Breast Tumor Classification Based on Bilateral TIC Quantitative Features

doi:10.12068/j.issn.1005-3026.2019.04.004

Abstract

Abstract: An effective bilateral quantitative analyzing method for breast tumor classification was proposed based on the time intensity curve(TIC) of dynamic contrast enhanced magnetic resonance imaging(DCE-MRI). The breast lesion region in DCE-MRI images was extracted using three-dimensional region growing algorithm， and 29 features were extracted based on the TIC curves of the ROI corresponding to the lesion area and its contralateral mammary gland. The two-sided difference feature parameters were defined， and 7 effective features after screening by the sequential floating forward selection(SFFS) method were obtained. The support vector machines(SVM) was used for classification， and the classification results were obtained on the basis of cross-validation method for feature training. A hundred and twelve retrospective cases(67 benign， 45 malignant) were chosen randomly， and the average classification accuracy is 88.39%.The experimental results showed that this method has a high accuracy rate for breast tumor classification， and is of great value for assisting doctors in differential diagnosis of breast tumor.

Key words: breast tumor, DCE-MRI, TIC curve, bilateral quantitative analysis, tumor classification

CLC Number:

TP391

SUN Hang， LI Hong， LIU Si-qi， ZHANG Wei. Breast Tumor Classification Based on Bilateral TIC Quantitative Features[J]. Journal of Northeastern University Natural Science, 2019, 40(4): 473-477.

References

[1]Jia L.Study on the application of MRI multi-sequence scan in the diagnosis and treatment of cervical carcinoma［J］.Chinese Journal of CT & MRI，2017，15(11):85-88.
[2]Tong Q，Zhang B，Ming L I.MR multiple sequence imaging optimization study in diagnosing breast tumor［J］.Chinese Journal of CT& MRI，2017，15(4):80-84.
[3]Yin J，Yang J，Lu H，et al.Quantitative discrimination between invasive ductal carcinomas and benign lesions based on semi-automatic analysis of time intensity curves from breast dynamic contrast enhanced MRI［J］.Journal of Experimental & Clinical Cancer Research，2015，34(1):1-10.
[4]Huang N，Deng D Q，Bin L I，et al.Value of time-signal intensity curve and ADC values in the diagnosis of breast diseases［J］.Hainan Medical Journal，2016，27(10):1563-1566.
[5]Yang S N，Li F J，Chen J M，et al.Kinetic curve type assessment for classification of breast lesions using dynamic contrast-enhanced MR imaging［J］.Plos One，2016，11(4):e0152827.
[6]Huang Y H，Guo Y M.Comparative study of time-intensity curve and K~(trans) value of dynamic contrast-enhanced MRI in the diagnosis of prostate cancer［J］.Radiologic Practice，2016，31(6):511-515.
[7]Aribal E，Asodov R.Multiparametric breast MRI with 3T:effectivity of combination of contrast enhanced MRI， DWI and 1H signal voxel spectroscopy in differentiation of breast tumors［J］.European Journal of Radiology，2016， 85(5): 979-986.
[8]Hompland T，Ellingsen C，Ovreb K M，et al.Interstitial fluid pressure and associated lymph node metastasis revealed in tumors by dynamic contrast-enhanced MRI［J］.Cancer Research，2012，72(19):4899-4908.
[9]Preim U，Glaber S，Preim B，et al.Computer-aided diagnosis in breast DCE-MRI:quantification of the heterogeneity of breast lesions［J］.European Journal of Radiology，2012，81(7):1532-1538.
[10]蔡毓琪，周研，吴先衡，等.MRI 动态增强扫描联合DWI 鉴别乳腺良恶性肿瘤的应用价值［J］.中国中西医结合影像学杂志， 2017， 15(3): 333-335.(Cai Yu-qi，Zhou Yan，Wu Xian-heng，et al.The value of dynamic enhanced MRI combined with DWI in diagnosis of benign and malignant breast tumors［J］.Chinese Imaging Journal of Integrated Traditional and Western Medicine，2017，15(3):333-335.)
[11]彭武祥，李一辉.MRI动态增强对早期乳腺癌的诊断价值［J］.现代中西医结合杂志， 2014， 23(24): 2719-2721.(Peng Wu-xiang，Li Yi-hui.The value of dynamic enhanced MRI in the diagnosis of early breast cancer［J］.Modern Journal of Integrated Traditional Chinese and Western Medicine，2014，23(24):2719-2721.)
[12]Hetta W.Role of diffusion weighted images combined with breast MRI in improving the detection and differentiation of breast lesions［J］.Egyptian Journal of Radiology & Nuclear Medicine，2015，46(1):259-270.
[13]Fusco R，Marzo M D，Sansone C，et al.Breast DCE-MRI:lesion classification using dynamic and morphological features by means of a multiple classifier system［J］.European Radiology Experimental， 2017，1(1):10-15.
[14]Wang X，Li L，Xu W，et al.Improving performance of computer-aided detection of masses by incorporating bilateral mammographic density asymmetry:an assessment.［J］.Academic Radiology， 2012，19(3):303-310.(上接第472页)
[7]赵晓煜，黄小原，曹忠鹏，等.基于顾客交易数据的协同过滤推荐方法［J］.东北大学学报(自然科学版)，2009，30(12):1792-1795.(Zhao Xiao-Yu，Huang Xiao-Yuan，Cao Zhong-Peng，et al.Improved collaborative filtering recommendation based on customers′ transaction data［J］.Journal of Northeastern University(Natural Science)，2009，30(12):1792-1795.)
[8]Sarwar B，Karypis G，Konstan J，et al.Item-based collaborative filtering recommendation algorithms［C］// International Conference on World Wide Web.Hong Kong，2001:285-295.
[9]Goldberg D，Nichols D，Oki B M，et al.Using collaborative filtering to weave an information tapestry［J］.Communications of the ACM，1992，35(12):61-70.
[10]Liu L M，Zhang P X，Lin L，et al.Research of data sparsity based on collaborative filtering algorithm［J］.Applied Mechanics and Materials，2014，462(463):856-860.
[11]潘一腾，何发智，于海平.一种基于信任关系隐含相似度的社会化推荐算法［J］.计算机学报， 2016， 39(175):1-19.(Pan Yi-teng，He Fa-zhi，Yu Hai-ping.Social recommendation algorithm using implicit similarity in trust［J］.Chinese Journal of Computers，2016，39(175):1-19.)
[12]潘新，邓贵仕，刘建国.用户兴趣对个性化推荐的影响［J］.控制工程，2010，17(1):59-62.(Pan Xin，Deng Gui-shi，Liu Jian-guo.Effects of user tastes on personalized recommendation［J］.Control Engineering of China，2010，17(1):59-62.)
[13]Long X，Joshi J.A HITS-based POI recommendation algorithm for location-based social networks［C］// Proceedings of the ACM International Conference on Advances in Social Networks Analysis and Mining.Niagara Falls，2013:642-647.
[14]Hu Y，Koren Y，Volinsky C.Collaborative filtering for implicit feedback datasets［C］//IEEE International Conference on Data Mining.Pisa，2008:263-272.
[15]喻金平，朱桂祥，梅宏标. 基于Web链接分析的HITS算法研究与改进［J］.计算机工程与应用，2013 ，49(21):42-45.(Yu Jing-ping，Zhu Gui-Xiang，Mei Hong-Biao.Research and improvement of HITS algorithm based on Web link analysis［J］.Computer Engineering and Applications，2013，49(21):42-45.)
[16]孟迪.基于隐因子的逻辑回归推荐模型研究［D］.汕头:汕头大学，2015.(Meng Di.A research of recommendation model using logistic regression based on latent factors［D］.Shantou:Shantou University，2015.)