Computerized Assessment of Breast Lesion Malignancy using DCE-MRI: Robustness Study on Two Independent Clinical Datasets from Two Manufacturers

被引:42
作者
Chen, Weijie [1 ]
Giger, Maryellen L. [1 ]
Newstead, Gillian M. [1 ]
Bick, Ulrich [1 ]
Jansen, Sanaz A. [1 ]
Li, Hui [1 ]
Lan, Li [1 ]
机构
[1] Univ Chicago, Dept Radiol, Comm Med Phys, Chicago, IL 60637 USA
关键词
Computer-aided diagnosis; breast MRI; robustness; AIDED-DIAGNOSIS; DISCRIMINATING BENIGN; IMAGE INTERPRETATION; TEXTURE ANALYSIS; KINETIC CURVES; CLASSIFICATION; CANCER; FEATURES; STANDARDIZATION; OBSERVER;
D O I
10.1016/j.acra.2010.03.007
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
Rationale and Objectives: To conduct a preclinical evaluation of the robustness of our computerized system for breast lesion characterization on two breast magnetic resonance imaging (MRI) databases that were acquired using scanners from two different manufacturers. Materials and Methods: Two clinical breast MRI databases were acquired from a Siemens scanner and a GE scanner, which shared similar imaging protocols and retrospectively collected under an institutional review board-approved protocol. In our computerized analysis system, after a breast lesion is identified by the radiologist, the computer performs automatic lesion segmentation and feature extraction and outputs an estimated probability of malignancy. We used a Bayesian neural network with automatic relevance determination for joint feature selection and classification. To evaluate the robustness of our classification system, we first used Database 1 for feature selection and classifier training, and Database 2 to test the trained classifier. Then, we exchanged the two datasets and repeated the process. Area under the receiver operating characteristic curve (AUC) was used as a performance figure of merit in the task of distinguishing between malignant and benign lesions. Results: We obtained an AUC of 0.85 (approximate 95% confidence interval [CI] 0.79-0.91) for (a) feature selection and classifier training using Database 1 and testing on Database 2; and an AUC of 0.90 (approximate 95% CI 0.84-0.96) for (b) feature selection and classifier training using Database 2 and testing on Database 1. We failed to observe statistical significance for the difference AUC of 0.05 between the two database conditions (P=.24; 95% confidence interval -0.03, 0.1). Conclusion: These results demonstrate the robustness of our computerized classification system in the task of distinguishing between malignant and benign breast lesions on dynamic contrast-enhanced (DCE) MRI images from two manufacturers. Our study showed the feasibility of developing a computerized classification system that is robust across different scanners.
引用
收藏
页码:822 / 829
页数:8
相关论文
共 52 条
  • [1] American College of Radiology, 2003, ACR BIRADS BREAST IM
  • [2] [Anonymous], 1992, BAYESIAN METHODS ADA
  • [3] Breast MRI lesion classification: Improved performance of human readers with a backpropagation neural network computer-aided diagnosis (CAD) system
    Arbash Meinel, Lina
    Stolpen, Alan H.
    Berbaum, Kevin S.
    Fajardo, Laurie L.
    Reinhardt, Joseph M.
    [J]. JOURNAL OF MAGNETIC RESONANCE IMAGING, 2007, 25 (01) : 89 - 95
  • [4] Barrett H. H., 2003, Foundations of Image Science
  • [5] Bishop CM., 1995, NEURAL NETWORKS PATT
  • [6] Improvement of radiologists' characterization of mammographic masses by using computer-aided diagnosis: An ROC study
    Chan, HP
    Sahiner, B
    Helvie, MA
    Petrick, N
    Roubidoux, MA
    Wilson, TE
    Adler, DD
    Paramagul, C
    Newman, JS
    Sanjay-Gopal, S
    [J]. RADIOLOGY, 1999, 212 (03) : 817 - 827
  • [7] CHEN W, 2007, P SPIE, V6514
  • [8] Volumetric texture analysis of breast lesions on contrast-enhanced magnetic resonance images
    Chen, Weijie
    Giger, Maryellen L.
    Li, Hui
    Bick, Ulrich
    Newstead, Gillian M.
    [J]. MAGNETIC RESONANCE IN MEDICINE, 2007, 58 (03) : 562 - 571
  • [9] Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE-MRI
    Chen, Weijie
    Giger, Maryellen L.
    Bick, Ulrich
    Newstead, Gillian M.
    [J]. MEDICAL PHYSICS, 2006, 33 (08) : 2878 - 2887
  • [10] A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images
    Chen, WJ
    Giger, ML
    Bick, U
    [J]. ACADEMIC RADIOLOGY, 2006, 13 (01) : 63 - 72