Cancer detection from biopsy images using probabilistic and discriminative features
Atsushi Yaguchi, Takumi Kobayashi, Kenji Watanabe, Kenji Iwata, Tadaaki Hosaka, Nobuyuki Otsu · 2011
In the cancer detection from stained biopsy images, it is important to extract histologically discriminative characteristics. For this purpose, we propose a novel method to extract statistical and morphological features. At the first stage, we estimate cell component memberships at each pixel by applying an expectation maximization (EM) algorithm to the color information. Next we calculate the local co-occurrence of the memberships as image features. And then, linear discriminant analysis (LDA) is applied to those features for final decision of whether cancer or not, with enhancing the discrimination. In the experiments on real biopsy images of cancers, the resulting detection accuracy is superior to the other methods.