|Table of Contents|

The application of deep learning combination with X-ray mammography and ultrasound in the breast carcinoma examination

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2019 01
Page:
144-149
Research Field:
Publishing date:

Info

Title:
The application of deep learning combination with X-ray mammography and ultrasound in the breast carcinoma examination
Author(s):
Qu WeihuaTang Zhen
Department of Radiology,South Branch Hospital of Sixth People's Hospital of Shanghai Jiaotong University,Shanghai 201499,China.
Keywords:
deep learningneural networksX-ray mammographyultrasoundbreast lesions
PACS:
R737.9
DOI:
10.3969/j.issn.1672-4992.2019.01.037
Abstract:
Objective:To discuss the performance of deep learning in differential diagnosis of breast benign and malignant lesions on X-ray mammography and ultrasound imaging data.Methods:100 cases of mammary gland disease in patients with X-ray mammography and ultrasound data using back propagation neural network were analyzed,and the random samples of 50 cases as the training sample,composition training set,the rest of sample test set.The model of artificial neural network was established and the diagnostic results of the model was analysed.Results:100 cases of patients,breast malignant lesions were proved by surgery and pathology in 62 cases,other 38 cases were breast benign tumors or tumor-like lesions.The specific degrees,the sensitivity and accuracy are 89.5%,87.1% and 88.0% respectively in X-ray mammography,and 86.8%,83.9% and 85.0% in ultrasonography.By comparison,the specific degrees,the sensitivity and accuracy are 95.5%,96.4% and 96.0% respectively in neural networks,which was significantly higher than X-ray mammography and ultrasonography,which was highly significant difference.No obvious difference was found between X-ray mammography and ultrasonography.Conclusion:Deep learning based on the artificial neural network combined with X-ray mammography and ultrasonography has certain application value in differential diagnosis of breast benign and malignant lesions.

References:

[1]Shao Zhenzhen,Li Junnan,Zhao Yumei,et al.Influencing factors analysis on mammography versus ultrasonography in detecting early stage breast cancer and epidemiological characteristics by Logistic regression[J].Chinese Journal of Radiology,2017,51(2):127-131.[邵真真,李军楠,赵玉梅,等.影响乳腺X线摄影和超声检出早期乳腺癌的流行病学相关因素分析[J].中华放射学杂志,2017,51(2):127-131.]
[2]Chen Xin,Huang Huan,Jin Rui,et al.Comparator analysis of mammographic features between invasive lobular carcinoma and invasive ductal carcinoma[J].Journal of Practical Radiology,2015,31(9):1435-1438.[陈欣,黄环,晋瑞,等.乳腺浸润性小叶癌与浸润性导管癌X线表现的对比分析[J].实用放射学杂志,2015,31(9):1435-1438.]
[3]Liu Shujing,Yang Guang,Li Yanan,et al.The analysis of X-ray manifestations and clinical pathology in triple negative breast cancer[J].Journal of Practical Radiology,2016,32(7):1043-1047.[刘淑敬,杨光,李亚男,等.三阴性乳腺癌X线征象及临床病理分析[J].实用放射学杂志,2016,32(7):1043-1047.]
[4]Zhao Hong,Zheng Suisheng,Jin Jing,et al.Value of mammography X-ray images in diagnosing breast diseases[J].Chinese Journal of Medical Imaging,2012,20(7):511-514.[赵红,郑穗生,金晶,等.钼靶X线影像对乳腺疾病的诊断价值[J].中国医学影像学杂志,2012,20(7):511-514.]
[5]Chen Jian,Tian Baoguo,Run Yunlong,et al.A tumor diagnostic method based on neural network[J].Journal of Medical Imaging,2009,19(8):978-980.[陈健,田宝国,闰云龙,等.基于人工神经网络的肿瘤诊断方法研究[J].医学影像学杂志,2009,19(8):978-980.]
[6]Matsuki Y,Nakamura K,Watanabe H,et al.Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT:Evaluation with receiver operating characteristic analysis[J].AJR,2002,178:657-663.
[7]Chen Hui,Wang Xiaohua,Zhou Xinhua,et al.Preliminary application of neural networks in differentiating benign from malignant solitary pulmonary nodule on HRCT images[J].Beijing Biomedical Engineering,2005,24(6):436-439.[陈卉,王晓华,周新华,等.神经网络在诊断HRCT上孤立肺结节良恶性中的初步应用[J].北京生物医学工程,2005,24(6):436-439.]
[8]Wang Wei,Ma Binlin.The value of the combination of mammography and ultrasonography in detection of the 146 cases with stage Ⅰ breast cancer[J].Journal of Xinjiang Medical University,2006,29(6):505-508.[王薇,马斌林.146例Ⅰ期乳腺癌的钼靶、B超与病理对照分析[J].新疆医科大学学报,2006,29(6):505-508.]
[9]Zhang Wenge,Wu Zening,Lu Hongbo.Improvement and application to BP neural network[J].Henan Science,2003,21(2):202-206.[张文鸽,吴泽宁,逯洪波.BP神经网络的改进及其应用[J].河南科学,2003,21(2):202-206.]
[10]Suzuki K.A supervised' lesion-enhancement' filter by use of a massive-training artificial neural network(MTANN) in computer-aided diagnosis(CAD) physics in medicine and biology[J].2009,54(18):S31-S45
[11]Suzuki K,Armato SG,Li F,et al.Massive training artificial neural network(MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography[J].Medical Physics,2003,30(7):1602-1617.
[12]Dayhof JE,Deleo JM.Artificial neural networks[J].Cancer,2001,91(8):1615-1634
[13]Wang Lijuan,Liu Yihui,Liu Qiang,et al.Study using neural networks improve the diagnostic accuracy rate of magnetic resonance spectroscopy in hepatocelluar carcinoma[J].China Journal of Bioinformatics,2010,8(2):171-174.[王丽娟,刘毅慧,刘强,等.神经网络提高肝细胞癌磁共振波谱诊断正确率[J].生物信息学,2010,8(2):171-174.]
[14]Makris GM,Pouliakis A,Siristatidis C,et al.Image analysis and multi-layer perceptron artificial neural networks for the discrimination between benign and malignant endometrial lesions[J].Diagn Cytopathol,2017,45(3):202-211.
[15]Yin Niandong.Design of BP neural network in engineering application[J].Information Technology,2003,27(6):18-20.[尹念东.BP神经网络的应用设计,信息技术,2003,27(6):18-20.]
[16]Raua HH,Hsu CY,Lin YA,et al.Development of a web-based liver cancer prediction model for type Ⅱ diabetes patients by using an artificial neural network[J].Comput Methods Programs Biomed,2016,125(1):58-65.

Memo

Memo:
上海市卫生与计划生育委员会基金(编号:201440564)
Last Update: 2018-11-30