Contrast-Enhanced Mammography and Radiomics Analysis for Noninvasive Breast Cancer Characterization: Initial Results

被引:65
作者
Marino, Maria Adele [1 ,2 ]
Pinker, Katja [1 ,3 ]
Leithner, Doris [1 ,4 ]
Sung, Janice [1 ]
Avendano, Daly [1 ,5 ]
Morris, Elizabeth A. [1 ]
Jochelson, Maxine [1 ]
机构
[1] Mem Sloan Kettering Canc Ctr, Dept Radiol, Breast Imaging Serv, 300 E 66th St, New York, NY 10065 USA
[2] Univ Messina, Dept Biomed Sci & Morphol & Funct Imaging, Messina, Italy
[3] Med Univ Vienna, Dept Biomed Imaging & Image Guided Therapy, Div Mol & Gender Imaging, Vienna, Austria
[4] Univ Hosp Frankfurt, Dept Diagnost & Intervent Radiol, Frankfurt, Germany
[5] ITESM Monterrey, Dept Breast Imaging, Breast Canc Ctr TecSalud, Monterrey, Nuevo Leon, Mexico
关键词
Mammography; Breast cancer; Contrast media; Biomarkers; Tumors; SPECTRAL MAMMOGRAPHY; DIGITAL MAMMOGRAPHY; MRI; CLASSIFICATION; HETEROGENEITY; FEASIBILITY; SUBTYPE; LESIONS; IMAGES; WOMEN;
D O I
10.1007/s11307-019-01423-5
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Purpose To investigate the potential of contrast-enhanced mammography (CEM) and radiomics analysis for the noninvasive differentiation of breast cancer invasiveness, hormone receptor status, and tumor grade. Procedures This retrospective study included 100 patients with 103 breast cancers who underwent pretreatment CEM. Radiomics analysis was performed using MAZDA software. Lesions were manually segmented. Radiomic features were derived from first-order histogram (HIS), co-occurrence matrix (COM), run length matrix (RLM), absolute gradient, autoregressive model, the discrete Haar wavelet transform (WAV), and lesion geometry. Fisher, probability of error and average correlation (POE+ACC), and mutual information (MI) coefficients informed feature selection. Linear discriminant analysis followed by k-nearest neighbor classification (with leave-one-out cross-validation) was used for pairwise texture-based separation of tumor invasiveness and hormone receptor status using histopathology as the standard of reference. Results Radiomics analysis achieved the highest accuracies of 87.4 % for differentiating invasive from noninvasive cancers based on COM+HIS/MI, 78.4 % for differentiating HR positive from HR negative cancers based on COM+HIS/Fisher, 97.2 % for differentiating human epidermal growth factor receptor 2 (HER2)-positive/HR-negative from HER2-negative/HR-positive cancers based on RLM+WAV/MI, 100 % for differentiating triple-negative from triple-positive breast cancers mainly based on COM+WAV+HIS/POE+ACC, and 82.1 % for differentiating triple-negative from HR-positive cancers mainly based on WAV+HIS/Fisher. Accuracies for differentiating grade 1 vs. grades 2 and 3 cancers were 90 % for invasive cancers (based on COM/MI) and 100 % for noninvasive cancers (almost entirely based on COM/MI). Conclusions Radiomics analysis with CEM has potential for noninvasive differentiation of tumors with different degrees of invasiveness, hormone receptor status, and tumor grade.
引用
收藏
页码:780 / 787
页数:8
相关论文
共 33 条
[1]   Computerized three-class classification of MRI-based prognostic markers for breast cancer [J].
Bhooshan, Neha ;
Giger, Maryellen ;
Edwards, Darrin ;
Yuan, Yading ;
Jansen, Sanaz ;
Li, Hui ;
Lan, Li ;
Sattar, Husain ;
Newstead, Gillian .
PHYSICS IN MEDICINE AND BIOLOGY, 2011, 56 (18) :5995-6008
[2]   Cancerous Breast Lesions on Dynamic Contrast-enhanced MR Images: Computerized Characterization for Image-based Prognostic Markers [J].
Bhooshan, Neha ;
Giger, Maryellen L. ;
Jansen, Sanaz A. ;
Li, Hui ;
Lan, Li ;
Newstead, Gillian M. .
RADIOLOGY, 2010, 254 (03) :680-690
[3]   MRI Phenotype of Breast Cancer: Kinetic Assessment for Molecular Subtypes [J].
Blaschke, Eric ;
Abe, Hiroyuki .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2015, 42 (04) :920-924
[4]   Classification of Breast Masses Using a Computer-Aided Diagnosis Scheme of Contrast Enhanced Digital Mammograms [J].
Danala, Gopichandh ;
Patel, Bhavika ;
Aghaei, Faranak ;
Heidari, Morteza ;
Li, Jing ;
Wu, Teresa ;
Zheng, Bin .
ANNALS OF BIOMEDICAL ENGINEERING, 2018, 46 (09) :1419-1431
[5]   Tomosynthesis and contrast-enhanced digital mammography: recent advances in digital mammography [J].
Diekmann, Felix ;
Bick, Ulrich .
EUROPEAN RADIOLOGY, 2007, 17 (12) :3086-3092
[6]   Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI [J].
Dong, Yuhao ;
Feng, Qianjin ;
Yang, Wei ;
Lu, Zixiao ;
Deng, Chunyan ;
Zhang, Lu ;
Lian, Zhouyang ;
Liu, Jing ;
Luo, Xiaoning ;
Pei, Shufang ;
Mo, Xiaokai ;
Huang, Wenhui ;
Liang, Changhong ;
Zhang, Bin ;
Zhang, Shuixing .
EUROPEAN RADIOLOGY, 2018, 28 (02) :582-591
[7]   Dual-energy contrast-enhanced digital mammography: initial clinical results [J].
Dromain, Clarisse ;
Thibault, Fabienne ;
Muller, Serge ;
Rimareix, Francoise ;
Delaloge, Suzette ;
Tardivon, Anne ;
Balleyguier, Corinne .
EUROPEAN RADIOLOGY, 2011, 21 (03) :565-574
[8]   Contrast-enhanced spectral mammography versus MRI: Initial results in the detection of breast cancer and assessment of tumour size [J].
Fallenberg, E. M. ;
Dromain, C. ;
Diekmann, F. ;
Engelken, F. ;
Krohn, M. ;
Singh, J. M. ;
Ingold-Heppner, B. ;
Winzer, K. J. ;
Bick, U. ;
Renz, D. M. .
EUROPEAN RADIOLOGY, 2014, 24 (01) :256-264
[9]   Radiomics in paediatric neuro-oncology: A multicentre study on MRI texture analysis [J].
Fetit, Ahmed E. ;
Novak, Jan ;
Rodriguez, Daniel ;
Auer, Dorothee P. ;
Clark, Christopher A. ;
Grundy, Richard G. ;
Peet, Andrew C. ;
Arvanitis, Theodoros N. .
NMR IN BIOMEDICINE, 2018, 31 (01)
[10]   Texture-based and diffusion-weighted discrimination of parotid gland lesions on MR images at 3.0 Tesla [J].
Fruehwald-Pallamar, Julia ;
Czerny, Christian ;
Holzer-Fruehwald, Laura ;
Nemec, Stefan F. ;
Mueller-Mang, Christina ;
Weber, Michael ;
Mayerhoefer, Marius E. .
NMR IN BIOMEDICINE, 2013, 26 (11) :1372-1379