版), 2024, 21(09): 852-858.
[5] 孙佳丽, 金琳, 沈崔琴, 陈晴晴, 林艳萍, 李朝军, 徐栋. 机器人辅助超声引导下经皮穿刺的体外实验研究[J/OL]. 中华医学超声杂志(电子版), 2024, 21(09): 884-889.
[6] 史学兵, 谢迎东, 谢霓, 徐超丽, 杨斌, 孙帼. 声辐射力弹性成像对不可切除肝细胞癌门静脉癌栓患者放射治疗效果的评价[J/OL]. 中华医学超声杂志(电子版), 2024, 21(08): 778-784.
[7] 韩萌萌, 冯雪园, 马宁. 乳腺癌改良根治术后桡神经损伤1例[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 117-118.
[8] 高杰红, 黎平平, 齐婧, 代引海. ETFA和CD34在乳腺癌中的表达及与临床病理参数和预后的关系研究[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 64-67.
[9] 张志兆, 王睿, 郜苹苹, 王成方, 王成, 齐晓伟. DNMT3B与乳腺癌预后的关系及其生物学机制[J/OL]. 中华普外科手术学杂志(电子版), 2024, 18(06): 624-629.
[10] 李浩, 陈棋帅, 费发珠, 张宁伟, 李元东, 王硕晨, 任宾. 慢性肝病肝纤维化无创诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(09): 863-867.
[11] 谭瑞义. 小细胞骨肉瘤诊断及治疗研究现状与进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 781-784.
[12] 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.
[13] 王子阳, 王宏宾, 刘晓旌. 血清标志物对甲胎蛋白阴性肝细胞癌诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(07): 677-681.
[14] 陈慧, 邹祖鹏, 周田田, 张艺丹, 张海萍. 皮肤镜对头皮红斑性皮肤病辅助鉴别诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(07): 692-698.
[15] 胡云鹤, 周玉焯, 付瑞瑛, 于凡, 李爱东. CHS-DRG付费制度下GB1分组住院费用影响因素分析与管理策略探讨[J/OL]. 中华临床医师杂志(电子版), 2024, 18(06): 568-574.
阅读次数
全文
29
HTML PDF
最新录用 在线预览 正式出版 最新录用 在线预览 正式出版
0 0 9 0 0 20

  来源 本网站 其他网站
  次数 24 5
  比例 83% 17%

摘要
574
最新录用 在线预览 正式出版
0 0 574
  来源 本网站 其他网站
  次数 429 145
  比例 75% 25%