多模态乳腺肿瘤图像特征提取与分级诊断的研究进展

doi:10.3969/j.issn.1009-976X.2020.06.021

摘要/Abstract

摘要： 乳腺癌是女性最常见的恶性肿瘤之一。影像学检查是诊断乳腺肿瘤的重要方法,其主要包括超声、钼靶、核磁共振成像（MRI）检查等。单一医学影像技术存在诸多的局限性,使用多种影像学技术联合诊断能提高分级诊断效率。临床亟需一个高度智能的乳腺肿瘤诊断系统,有望帮助临床医生提高整体诊断效率,降低漏诊误诊率。而图像特征提取是乳腺肿瘤诊断系统研制中的第一步,也是最关键的一步。本文回顾了超声、钼靶和MRI之间联合使用对乳腺癌进行分级诊断的研究方法,就多模态乳腺肿瘤图像特征提取与分级诊断的研究进展进行综述。

关键词: 超声, 钼靶, 核核磁共振, 乳腺肿瘤, 图像特征提取

Abstract: Breast cancer isoneof the most common malignant tumoraffecting women in recent years. Imaging examination is an important method for diagnosing breast tumors. It mainly includes ultrasound, mammography, CT, magnetic resonance imaging （MRI） and so on. The use of a single technique has limitations, and the combined use of multiple imaging techniques can improve the efficiency of graded diagnosis. At this stage, an artificial intelligence breast cancer diagnosis system is expected to help clinicians improve the overall diagnosis efficiency and reduce the rate of missed diagnosis. The most important step in developing an accurate and efficient breast tumor diagnosis system is image feature extraction. This article discusses the practical value of the combined use of ultrasound （US）,mammography and magnetic resonance imaging （MRI） for the classification diagnosis of breast cancer. This paper reviews the research advances in feature extraction and hierarchical diagnosis of multimodal breast tumor images.

Key words: ultrasound, mammography, magnetic resonance imaging, breast tumor, imagefeature extraction

中图分类号:

R445

陈继鑫, 孔恒. 多模态乳腺肿瘤图像特征提取与分级诊断的研究进展[J]. 岭南现代临床外科, 2020, 20(06): 789-795.

CHEN Ji-xin, KONG Heng. Research progress of multimodal image feature extraction and classification diagnosis for breast tumor[J]. Lingnan Modern Clinics In Surgery, 2020, 20(06): 789-795.

参考文献

[1] 邵志敏,李俊杰. 2015年St. Gallen国际乳腺癌研讨会乳腺癌新的诊疗理念[J/CD]. 中华乳腺病杂志(电子版),2015,9(2):73-77.
[2] Yang W, Dempsey PJ. Diagnostic breast ultrasound: current status and futuredirections [J]. Radiol Clin North Am, 2007, 45(5):845-vii.
[3] 张瑾,陈薇,刘蕾. 2017年NCCN乳腺癌筛查和诊断临床实践指南(第1版)更新与解读[J]. 中国全科医学,2017, 20(24):2939-2943.
[4] Oeffinger KC, Fontham ET, Etzioni R, et al.Breast Cancer Screening for Women at Average Risk: 2015 Guideline Update From the American Cancer Society[J]. JAMA, 2015, 314(15):1599-1614.
[5] 隋广平,梁冬梅,王春玥,等. 早期乳腺癌诊断中多模态影像技术的应用分析[J]. 影像研究与医学应用,2019,3(7): 99-100.
[6] Shao H, Li B, Zhang X, et al.Comparison of the diagnostic efficiency for breast cancer in Chinese women using mammography, ultrasound, MRI, and different combinations of these imaging modalities[J]. J Xray Sci Technol, 2013, 21(2): 283-292.
[7] Novak D.Indications for and comparative diagnostic value of combined ultrasound and X-ray mammography[J]. Eur J Radiol, 1983, 3(Suppl 1):299-302.
[8] 林欢,林汉生,梁红. 超声和钼靶X线联合诊断2cm以内乳腺癌的meta分析[J]. 南方医科大学学报, 2013, 33(11): 1699-1703.
[9] Giuliano V, Giuliano C.Improved breast cancer detection in asymptomatic women using 3D-automated breast ultrasound in mammographically dense breasts[J]. Clin Imaging, 2013, 37(3):480-486.
[10] Emons J, Wunderle M, Hartmann A, et al.Initial clinical results with a fusion prototype for mammography and three-dimensional ultrasound with a standard mammography system and a standard ultrasound probe[J]. Acta Radiol, 2018, 59(12):1406-1413.
[11] 卢向军. 乳腺癌全数字化X线摄影表现与病理、彩色多普勒超声的对比研究[D]. 浙江大学,2011.
[12] Boroczky L, Simpson M, Abe H, Drysdale J.Observer study of a prototype clinical decision support system for breast cancer diagnosis using dynamic contrast-enhanced MRI[J]. AJR Am J Roentgenol, 2013, 200(2):277-283.
[13] 马财,张文馨,徐蕊,等. 彩色多普勒超声与核磁共振增强扫描联合应用在乳腺结节病灶中的诊断价值[J]. 中国CT和MRI杂志,2017,15(8): 77-79.
[14] Pan Q, Ji J.Diagnostic value of ultrasound combined with magnetic resonance imaging in different stages of breast cancer[J].Oncol Lett, 2019, 17(1):209-214.
[15] Nakashima K, Uematsu T, Harada TL, et al.MRI-detected breast lesions: clinical implications and evaluation based on MRI/ultrasonography fusion technology[J]. Jpn J Radiol, 2019, 37(10):685-693.
[16] 周美亚,赵金丽,曹亮,等. MRI检查对乳腺X线摄影中非对称性致密和/或结构扭曲的诊断价值[J]. 医学影像学杂志,2018, 28(1):66-68,72.
[17] 雷焦,章园. 核核磁共振和钼靶X线联合对乳腺癌诊断的Meta分析[J]. 中国数字医学, 2016,11(12): 1673-7571.
[18] Shao H, Li B, Zhang X, et al.Comparison of the diagnostic efficiency for breast cancer in Chinese women using mammography, ultrasound, MRI, and different combinations of these imaging modalities[J]. J Xray Sci Technol, 2013, 21(2):283-292.
[19] Vyborny CJ, Giger ML.Computer vision and artificial intelligence in mammography[J]. AJR Am J Roentgenol, 1994, 162(3): 699-708.
[20] Gillies RJ, Anderson AR, Gatenby RA, et al.The biology underlying molecular imaging in oncology: from genome to anatome and back again[J]. Clin Radiol, 2010, 65(7): 517-521.
[21] Lambin P, Rios-Velazquez E, Leijenaar R, et al.Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Ca, 2012, 48(4):441-446.
[22] Gillies RJ, Kinahan PE, Hricak H.Radiomics:images are more than pictures, they are data[J]. Radiology, 2015, 278(2):563-577.
[23] Zhang L, Chen B, Liu X, et al.Quantitative biomarkers for prediction of epidermal growth factor receptor mutation in nonsmall cell lung cancer[J]. Transl Oncol, 2018, 11(1):94-101.
[24] 王敏, 宋彬, 黄子星, 等. 大数据时代的精准影像医学: 放射组学[J]. 中国普外基础与临床杂志, 2016, 23(6): 752-755.
[25] Parekh V, Jacobs MA.Radiomics: a new application from established techniques[J]. Expert Rev Precis Med Drug Dev, 2016, 1(2): 207-226.
[26] Melendez J, Sánchez CI, van Ginneken B, et al. Improving mass candidate detection in mammograms via feature maxima propagation and local feature selection[J]. Med Phys, 2014, 41(8): 081904.
[27] Sedgwick E.The breast ultrasound lexicon: breast imaging reporting and data system (BI-RADS)[J]. Semin Roentgenol, 2011, 46(4):245-251.
[28] DeSantis CE, Ma J, Goding Sauer A, et al. Breast cancer statistics, 2017, racial disparity in mortality by state[J]. CA Cancer J Clin, 2017, 67(6):439-448.