Zheng Yuanjie, Baloch Sajjad, Englander Sarah, Schnall Mitchell D, Shen Dinggang
Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.
Med Image Comput Comput Assist Interv. 2007;10(Pt 2):393-401. doi: 10.1007/978-3-540-75759-7_48.
Accuracy of automatic cancer diagnosis is largely determined by two factors, namely, the precision of tumor segmentation, and the suitability of extracted features for discrimination between malignancy and benignancy. In this paper, we propose a new framework for accurate characterization of tumors in contrast enhanced MR images. First, a new graph cut based segmentation algorithm is developed for refining coarse manual segmentation, which allows precise identification of tumor regions. Second, by considering serial contrast-enhanced images as a single spatio-temporal image, a spatio-temporal model of segmented tumor is constructed to extract Spatio-Temporal Enhancement Patterns (STEPs). STEPs are designed to capture not only dynamic enhancement and architectural features, but also spatial variations of pixel-wise temporal enhancement of the tumor. While temporal enhancement features are extracted through Fourier transform, the resulting STEP framework captures spatial patterns of temporal enhancement features via moment invariants and rotation invariant Gabor textures. High accuracy of the proposed framework is a direct consequence of this two pronged approach, which is validated through experiments yielding, for instance, an area of 0.97 under the ROC curve.
自动癌症诊断的准确性很大程度上由两个因素决定，即肿瘤分割的精度以及提取的特征对于区分恶性和良性的适用性。在本文中，我们提出了一种用于在对比增强磁共振图像中准确表征肿瘤的新框架。首先，开发了一种基于图割的新分割算法来细化粗略的手动分割，从而能够精确识别肿瘤区域。其次，通过将序列对比增强图像视为单个时空图像，构建分割肿瘤的时空模型以提取时空增强模式（STEP）。STEP旨在不仅捕获动态增强和结构特征，还捕获肿瘤逐像素时间增强的空间变化。虽然通过傅里叶变换提取时间增强特征，但所得的STEP框架通过矩不变量和旋转不变Gabor纹理捕获时间增强特征的空间模式。所提出框架的高精度是这种双管齐下方法的直接结果，通过实验验证，例如，ROC曲线下面积为0.97。
