2020 , Vol. 16 >Issue 03: 368 - 372
DOI: https://doi.org/10.3877/cma.j.issn.1673-5250.2020.03.018
人工智能乳腺超声对乳腺癌的诊断及预后预测价值
收稿日期: 2020-01-03
修回日期: 2020-05-05
网络出版日期: 2020-06-01
Values of artificial intelligence breast ultrasound in diagnosis and prognosis assessment of breast carcinoma
Received date: 2020-01-03
Revised date: 2020-05-05
Online published: 2020-06-01
Supported by
National Key Research & Development Project(2017YFC0113905)
人工智能(AI)乳腺超声将AI技术应用于乳腺癌的诊断及预后预测，不仅可以为超声科医师节省时间，还可以弥补由于初学者经验和技能不足导致的误诊及漏诊。现代医学影像学是AI在临床中发挥重要作用的最早领域之一。AI乳腺超声采集乳腺超声图像(BUI)，作为一种横断面成像技术，应用计算机辅助设计(CAD)系统，对乳腺癌进行计算机辅助诊断，可提高临床对乳腺癌诊断的准确性。目前，CAD系统可帮助超声科医师更有效地实现对乳腺癌的早期筛查。AI乳腺超声可对乳腺癌病灶进行自动识别及分类，甚至模拟临床医师对乳腺癌进行诊断和预后评估。笔者拟就AI乳腺超声对乳腺癌的诊断及预后预测价值的最新研究进展，进行阐述。
谢川博 , 满琴 , 罗红 . 人工智能乳腺超声对乳腺癌的诊断及预后预测价值[J]. 中华妇幼临床医学杂志(电子版), 2020 , 16(03) : 368 -372 . DOI: 10.3877/cma.j.issn.1673-5250.2020.03.018
The application of artificial intelligence (AI) breast ultrasonography for diagnosis breast carcinoma and prognosis prediction of breast cancer treatment can not only save time for ultrasound doctors, but also reduce the misdiagnosis and miss diagnosis cause by the lack of experience and skills of beginners. Modern medical imaging is one of the earliest areas where AI plays an important role in clinic. As a cross-sectional imaging technology, breast ultrasound image (BUI) collected by AI breast ultrasonography uses a computer-aided design (CAD) system to perform computer-aided diagnosis of breast cancer, and it can improve the accuracy of clinical diagnosis of breast cancer. Up to now, the intelligent CAD system can help ultrasound doctors more effectively screening early breast cancer. AI breast ultrasound can automatically identify and classify breast cancer lesions, and even simulate clinicians in diagnosis and prognosis prediction of patients with breast cancer. This article focuses on the latest research progresses of diagnosis and prognosis prediction of breast cancer by AI breast ultrasound.
| [1] | Siegel R, DeSantis C, Jemal A. Colorectal cancer statistics, 2014 [J]. CA Cancer J Clin, 2014, 64(2): 104-117. DOI: 10.3322/caac.21220. |
| [2] | Ferlay J, Soerjomataram I, Dikshit R, et al. Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012 [J]. Int J Cancer, 2015, 136(5): E359-E386. DOI: 10.1002/ijc.29210. |
| [3] | Wu GG, Zhou LQ, Xu JW, et al. Artificial intelligence in breast ultrasound [J]. World J Radiol, 2019, 11(2): 19. DOI: 10.4329/wjr.v11.i2.19. |
| [4] | Sepandi M, Taghdir M, Rezaianzadeh A, et al. Assessing breast cancer risk with an artificial neural network [J]. Asian Pac J Cancer Prev, 2018, 19(4): 1017. DOI: 10.22034/APJCP.2018.19.4.1017. |
| [5] | Zain NM, Chelliah KK. Breast imaging using electrical impedance tomography: correlation of quantitative assessment with visual interpretation [J]. Asian Pac J Cancer Prev, 2014, 15(3): 1327-1331. DOI: 10.7314/APJCP.2014.15.3.1327. |
| [6] | Shen WC, Chang RF, Moon WK, et al. Breast ultrasound computer-aided diagnosis using BI-RADS features [J]. Acad Radiol, 2007, 14(8): 928-939. DOI: 10.1016/j.acra.2007.04.016. |
| [7] | EI-Naqa I, Yang Y, Wernick MN, et al. A support vector machine approach for detection of microcalcifications [J]. IEEE Trans Med Imaging, 2002, 21(12): 1552-1563. DOI: 10.1109/TMI.2002.806569. |
| [8] | Marmot MG, Altman DG, Cameron DA, et al. The benefits and harms of breast cancer screening: an independent review [J]. Br J Cancer, 2013, 108(11): 2205-2240. DOI: 10.1038/bjc.2013.177. |
| [9] | Ciritsis A, Rossi C, Eberhard M, et al. Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making [J]. Eur Radiol, 2019, 29(10): 5458-5468. DOI: 10.1007/s00330-019-06118-7. |
| [10] | Fujioka T, Kubota K, Mori M, et al. Distinction between benign and malignant breast masses at breast ultrasound using deep learning method with convolutional neural network [J]. Jap J Radiol, 2019, 37(6): 466-472. DOI: 10.1007/s11604-019-00831-5. |
| [11] | 吴英，罗良平，许波，等. 基于迁移学习的乳腺肿瘤超声图像智能分类诊断[J]. 中国医学影像技术，2019, 35(3): 42-45. DOI: 10.13929/j.1003-3289.201807052. |
| [12] | Han S, Kang HK, Jeong JY, et al. A deep learning framework for supporting the classification of breast lesions in ultrasound images [J]. Phys Med Biol, 2017, 62(19): 7714-7728. DOI: 10.1088/1361-6560/aa82ec. |
| [13] | Lo CM, Chang RF. Intelligent diagnosis of breast cancer based on quantitative B-mode and elastography features//Artificial intelligence in decision support systems for diagnosis in medical imaging [M]. Switzerland: Springer, Cham, 2018: 165-191. DOI: 10.1007/978-3-319-68843-5. |
| [14] | Moon WK, Chang SC, Huang CS, et al. Breast tumor classification using fuzzy clustering for breast elastography [J]. Ultrasound Med Biol, 2011, 37(5): 700-708. DOI: 10.1016/j.ultrasmedbio.2011.02.003. |
| [15] | Chang SC, Lai YC, Chou YH, et al. Breast elastography diagnosis based on dynamic sequence features [J]. Med Phys, 2013, 40(2): 022905. DOI: 10.1118/1.4788652. |
| [16] | Marcomini K, Fleury E, Oliveira V, et al. Evaluation of a computer-aided diagnosis system in the classification of lesions in breast strain elastography imaging [J]. Bioengineering (Basel), 2018, 5(3): 62. DOI: 10.3390/bioengineering5030062. |
| [17] | Zhang Q, Song S, Xiao Y, et al. Dual-mode artificially-intelligent diagnosis of breast tumours in shear-wave elastography and B-mode ultrasound using deep polynomial networks [J]. Med Eng Phys, 2019, 64(1): 1-6. DOI: 10.1016/j.medengphy.2018.12.005. |
| [18] | Kelly KM, Dean J, Comulada WS, et al. Breast cancer detection using automated whole breast ultrasound and mammography in radiographically dense breasts [J]. Eur Radiol, 2010, 20(3): 734-742. DOI: 10.1007/s00330-009-1588-y. |
| [19] | Moon WK, Shen YW, Huang CS, et al. Computer-aided diagnosis for the classification of breast masses in automated whole breast ultrasound images [J]. Ultrasound Med Biol, 2011, 37(4): 539-548. DOI: 10.1016/j.ultrasmedbio.2011.01.006. |
| [20] | Lo C, Shen YW, Huang CS, et al. Computer-aided multiview tumor detection for automated whole breast ultrasound [J]. Ultrason Imaging, 2014, 36(1): 3-17. DOI: 10.1177/0161734613507240. |
| [21] | Chiang TC, Huang YS, Chen RT, et al. Tumor detection in automated breast ultrasound using 3-D CNN and prioritized candidate aggregation [J]. IEEE Trans Med Imaging, 2019, 38(1): 240-249. DOI: 10.1109/tmi.2018.2860257. |
| [22] | Tran WT, Jerzak K, Lu FI, et al. Personalized breast cancer treatments using artificial intelligence in radiomics and pathomics [J]. J Med Imaging Radiat Sci, 2019, 50(4 Suppl 2): S32-S41. DOI: 10.1016/j.jmir.2019.07.010. |
| [23] | Nasief HG, Rosado-Mendez IM, Zagzebski JA, et al. A quantitative ultrasound-based multi-parameter classifier for breast masses [J]. Ultrasound Med Biol, 2019, 45(7): 1603-1616. DOI: 10.1016/j.ultrasmedbio.2019.02.025. |
| [24] | Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data [J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169. |
| [25] | Klimonda Z, Karwat P, Dobruch-Sobczak K, et al. Breast-lesions characterization using quantitative ultrasound features of peritumoral tissue [J]. Sci Rep, 2019, 9(1): 7963. DOI: 10.1038/s41598-019-44376-z. |
| [26] | Sannachi L, Gangeh M, Tadayyon H, et al. Breast cancer treatment response monitoring using quantitative ultrasound and texture analysis: comparative analysis of analytical models [J]. Transl Oncol, 2019, 12(10): 1271-1281. DOI: 10.1016/j.tranon.2019.06.004. |
| [27] | Hsu SM, Kuo WH, Kuo FC, et al. Breast tumor classification using different features of quantitative ultrasound parametric images [J]. Int J Comput Assist Radiol Surg, 2019, 14(4): 623-633. DOI: 10.1007/s11548-018-01908-8. |
| [28] | Sadeghi-Naini A, Sannachi L, Pritchard K, et al. Early prediction of therapy responses and outcomes in breast cancer patients using quantitative ultrasound spectral texture [J]. Oncotarget, 2014, 5(11): 3497-3511. DOI: 10.18632/oncotarget.1950. |
| [29] | Tadayyon H, Sadeghi-Naini A, Sannachi L, et al. Quantitative ultrasound assessment of tumor responses to chemotherapy using a time-integrated multi-parameter approach [J]. J Acoust Soc Am, 2014, 136(4): 2123-2123. DOI: 10.1121/1.4899647. |
| [30] | Lassau N, Estienne T, de Vomecourt P, et al. Five simultaneous artificial intelligence data challenges on ultrasound, CT, and MRI [J]. Diagn Intervent Imaging, 2019, 100(4): 199-209. DOI: 10.1016/j.diii.2019.02.001. |
/
| 〈 |
|
〉 |