Multifeature prostate cancer diagnosis and Gleason grading of histological images
Multifeature prostate cancer diagnosis and Gleason grading of histological images
复制标题
DOI：
10.1109/tmi.2007.898536
复制
发表时间：
2007-10-01
影响因子：
10.6
通讯作者：
Saidi, Olivier
中科院分区：
文献类型：
--
作者：
Tabesh, Ali;Teverovskiy, Mikhail;Saidi, Olivier
我们提出了一个研究的图像特征的癌症诊断和Gleason分级的组织学图像的前列腺。在诊断中，组织图像被分类为肿瘤和非肿瘤类。在表征肿瘤侵袭性的Gleason分级中，图像被分类为包含低级别或高级别肿瘤。本文中使用的图像集包括367和268彩色图像的诊断和Gleason分级问题，分别从苏木精和伊红染色的组织从组织微阵列核心或整个切片检索的代表性区域捕获。本文的主要贡献是聚合颜色，纹理和形态学的线索在全球和组织学的对象水平进行分类。代表不同视觉线索的特征被组合在监督学习框架中。我们比较了高斯分类器、k-最近邻分类器和支持向量机分类器以及顺序前向特征选择算法的性能。在诊断上，使用五倍交叉验证估计，获得了96.7%的准确性。在Gleason分级中，低等级和高等级分类的准确率为81.0%。
We present a study of image features for cancer diagnosis and Gleason grading of the histological images of prostate. In diagnosis, the tissue image is classified into the tumor and nontumor classes. In Gleason grading, which characterizes tumor aggressiveness, the image is classified as containing a low- or high-grade tumor. The image sets used in this paper consisted of 367 and 268 color images for the diagnosis and Gleason grading problems, respectively, and were captured from representative areas of hematoxylin and eosin-stained tissue retrieved from tissue microarray cores or whole sections. The primary contribution of this paper is to aggregate color, texture, and morphometric cues at the global and histological object levels for classification. Features representing different visual cues were combined in a supervised learning framework. We compared the performance of Gaussian, k-nearest neighbor, and support vector machine classifiers together with the sequential forward feature selection algorithm. On diagnosis, using a five-fold cross-validation estimate, an accuracy of 96.7% was obtained. On Gleason grading, the achieved accuracy of classification into low- and high-grade classes was 81.0%.