Yu Elaine, Monaco James P, Tomaszewski John, Shih Natalie, Feldman Michael, Madabhushi Anant
Department of Biomedical Engineering, Rutgers University, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:3427-30. doi: 10.1109/IEMBS.2011.6090927.
In this paper we present a system for detecting regions of carcinoma of the prostate (CaP) in H&E stained radical prostatectomy specimens using the color fractal dimension. Color textural information is known to be a valuable characteristic to distinguish CaP from benign tissue. In addition to color information, we know that cancer tends to form contiguous regions. Our system leverages the color staining information of histology as well as spatial dependencies. The color and textural information is first captured using color fractal dimension. To incorporate spatial dependencies, we combine the probability map constructed via color fractal dimension with a novel Markov prior called the Probabilistic Pairwise Markov Model (PPMM). To demonstrate the capability of this CaP detection system, we applied the algorithm to 27 radical prostatectomy specimens from 10 patients. A per pixel evaluation was conducted with ground truth provided by an expert pathologist using only the color fractal feature first, yielding an area under the receiver operator characteristic curve (AUC) curve of 0.790. In conjunction with a Markov prior, the resultant color fractal dimension + Markov random field (MRF) classifier yielded an AUC of 0.831.
在本文中，我们提出了一种利用颜色分形维数在苏木精-伊红（H&E）染色的前列腺癌根治术标本中检测前列腺癌（CaP）区域的系统。颜色纹理信息是区分CaP与良性组织的一个有价值的特征。除了颜色信息外，我们还知道癌症倾向于形成连续区域。我们的系统利用了组织学的颜色染色信息以及空间依赖性。首先使用颜色分形维数来获取颜色和纹理信息。为了纳入空间依赖性，我们将通过颜色分形维数构建的概率图与一种名为概率成对马尔可夫模型（PPMM）的新型马尔可夫先验相结合。为了证明这种CaP检测系统的能力，我们将该算法应用于来自10名患者的27个前列腺癌根治术标本。首先仅使用颜色分形特征，由专家病理学家提供的真实数据进行逐像素评估，得到接收器操作特征曲线（AUC）下的面积为0.790。结合马尔可夫先验，所得的颜色分形维数+马尔可夫随机场（MRF）分类器的AUC为0.831。
