Automated classification for pathological prostate images using AdaBoost-based Ensemble Learning

Abstract

We present an AdaBoost-based Ensemble Learning for supporting automated Gleason grading of prostate adenocarcinoma (PRCA). The method is able to differentiate Gleason patterns 4–5 from patterns 1–3 as the patterns 4–5 are correlated to more aggressive disease while patterns 1–3 tend to reflect more favorable patient outcome. This method is based on various feature descriptors and classifiers for multiple color channels, including color channels of red, green and blue, as well as the optical intensity of hematoxylin and eosin stainings. The AdaBoost-based Ensemble Learning method integrates the color channels, feature descriptors and classifiers, and finally constructs a strong classifier. We tested our method on the histopathological images and the corresponding medical reports obtained from The Cancer Genome Atlas (TCGA) using 10-fold cross validation, the accuracy achieved 97.8%. As a result, this method can be used to support the diagnosis on prostate cancer.