Computational Breast Imaging Group, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.
IEEE Trans Med Imaging. 2013 Apr;32(4):637-48. doi: 10.1109/TMI.2012.2219589. Epub 2012 Sep 19.
We present a methodological framework for multichannel Markov random fields (MRFs). We show that conditional independence allows loopy belief propagation to solve a multichannel MRF as a single channel MRF. We use conditional mutual information to search for features that satisfy conditional independence assumptions. Using this framework we incorporate kinetic feature maps derived from breast dynamic contrast enhanced magnetic resonance imaging as observation channels in MRF for tumor segmentation. Our algorithm based on multichannel MRF achieves an receiver operating characteristic area under curve (AUC) of 0.97 for tumor segmentation when using a radiologist's manual delineation as ground truth. Single channel MRF based on the best feature chosen from the same pool of features as used by the multichannel MRF achieved a lower AUC of 0.89. We also present a comparison against the well established normalized cuts segmentation algorithm along with commonly used approaches for breast tumor segmentation including fuzzy C-means (FCM) and the more recent method of running FCM on enhancement variance features (FCM-VES). These previous methods give a lower AUC of 0.92, 0.88, and 0.60, respectively. Finally, we also investigate the role of superior segmentation in feature extraction and tumor characterization. Specifically, we examine the effect of improved segmentation on predicting the probability of breast cancer recurrence as determined by a validated tumor gene expression assay. We demonstrate that an support vector machine classifier trained on kinetic statistics extracted from tumors as segmented by our algorithm gives a significant improvement in distinguishing between women with high and low recurrence risk, giving an AUC of 0.88 as compared to 0.79, 0.76, 0.75, and 0.66 when using normalized cuts, single channel MRF, FCM, and FCM-VES, respectively, for segmentation.
我们提出了一种多通道马尔可夫随机场（MRF）的方法框架。我们表明条件独立性允许有环置信传播将多通道 MRF 解耦为单通道 MRF。我们使用条件互信息来寻找满足条件独立性假设的特征。使用这个框架，我们将从乳腺动态对比增强磁共振成像中提取的动力学特征图作为 MRF 的观测通道，用于肿瘤分割。我们的基于多通道 MRF 的算法在使用放射科医生的手动勾画作为金标准时，肿瘤分割的接收者操作特征曲线下面积（AUC）达到 0.97。基于从与多通道 MRF 相同的特征池中选择的最佳特征的单通道 MRF 则获得了较低的 AUC（0.89）。我们还与归一化割分算法进行了比较，并与常用的乳腺肿瘤分割方法进行了比较，包括模糊 C-均值（FCM）和最近提出的基于增强方差特征的 FCM 方法（FCM-VES）。这些先前的方法的 AUC 分别为 0.92、0.88 和 0.60。最后，我们还研究了优越的分割在特征提取和肿瘤特征描述中的作用。具体来说，我们检查了改进的分割对基于验证的肿瘤基因表达测定来预测乳腺癌复发概率的影响。我们证明了基于我们算法分割的肿瘤提取的动力学统计量训练的支持向量机分类器在区分高复发风险和低复发风险的女性方面有显著的改善，AUC 为 0.88，而使用归一化割分、单通道 MRF、FCM 和 FCM-VES 时，AUC 分别为 0.79、0.76、0.75 和 0.66。
