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

王琪; 宋宏萍; 许磊

doi:10.12122/j.issn.1674-4500.2024.10.15

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

doi: 10.12122/j.issn.1674-4500.2024.10.15

王琪^{1, 2,},
宋宏萍²,
许磊^3, ,

1.
陕西中医药大学医学技术学院，陕西咸阳 712046
2.
空军军医大学西京医院超声医学科，陕西西安 710032
3.
西安市中医医院功能科，陕西西安 710021

基金项目:

国家自然科学基金面上项目 82471991

国家自然科学基金面上项目 82071934

陕西省国际科技合作与交流计划重点项目 2020KWZ-022

详细信息

作者简介:
王琪，在读硕士研究生，主治医师，E-mail: csyjswq@163.com

通讯作者:
许磊，副主任医师，E-mail: xulfmmu@126.com

计量
- 文章访问数: 59
- HTML全文浏览量: 20
- PDF下载量: 12
- 被引次数: 0
出版历程
- 收稿日期: 2024-07-14
- 网络出版日期: 2024-11-02
- 刊出日期: 2024-10-20

Research progress of multimodal ultrasound and its combination with deep learning in breast cancer diagnosis

WANG Qi^{1, 2
,},
SONG Hongping²,
XU Lei^{3
, ,}

1.
School of Medical Technology, Shaanxi University of Chinese Medicine, Xianyang 712046, China
2.
Department of Ultrasound, Xijing Hospital, Air Force Military Medical University, Xi'an 710032, China
3.
Department of Functional, Xi'an Hospital of Traditional Chinese Medicine, Xi'an 710021, China

摘要

摘要: 乳腺癌是导致女性死亡的重要原因。超声是乳腺癌疾病的主要影像学检查方法，将二维超声、彩色多普勒血流成像、超声弹性成像等不同超声技术联合应用于乳腺癌的诊断可显著提高诊断效率和准确性，减少不必要的穿刺活检。人工智能技术的加入，有潜力帮助医生更高效、更精准的作出决策，为诊断乳腺癌提供一种新的策略。本文将对比不同超声技术在乳腺癌诊断中的优劣，讨论深度学习联合多模态超声成像在乳腺癌诊断、预测和疗效评估等方面的积极作用，并提出乳腺超声未来可能面临的挑战，以期为临床医生提供参考。
- 乳腺癌 /
- 超声 /
- 诊断 /
- 深度学习
Abstract: Breast cancer is an important cause of death in women. Ultrasound is the main imaging examination method for breast cancer. The combined application of different ultrasound technologies such as two- dimensional ultrasound, color Doppler flow imaging, and ultrasound elastography to the diagnosis of breast cancer can significantly improve diagnostic efficiency and accuracy, and reduce unnecessary needle biopsy. The addition of artificial intelligence technology has the potential to help doctors make more efficient and accurate decisions, providing a new strategy for diagnosing breast cancer. This review compared the advantages and disadvantages of different ultrasound technologies in the diagnosis of breast cancer, discussed the positive role of deep learning combined with multi-modal ultrasound imaging in the diagnosis, prediction and efficacy evaluation of breast cancer, and proposed the challenges that breast ultrasound may face in the future, with a view to providing clinical doctors with reference.
- breast cancer /
- ultrasound /
- diagnosis /
- deep learning

HTML全文

参考文献(50)

[1]	郑荣寿, 陈茹, 韩冰峰, 等. 2022年中国恶性肿瘤流行情况分析[J]. 中华肿瘤杂志, 2024, 46(3): 221-31. doi: 10.3760/cma.j.cn112152-20240119-00035
[2]	中国研究型医院学会乳腺专业委员会中国女性乳腺癌筛查指南制定专家组. 中国女性乳腺癌筛查指南(2022年版)[J]. 中国研究型医院, 2022, 9(2): 6-13.
[3]	王琪, 党晓智, 许磊, 等. 超声在乳腺癌筛查中的应用现状与未来[J]. 中华医学超声杂志(电子版), 2024, 21(4): 429-33.
[4]	陈静, 何之彦, 姚明华, 等. 比较分析常规超声及乳腺X线摄影对不同类型乳腺肿块的诊断价值[J]. 肿瘤影像学, 2021, 30(1): 1-5.
[5]	Nicosia L, Pesapane F, Bozzini AC, et al. Prediction of the malignancy of a breast lesion detected on breast ultrasound: radiomics applied to clinical practice[J]. Cancers, 2023, 15(3): 964. doi: 10.3390/cancers15030964
[6]	Wang YJ, Li YC, Song Y, et al. Comparison of ultrasound and mammography for early diagnosis of breast cancer among Chinese women with suspected breast lesions: a prospective trial[J]. Thorac Cancer, 2022, 13(22): 3145-51. doi: 10.1111/1759-7714.14666
[7]	Duffy SW, Tabar L, Vitak B, et al. The relative contributions of screen-detected in situ and invasive breast carcinomas in reducing mortality from the disease[J]. Eur J Cancer, 2003, 39(12): 1755-60. doi: 10.1016/S0959-8049(03)00259-4
[8]	Zhang WY, Wang SY, Wang YC, et al. Ultrasound-based radiomics nomogram for predicting axillary lymph node metastasis in early-stage breast cancer[J]. Radiol Med, 2024, 129(2): 211-21. doi: 10.1007/s11547-024-01768-0
[9]	李金凤. CDFI在乳腺导管扩张症与乳腺癌中的鉴别诊断价值[J]. 中国超声医学杂志, 2020, 36(1): 21-4. doi: 10.3969/j.issn.1002-0101.2020.01.007
[10]	Li X, Xu S, Hao LW, et al. Value of molybdenum target X-ray and high-frequency color Doppler flow imaging in early diagnosis of breast carcinoma: a comparative analysis[J]. Cancer Manag Res, 2023, 15: 1155-63. doi: 10.2147/CMAR.S412924
[11]	杨萌, 晋思琦, 朱庆莉, 等. 乳腺癌超声诊断技术的发展历程及协和经验[J]. 中国科学: 生命科学, 2021, 51(8): 1092-100.
[12]	Berg WA. BI-RADS 3 on screening breast ultrasound: what is it and what is the appropriate management?[J]. J Breast Imaging, 2021, 3(5): 527-38. doi: 10.1093/jbi/wbab060
[13]	He HL, Wu XJ, Jiang MJ, et al. Diagnostic accuracy of contrast-enhanced ultrasound synchronized with shear wave elastography in the differential diagnosis of benign and malignant breast lesions: a diagnostic test[J]. Gland Surg, 2023, 12(1): 54-66. doi: 10.21037/gs-22-684
[14]	Abedi M, Sahebi L, Eslami B, et al. Using a combination of superb microvascular imaging and other auxiliary ultrasound techniques to increase the accuracy of gray-scale ultrasound for breast masses[J]. BMC Cancer, 2024, 24(1): 224. doi: 10.1186/s12885-024-11981-9
[15]	Feng JP, Lu JH, Jin CC, et al. Diagnostic value of superb microvascular imaging in differentiating benign and malignant breast tumors: a systematic review and meta-analysis[J]. Diagnostics, 2022, 12(11): 2648. doi: 10.3390/diagnostics12112648
[16]	Zhong L, Wang C. Diagnostic accuracy of ultrasound superb microvascular imaging for breast tumor: a meta-analysis[J]. Med Ultrason, 2020, 22(3): 313-8. doi: 10.11152/mu-2460
[17]	Yuan YY, Xu M, Ren Y, et al. Clinical value of contrast-enhanced ultrasound in breast cancer diagnosis[J]. Comput Math Methods Med, 2022, 2022: 2017026.
[18]	Sigrist RMS, Liau J, Kaffas AE, et al. Ultrasound elastography: review of techniques and clinical applications[J]. Theranostics, 2017, 7(5): 1303-29. doi: 10.7150/thno.18650
[19]	Janu E, Krikavova L, Little J, et al. Prospective evaluation of contrast-enhanced ultrasound of breast BI-RADS 3-5 lesions[J]. BMC Med Imaging, 2020, 20(1): 66. doi: 10.1186/s12880-020-00467-2
[20]	Monzeglio O, Melissa VM, Rodolfi S, et al. Exploring the potential of contrast agents in breast cancer echography: current state and future directions[J]. J Ultrasound, 2023, 26(4): 749-56. doi: 10.1007/s40477-023-00809-0
[21]	田苗, 高小瞻, 马飞, 等. 超声分子成像在乳腺病灶良恶性质鉴别诊断中的应用[J]. 分子诊断与治疗杂志, 2021, 13(10): 1623-6. doi: 10.3969/j.issn.1674-6929.2021.10.018
[22]	Hu ZQ, Bachawal SV, Li XL, et al. Detection and characterization of sentinel lymph node by ultrasound molecular imaging with B7-H3-targeted microbubbles in orthotopic breast cancer model in mice[J]. Mol Imaging Biol, 2022, 24(2): 333-40. doi: 10.1007/s11307-021-01680-3
[23]	Zhang L, Dong YJ, Zhou JQ, et al. Similar reproducibility for strain and shear wave elastography in breast mass evaluation: a prospective study using the same ultrasound system[J]. Ultrasound Med Biol, 2020, 46(4): 981-91. doi: 10.1016/j.ultrasmedbio.2019.12.017
[24]	Wu HY, Wang C, An Q, et al. Comparing the accuracy of shear wave elastography and strain elastography in the diagnosis of breast tumors: a systematic review and meta-analysis[J]. Medicine, 2022, 101(44): e31526. doi: 10.1097/MD.0000000000031526
[25]	Li JN, Liu YC, Li YB, et al. Comparison of diagnostic potential of shear wave elastography between breast mass lesions and non-mass-like lesions[J]. Eur J Radiol, 2023, 158: 110609. doi: 10.1016/j.ejrad.2022.110609
[26]	Golatta M, Pfob A, Büsch C, et al. The potential of shear wave elastography to reduce unnecessary biopsies in breast cancer diagnosis: an international, diagnostic, multicenter trial[J]. Ultraschall Med, 2023, 44(2): 162-8. doi: 10.1055/a-1543-6156
[27]	Togawa R, Riedel F, Feisst M, et al. Shear-wave elastography as a supplementary tool for axillary staging in patients undergoing breast cancer diagnosis[J]. Insights Imaging, 2024, 15(1): 196. doi: 10.1186/s13244-024-01747-z
[28]	Dan Q, Zheng TT, Liu L, et al. Ultrasound for breast cancer screening in resource-limited settings: current practice and future directions[J]. Cancers, 2023, 15(7): 2112. doi: 10.3390/cancers15072112
[29]	唐燕, 谷颖. 超声筛查乳腺恶性非肿块型病变的研究现状[J]. 中华妇幼临床医学杂志: 电子版, 2022, 18(4): 379-86. doi: 10.3877/cma.j.issn.1673-5250.2022.04.002
[30]	Spear GG, Mendelson EB. Automated breast ultrasound: supplemental screening for average-risk women with dense breasts[J]. Clin Imaging, 2021, 76: 15-25. doi: 10.1016/j.clinimag.2020.12.007
[31]	Ren WH, Yan HJ, Zhao XL, et al. Integration of handheld ultrasound or automated breast ultrasound among women with negative mammographic screening findings: a multi-center population- based study in China[J]. Acad Radiol, 2023, 30(Suppl 2): S114-26.
[32]	Huppe AI, Inciardi MF, Aripoli AM, et al. Pearls and pitfalls of interpretation of automated breast US[J]. Radiographics, 2023, 43 (10): e230023. doi: 10.1148/rg.230023
[33]	Yoon JH, Kim EK. Deep learning-based artificial intelligence for mammography[J]. Korean J Radiol, 2021, 22(8): 1225-39. doi: 10.3348/kjr.2020.1210
[34]	Balkenende L, Teuwen J, Mann RM. Application of deep learning in breast cancer imaging[J]. Semin Nucl Med, 2022, 52(5): 584-96. doi: 10.1053/j.semnuclmed.2022.02.003
[35]	Xiang HL, Wang X, Xu M, et al. Deep learning-assisted diagnosis of breast lesions on US images: a multivendor, multicenter study[J]. Radiol Artif Intell, 2023, 5(5): e220185. doi: 10.1148/ryai.220185
[36]	Afrin H, Larson NB, Fatemi M, et al. Deep learning in different ultrasound methods for breast cancer, from diagnosis to prognosis: current trends, challenges, and an analysis[J]. Cancers, 2023, 15 (12): 3139. doi: 10.3390/cancers15123139
[37]	钟仕维, 魏达友, 巫朝君, 等. 深度学习超声组学鉴别肿块型乳腺炎和乳腺癌的应用价值[J]. 中国超声医学杂志, 2023, 39(12): 1341-4. doi: 10.3969/j.issn.1002-0101.2023.12.006
[38]	Misra S, Yoon C, Kim KJ, et al. Deep learning-based multimodal fusion network for segmentation and classification of breast cancers using B- mode and elastography ultrasound images[J]. Bioeng Transl Med, 2022, 8(6): e10480.
[39]	Gong X, Zhao X, Fan L, et al. BUS-net: a bimodal ultrasound network for breast cancer diagnosis[J]. Int J Mach Learn Cybern, 2022, 13(11): 3311-28. doi: 10.1007/s13042-022-01596-6
[40]	Yu TF, He W, Gan CG, et al. Deep learning applied to two-dimensional color Doppler flow imaging ultrasound images significantly improves diagnostic performance in the classification of breast masses: a multicenter study[J]. Chin Med J, 2021, 134(4): 415-24. doi: 10.1097/CM9.0000000000001329
[41]	王彤, 何萍, 苏畅, 等. 计算机辅助多模态融合超声诊断乳腺良恶性肿瘤[J]. 中国医学影像技术, 2021, 37(8): 1210-3.
[42]	Zhou BY, Wang LF, Yin HH, et al. Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: a prospective and multicentre study[J]. EBioMedicine, 2021, 74: 103684. doi: 10.1016/j.ebiom.2021.103684
[43]	Liu WY, Wang DY, Liu L, et al. Assessing the influence of B-US, CDFI, SE, and patient age on predicting molecular subtypes in breast lesions using deep learning algorithms[J]. J Ultrasound Med, 2024, 43(8): 1375-88. doi: 10.1002/jum.16460
[44]	于丹阳, 吴桐, 荆慧, 等. 乳腺癌多模态超声评估新辅助化疗后腋窝淋巴结病理状态的研究[J]. 中华超声影像学杂志, 2022, 31(8): 685-90. doi: 10.3760/cma.j.cn131148-20211226-00962
[45]	Zheng XY, Yao Z, Huang YN, et al. Deep learning radiomics can predict axillary lymph node status in early- stage breast cancer[J]. Nat Commun, 2020, 11(1): 1236. doi: 10.1038/s41467-020-15027-z
[46]	Jiang M, Li CL, Luo XM, et al. Radiomics model based on shear-wave elastography in the assessment of axillary lymph node status in early-stage breast cancer[J]. Eur Radiol, 2022, 32(4): 2313-25. doi: 10.1007/s00330-021-08330-w
[47]	中国抗癌协会乳腺癌专业委员会, 中华医学会肿瘤学分会乳腺肿瘤学组, 邵志敏. 中国抗癌协会乳腺癌诊治指南与规范(2024年版)[J]. 中国癌症杂志, 2023, 33(12): 1092-186.
[48]	刘锦辉, 冷晓玲. 多模态超声联合深度学习对乳腺癌新辅助化疗疗效及侵袭性评价的研究进展[J]. 分子影像学杂志, 2021, 44(6): 1034-40. doi: 10.12122/j.issn.1674-4500.2021.06.30
[49]	Gu JH, Zhong X, Fang CY, et al. Deep learning of multimodal ultrasound: stratifying the response to neoadjuvant chemotherapy in breast cancer before treatment[J]. Oncologist, 2024, 29(2): e187-97. doi: 10.1093/oncolo/oyad227
[50]	Huang JX, Shi J, Ding SS, et al. Deep learning model based on dual- modal ultrasound and molecular data for predicting response to neoadjuvant chemotherapy in breast cancer[J]. Acad Radiol, 2023, 30(Suppl 2): S50-61.