Computational image analysis of mass lesions on dynamic contrast-enhanced breast MRI

This dissertation presents results of a medical image analysis project leading towards development of a comprehensive set of methods and tools for computational image analysis of dynamic contrast-enhanced (DCE) breast magnetic resonance image (MRI), with the aim to aid the physician in interpreting DCE breast MRI examinations. Toward this goal, we developed image analysis methods that would be needed in a breast MRI computer aided diagnosis (CADx) system. A novel contribution of this dissertation is the performance evaluation for each of the major algorithm components developed in this dissertation project. This dissertation begins with reviewing breast imaging techniques, including routinely used modalities in current clinical practice and emerging techniques still in development. We discuss at length the principles of DCE breast MRI, a very sensitive breast imaging modality that has been increasingly used in clinical practice. Then we review the diagnostic guidelines for interpreting DCE breast MRI, and explain the needs and challenges that arise in developing computational image analysis system for breast MRI applications. In this dissertation project, both the morphological and kinetic features of the lesion are automatically extracted for diagnostic purpose. In order to extract morphological features from the segmented lesions, the lesion needs to be accurately segmented out from its surrounding tissues. We utilized a probabilistic method to obtain an optimal segmentation map based on several algorithmic segmentation outputs. In evaluating the performance of segmentation algorithms, we compared the algorithmic segmentation results against manually segmented lesions, and further assessed the segmentation impact on subsequent classification stage. In order to extract accurate kinetic information, the motion needs to be compensated across image volumes acquired sequentially. In this dissertation, we comparatively assessed the similarity metric in registering DCE breast MR images. The performance of cross correlation(CC) coefficient, and mutual information (MI) were studied in both rigid and non-rigid registration schemes. Numerical results and statistical properties were reported. The resultant image quality after registration is discussed both qualitatively and quantitatively. In this dissertation we implemented a classification system based upon quantitative morphological and kinetic features in improving the specificity of breast MRI. Morphological and kinetic features of the lesion were extracted automatically, and then the feature selection step was utilized to select the most relevant features to maximize the classifier performance. In our study, the area under the receiver operating curve (AUC) is used as the performance metric of the classifier, and our results are competitive with those of previous studies. The dissertation concludes by summarizing the contribution of this project and suggesting the future directions of quantitative and highly automated approaches to breast MR image analysis.