基于活动轮廓模型和影像组学的乳腺癌LVI状态预测

doi:10.12068/j.issn.1005-3026.2020.02.008

东北大学学报:自然科学版 ›› 2020, Vol. 41 ›› Issue (2): 193-199.DOI: 10.12068/j.issn.1005-3026.2020.02.008

基于活动轮廓模型和影像组学的乳腺癌LVI状态预测

冯宝^1,2，李昌林³，李智²，刘壮盛³

(1. 中山大学生物医学工程学院，广东广州511400; 2. 桂林航天工业学院电子信息与自动化学院，广西桂林541004; 3. 中山大学附属江门市中心医院放射科，广东江门529000)

收稿日期:2018-12-21 修回日期:2018-12-21 出版日期:2020-02-15 发布日期:2020-03-06
通讯作者: 冯宝
作者简介:冯明杰(1971-)，男，河南禹州人，东北大学副教授; 王恩刚(1962-)，男，辽宁沈阳人，东北大学教授，博士生导师.冯宝 (1986-)，男，山西太原人，中山大学博士后研究人员；李智 (1965-)，男，广西桂林人，桂林航天工业学院教授，博士生导师.
基金资助:
广西壮族自治区自然科学基金资助项目(2016GXNSFBA380160)；广西壮族自治区千名中青年骨干教师培育计划项目 (2018GXQGFB160)；国家自然科学基金地区科学基金资助项目(81960324).

Breast Cancer Related LVI Status Prediction Based on Active Contour Model and Radiomics

FENG Bao^1,2， LI Chang-lin³， LI Zhi²， LIU Zhuang-sheng³

1. School of Biomedical Engineering， Sun Yat-sen University， Guangzhou 511400， China; 2. School of Electronic Information and Automation， Guilin University of Aerospace Technology， Guilin 541004， China; 3. Department of Radiology， Affiliated Jiangmen Hospital of Sun Yat-sen University， Jiangmen 529000， China.

Received:2018-12-21 Revised:2018-12-21 Online:2020-02-15 Published:2020-03-06
Contact: LI Zhi
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对乳腺癌患者术前LVI状态预测问题，提出了活动轮廓模型和影像组学相结合的计算机辅助分析方法.首先，提出一种基于后验概率和模糊速度函数的活动轮廓模型方法来完成乳腺癌DCE-MRI图像分割.通过在小波域下构建基于后验概率的活动轮廓模型的区域项，同时利用模糊速度函数构建活动轮廓模型的边界项，可以提高乳腺癌病灶分割的准确性.其次，提取形态、灰度、纹理等图像特征，利用集成分类器随机森林方法构造LVI状态的预测模型.实验结果表明，所构建的模型对乳腺癌患者LVI状态具有较好的预测能力.

关键词: DCE-MRI, 乳腺癌, 活动轮廓模型, 影像组学, 图像分割, 图像分类

Abstract: To predict preoperative lymphovascular invasion(LVI)status of breast cancer patients， a computer-aided analysis method which combines an active contour model and radiomics is proposed. First， the image from dynamic contrast enhanced magnetic resonance imaging(DCE-MRI)of breast cancer is segmented by an active contour model(ACM)based on post probability and fuzzy velocity function. By constructing the region term of the active contour model based on post probability in the wavelet domain and the edge stop term of the active contour model by using the fuzzy velocity function， the accuracy of breast cancer lesion segmentation can be improved. Second， the image features such as morphology， grayscale and texture are extracted. Finally， a model for predicting LVI status is developed by the random forest classifier and its predictive ability is verified by experimental results.

Key words: DCE-MRI, breast cancer, active contour model, radiomics, image segmentation, image classification

中图分类号:

TP391.41

冯宝，李昌林，李智，刘壮盛. 基于活动轮廓模型和影像组学的乳腺癌LVI状态预测[J]. 东北大学学报:自然科学版, 2020, 41(2): 193-199.

FENG Bao， LI Chang-lin， LI Zhi， LIU Zhuang-sheng. Breast Cancer Related LVI Status Prediction Based on Active Contour Model and Radiomics[J]. Journal of Northeastern University Natural Science, 2020, 41(2): 193-199.

参考文献

[1]Fitzmaurice C，Allen C，Barber R M，et al.Global，regional，and national cancer incidence，mortality，years of life lost，years lived with disability，and disability-adjusted life-years for 32 cancer groups，1990 to 2015 ［J］.JAMA Oncology，2017，3(4):524-548.
[2]Dong Y，Feng Q，Yang W，et al.Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI［J］.European Radiology，2017，28(2):582-591.
[3]Torre L A，Bray F，Siegel R L，et al.Global cancer statistics，2012［J］.CA:A Cancer Journal for Clinicians，2015，65(2):87-108.
[4]Aleskandarany M A，Sonbul S N，Mukherjee A，et al.Molecular mechanisms underlying lymphovascular invasion in invasive breast cancer［J］.Pathobiology，2015，82(3/4):113-123.
[5]Paduch R.The role of lymphangiogenesis and angiogenesis in tumor metastasis［J］.Cellular Oncology，2016，39(5):397-410.
[6]Bae M S，Moon H G，Han W，et al.Early stage triple-negative breast cancer:imaging and clinical-pathologic factors associated with recurrence［J］.Radiology，2016，278(2):356-364.
[7]Uematsu T，Kasami M，Watanabe J，et al.Is lymphovascular invasion degree one of the important factors to predict neoadjuvant chemotherapy efficacy in breast cancer ?［J］.Breast Cancer，2011，18(4):309-313.
[8]Ryu J M，Lee S K，Kim J Y，et al.Predictive factors for non-sentinel lymph node metastasis in patients with positive sentinel lymph nodes after neoadjuvant chemotherapy:nomogram for predicting nonsentinel lymph node metastasis［J］.Clinical Breast Cancer，2017，17(7):550-558.
[9]Kumar V，Gu Y，Basu S，et al.Radiomics:the process and the challenges［J］.Magnetic Resonance Imaging，2012，30(9):1234-1248.
[10]刘桐桐，李佳伟，胡雨舟，等.基于影像组学预测乳腺癌雌激素受体表达情况的可行性分析［J］.生物医学工程学杂志，2017，34(4):597-601.(Liu Tong-tong，Li Jia-wei，Hu Yu-zhou，et al.Feasibility analysis of predicting expression of estrogen receptor in breast cancer based on radiomics［J］.Journal of Biomedical Engineering，2017，34(4):597-601.)
[11]吴佩琪，刘再毅，梁长虹.基于MRI的影像组学特征在鉴别乳腺浸润性导管癌病理分级中的价值［J］.医学研究生学报，2018，31(9):938-942.(Wu Pei-qi，Liu Zai-yi，Liang Chang-hong.MRI-based radiomic features in histological grading of breast invasive ductal carcinoma［J］.Journal of Medical Postgraduates，2018，31(9):938-942.)
[12]Huang Y H，Chang Y C，Huang C S，et al.Computerized breast mass detection using multi-scale hessian-based analysis for dynamic contrast-enhanced MRI［J］.Journal of Digital Imaging，2014，27(5):649-660.
[13]Fan M，He T，Zhang P，et al.Diffusion-weighted imaging features of breast tumours and the surrounding stroma reflect intrinsic heterogeneous characteristics of molecular subtypes in breast cancer［J］.NMR in Biomedicine，2018，31(2):e0189302.
[14]孙利雷，徐勇.基于深度学习的乳腺X射线影像分类方法研究［J］.计算机工程与应用，2018，54(21):13-19.(Sun Li-lei，Xu Yong.Research on classification method of mammography based on deep learning［J］.Computer Engineering and Applications，2018，54(21):13-19.)
[15]Boné B，Szabó B K，Perbeck L G，et al.Can contrast-enhanced MR imaging predict survival in breast cancer［J］.Acta Radiologica，2015，44(4):373-378.
[16]Achuthan A，Rajeswari M，Ramachandram D，et al.Wavelet energy-guided level set-based active contour:a segmentation method to segment highly similar regions［J］.Computers in Biology and Medicine，2010，40(7):608-620.
[17]Gianluca M，Matthias E，Katharina M，et al.Vessel suppressed chest computed tomography for semi-automated volumetric measurements of solid pulmonary nodules［J］.European Journal of Radiology，2018，101(5):97-102.
[18]Kokkinos I，Maragos P.Synergy between object recognition and image segmentation using the expectation maximization algorithm［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2009，31(8):1486-1501.
[19]Kwedlo W.A new random approach for initialization of the multiple restart EM algorithm for Gaussian model-based clustering［J］.Pattern Analysis & Applications，2015，18(4):757-770.
[20]Dong Y，Feng Q，Yang W，et al.Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI［J］.European Radiology，2018，28(2):582-591.
[21]Rose C J，Mills S，O’Connor J P B，et al.Quantifying heterogeneity in dynamic contrast-enhanced MRI parameter maps［J］.Medical Image Computing and Computer-Assisted Intervention，2010，62(2):488-499.
[22]Fan M，Wu G，Cheng H，et al.Radiomic analysis of DCE-MRI for prediction of response to neoadjuvant chemotherapy in breast cancer patients［J］.European Journal of Radiology，2017，94(2):140-147.
[23]张文华，陈韬，张明慧，等.基于放射组学的胃肠道间质瘤分类模型［J］.南方医科大学学报，2018，38(1):55-61.(Zhang Wen-hua，Chen Tao，Zhang Ming-hui，et al.A radiomics-based model for differentiation between benign and malignant gastrointestinal stromal tumors［J］.Journal of Southern Medical University，2018，38(1):55-61.)
[24]李祥霞，李彬，田联房，等.基于放射影像组学和随机森林算法的肺结节良恶性分类［J］.华南理工大学学报，2018，46(8):78-86.(Li Xiang-xia，Li Bin，Tian Lian-fang，et al.Classification of benign and malignant pulmonary nodules based on radiomics and random forests algorithm［J］.Journal of South China University of Technology，2018，46(8):78-86.)
[25]Dougherty E，Hua J，Sima C.Performance of feature selection methods［J］.Current Genomics，2009，10(6):365-374.
[26]Pripp A H，Staniic′ M.Association between biomarkers and clinical characteristics in chronic subdural hematoma patients assessed with lasso regression［J］.PloS One，2017，12(11):e0186838.
[27]Breiman L.Random forest［J］.Machine Learning，2001，45(1):5-32.
[28]郑强，董恩清.一种新的基于二值水平集和形态学的局部分割方法［J］.电子与信息学报，2012，34(2):375-381.(Zheng Qiang，Dong En-qing.A new local segmentation method based on binary level set and morphological operation［J］.Journal of Electronics & Information Technology，2012，34(2):375-381.)
[29]陈明，赵云，范能胜，等.医学图像分割中的主动轮廓模型研究现状［J］.北京生物医学工程，2010，29(4):426-431.(Chen Ming，Zhao Yun，Fan Neng-sheng，et al.A review of the active contour models in medical image segmentation［J］.Beijing Biomedical Engineering，2010，29(4):426-431.)

基于活动轮廓模型和影像组学的乳腺癌LVI状态预测

Breast Cancer Related LVI Status Prediction Based on Active Contour Model and Radiomics

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	魏颖，林子涵，齐林，李伯群. 基于空间自注意力机制和深度特征重建的脑MR图像分割方法[J]. 东北大学学报（自然科学版）, 2023, 44(2): 177-185.
[2]	方亮，周云，唐志泉. 基于优化的残差网络的锈蚀钢筋图像分类[J]. 东北大学学报（自然科学版）, 2021, 42(11): 1625-1633.
[3]	张田，田勇，王子，王昭东. 基于清晰度评价的自适应阈值图像分割法[J]. 东北大学学报:自然科学版, 2020, 41(9): 1231-1238.
[4]	李晨，张家伟，张昊，汪茜. 基于生成对抗网络的低分化宫颈癌病理图像分类[J]. 东北大学学报:自然科学版, 2020, 41(7): 1054-1061.
[5]	佘黎煌，郭一蓉，张石. 基于方向分数和Frangi滤波器的视网膜血管分割算法[J]. 东北大学学报:自然科学版, 2020, 41(2): 182-187.
[6]	马树军，方锐. 数字全息显微中的相位像差自动补偿算法[J]. 东北大学学报:自然科学版, 2020, 41(11): 1591-1595.
[7]	孙航，李宏，刘思琪，张伟. 基于双侧TIC定量特征的乳腺肿瘤良恶性鉴别[J]. 东北大学学报:自然科学版, 2019, 40(4): 473-477.
[8]	卢绍文，李鹏琦，郑秀萍，郭章. 动态火焰图像分割及在电熔镁炉视频监控中的应用[J]. 东北大学学报:自然科学版, 2019, 40(2): 153-158.
[9]	王洋，刘积仁，赵大哲，邱道云. 卷积神经网络在MRI图像诊断中的应用[J]. 东北大学学报:自然科学版, 2019, 40(2): 169-173.
[10]	陈红，于晓升，吴成东，孙鹏. 参数化水平集活动轮廓模型的快速图像分割算法[J]. 东北大学学报:自然科学版, 2019, 40(1): 6-10.
[11]	李宏，孙航，刘圣楠，潘诗农. 基于3D-CT图像的髋脱位定量智能诊断方法[J]. 东北大学学报:自然科学版, 2018, 39(2): 190-194.
[12]	魏颖，张开，韩枫. 改进的基于ASFCM婴幼儿脑部MRI分割算法[J]. 东北大学学报:自然科学版, 2017, 38(8): 1079-1084.
[13]	朴春赫，曹鹏，赵海，朱宏博. 基于CV模型与改进ME模型的肺癌检测算法[J]. 东北大学学报:自然科学版, 2017, 38(5): 639-644.
[14]	于晓升，胡楠. 基于局部灰度聚类的高斯分布拟合模型[J]. 东北大学学报:自然科学版, 2017, 38(2): 185-189.
[15]	徐礼胜，郭增智，覃文军，王璐. 心脏核磁共振图像左心室底层组织分割方法[J]. 东北大学学报:自然科学版, 2017, 38(10): 1383-1387.